MEDICAL IMAGE DIAGNOSIS IN HEALTHCARE

UTILIZING A WEB APPLICATION

PHASE II REPORT
Submitted by

KESHAV SR 2116200701124
MITHILESH KUMAAR JS 2116200701145

in partial fulfillment for the award of the degree

of
BACHELOR OF ENGINEERING
IN
COMPUTER SCIENCE AND ENGINEERING

RAJALAKSHMI ENGINEERING COLLEGE, CHENNAI

ANNA UNIVERSITY :: CHENNAI 600 025

MAY 2024

i
 ANNA UNIVERSITY : CHENNAI 600 025

BONAFIDE CERTIFICATE

Certified that this project “Medical Image Diagnosis In Healthcare Utilizing A

Web Application” is the bonafide work of “KESHAV SR (200701124) and

MITHILESH KUMAAR JS (200701145)” who carried out the work under my

supervision. Certified further that to the best of my knowledge the work reported

herein does not form part of any other thesis or dissertation on the basis of which a

degree or award was conferred on an earlier occasion on this or any other

candidate.

SIGNATURE SIGNATURE

Dr. P. KUMAR, M.E.,Ph.D., Dr. P. SHANMUGAM M.Tech., Ph.D.,

HEAD OF THE DEPARTMENT SUPERVISOR

Associate Professor,

Department of Computer Science and Department of Computer Science and

Engineering, Engineering,

Rajalakshmi Engineering College, Rajalakshmi Engineering College,

Thandalam, Chennai - 602105. Thandalam, Chennai - 602105.

Submitted to Project Viva-Voce Examination held on. _____________________

INTERNAL EXAMINER EXTERNAL EXAMINER

ii
 ACKNOWLEDGEMENT

Initially we thank the Almighty for being with us through every walk of our life
and showering his blessings through the endeavor to put forth this report. Our
sincere thanks to our Chairman Mr. S.MEGANATHAN, B.E, F.I.E., our Vice
Chairman Mr. ABHAY SHANKAR MEGANATHAN, B.E., M.S., and our
respected Chairperson Dr. (Mrs.) THANGAM MEGANATHAN, Ph.D., for
providing us with the requisite infrastructure and sincere endeavoring in educating
us in their premier institution.

Our sincere thanks to Dr. S.N. MURUGESAN, M.E., Ph.D., our beloved
Principal for his kind support and facilities provided to complete our work in time.
We express our sincere thanks to Dr. P.KUMAR, M.E., Ph.D., Professor and Head
of the Department of Computer Science and Engineering for his guidance and
encouragement throughout the project work. We convey our sincere and deepest
gratitude to our internal guide, Dr. P.SHANMUGAM, M.Tech, Ph.D.,
Department of Computer Science and Engineering. Rajalakshmi Engineering
College for his valuable guidance throughout the course of the project. We are very
glad to thank our Project Coordinator, Mr. V.KARTHIK, M.tech(Ph.D)
Department of Computer Science and Engineering for his useful tips during our
review to build our project.

KESHAV SR

MITHILESH KUMAAR JS

ⅲ
 ABSTRACT

In today's world, the demand for medical diagnosis has become mandatory

and important in the field of medicine. The main idea behind clinical diagnosis is

to eliminate human error in clinical settings. Not only in medicine, but also in

many areas such as examining the earth with satellites and understanding all

activities in space. The motivation behind the development of this project is to help

doctors predict health problems using a simple website. The project aims to reduce

human error in medical image diagnosis, with the help of artificial neural networks

We also plan to improve user experience with a help of easy to use user interface

and by managing user history and preferences. The main purpose of the user

interface is to effectively communicate with the server and to produce the results to

the users in a human readable format. The data is processed and organized for

effective training of the model, and to make effective use of the data. The

technologies used here are convolutional neural networks, EfficientNetb3 for

image processing and Reactjs for web front-end. The data we use is image data.

The main problems faced by other tasks similar to image processing are

overfitting, hyperparameter sensitivity, and time consumption. Our projects help

eliminate all of the above. In general, we aim that doctors sometimes want the

fastest and quickest medical results for their patients. s

ⅳ
 TABLE CONTENT

CHAPTER NO TITLE PAGE NO.

ABSTRACT v

ACKNOWLEDGEMENT vi

LIST OF TABLES vii

LIST OF FIGURES viii

LIST OF ABBREVIATION ix

1 INTRODUCTION 1
1.1 OBJECTIVE 3
1.2 EXISTING SYSTEM 3

2 LITERATURE SURVEY 4
3 SYSTEM DESIGN 11
3.1 INTRODUCTION 11
3.2 SYSTEM OVERVIEW 11
3.3 DEVELOPMENT ENVIRONMENT 12
3.3.1 Hardware Requirement 12
3.3.2 Software Requirement 13
3.4 SYSTEM WORKFLOW 14
3.4.1 user login 15
3.4.2 Homepage and Image Upload 16
3.4.3 Image Upload and Processing 16
3.4.4 Diagnosis Process 16
3.4.5. Result Presentation 17
3.4.6. Data Safety and Privacy 17
3.4.7 Logout and User Management 17

v
4 PROJECT DESCRIPTION 18
4.1 METHODOLOGY 18

4.1.1 Data Collection 18

4.1.2 Data Labeling 19

4.1.3 Data Preprocessing 19

4.2 MODEL DEVELOPMENT AND

TRAINING 20

4.2.1 EfficientNet B3 20

4.2.2 Transfer Learning 20

4.2.3 Fine-tuning 20

4.2.4 Data Augmentation 21

4.2.3 Regularization 21

4.3. USER INTERFACE DEVELOPMENT 21

4.3.1 Front-End Development 21

4.3.2 Back-End Integration 22

4.3.3 Data Handling 22

4.4. MODULE DESCRIPTION 23

4.4.1 User Authentication Module 23

4.4.2 Photo Upload Module 23

4.4.3 Image Processing Module 23

5 RESULT AND DISCUSSIONS 25

6 CONCLUSION AND FUTURE 30

WORK
APPENDIX 31

REFERENCES 33

vi
 LIST OF TABLE

TABLE.NO TITLE PAGE NO

3.1 Hardware Requirements 13

3.2 Software Requirements 14

vii
 LIST OF FIGURES

FIGURE.NO TITLE PAGE NO

3.1 Flow of the project 12

3.2 System Workflow 15

4.1 EfficientNetB3 Architecture 20

4.2 Image Processing Model 24

viii
 LIST OF ABBREVIATIONS

HTML - HyperText Markup Language

CSS - Cascading Style Sheets

CNN - Convolutional Neural Network

MRI - Magnetic resonance imaging

CT - Computed Tomography Scan

ix
 CHAPTER 1

INTRODUCTION

In today's world, medical imaging uses digital technology and

advanced techniques to enhance, analyze and interpret medical images. It
includes a variety of measurement methods, from X-rays to MRI and CT
scans, and facilitates operations such as segmentation, feature extraction and
computer-aided diagnosis. Thanks to the combination of machine learning
and deep learning, it helps recognize the disease, plan treatment and predict
outcomes. In addition, 3D and 4D imaging technologies provide better
understanding and the use of telemedicine expands the scope of healthcare
services.

Image processing techniques aim to revolutionize healthcare by

enhancing the accuracy, efficiency, and usability of medical imaging. These
systems enable early detection of the disease, allowing timely and accurate
diagnosis. The system also helps in prevention of human errors in detection
of diseases and prevent any misdiagnosis. It supports individualized
treatment plans, reduces procedural complications and improves patient
outcomes. Medical imaging also extends medical care to areas underserved
by telemedicine and contributes to research and medical education. By
integrating intelligence, these systems help inform decision-making, increase
efficiency, engage patients, and ultimately control healthcare costs. The main
goal is to improve the quality of patient care, diagnosis and treatment while
making healthcare more efficient and patient-focused

1
 Convolutional Neural Network (CNN) is a deep learning model
designed for image processing and pattern recognition. It uses convolutional
layers to automatically learn hierarchical features of data. CNNs perform the
most accurate and adaptive computer vision tasks, including image
classification, object detection, and face recognition.

EfficientNet is a family of convolutional neural networks (CNN)

optimized for computer vision. It uses a combination of various techniques
to balance depth, width and resolution, making the model effective with
accuracy. EfficientNet is well-known in the deep learning community for its
ability to deliver high performance while using fewer computational
resources. EfficientNetB3 is a specific architecture of convolutional neural
networks (CNNs) that is part of the EfficientNet family of models. These
models are designed to be efficient and accurate for various computer vision
tasks, such as image classification, object detection, and segmentation. The
"B3" in EfficientNetB3 refers to a specific variant or scale of the
EfficientNet architecture.

This article aims to provide an overview of the system by touching on

its architecture, functionality and benefits. By exploring its potential and
practical applications, we aim to demonstrate the transformative power of
this technology, which integrates the highest level of intelligence with
humans to edit medical images. Through this research, we aim to
demonstrate the potential of this system to transform customer loyalty and
error-free operation in healthcare, ushering in a new era of efficiency and
consumer analysis.

2
1.1 OBJECTIVE
The primary goal of this project is to design and implement a
user-friendly website with the ability to function as a secondary diagnostic
tool for healthcare professionals. In particular, it will focus on the use of
medical imaging scans for accurate detection of various diseases. The
overarching purpose is not only to assist doctors in their diagnostic
processes, but also to mitigate the risk of misdiagnosis. By incorporating
advanced algorithms and technologies, the system aims to contribute to the
early detection of diseases.

1.2 EXISTING SYSTEM

The current system is challenged with inefficiency, overfitting, and the
use of outdated algorithms, leading to lower performance. Its user-unfriendly
interface prevents access by medical professionals, while data privacy
concerns reduce its reliability. To improve the system, it is recommended to
move to advanced algorithms such as CNN with EfficientNetB3 architecture
to increase accuracy and efficiency. Prioritizing a user-friendly interface,
implementing robust data encryption, and ensuring cost-effectiveness will all
contribute to a more efficient and reliable secondary diagnostic tool for
disease detection through medical imaging scans.

3
 CHAPTER 2

LITERATURE SURVEY

Tsung-Yu Lin et.al[1], discussed the architecture bilinear pooling to

combine the outer product of two features through global averaging,
resulting in a covariance matrix that captures pairwise interactions. When
these two features are identical, it leads to the creation of symmetric
B-CNNs, reminiscent of second-order pooling (O2P), a common technique
used in semantic segmentation However, this approach comes with some
limitations, including sensitivity to hyperparameters, risk of overfitting,
limited applicability to specific scenarios and problems in achieving
interpretable functions.

Ishani Dabral et.al [2], proposed Cancer Detection Using

convolutional neural network (CNN) architecture for cancer detection
focusing on the Invasive Ductal Carcinoma (IDC) dataset. This innovative
architecture combines convolutional, dropout, and fully connected layers
along with specific data preprocessing steps. However, it faces challenges
such as the demand for a large dataset, model complexity, excessive risks,
and the complexity of implementing transfer learning techniques.

Yu Hu and Yongkang Wong et.al [3], In A Novel Attention-Based

CNN-RNN Hybrid Architecture for sEMG-Based Gesture Recognition
(2018)[3], the proposed architecture combines convolutional neural
networks (CNNs) and recurrent neural networks (RNNs) with an attentional
mechanism that recognizes gestures based on surface electromyography

4
signals (sEMG). CNNs extract features from images, while RNNs,
especially Long Short-Term Memory (LSTM) units, model temporal
dependencies in data. An attention mechanism is introduced to highlight
relevant information in sEMG signals. The architecture uses a combination
of loss functions, including attention loss and target replication loss.

Wei Fang et.al[4] proposed a Deep Convolutional Generative

Adversarial Network (DCGAN) including a discriminative network and a
generative network, both consisting of four layers. The generator transforms
noise vectors into realistic samples, while the discriminator distinguishes
between real and generated data. The training process involves a non-convex
game, and an adaptive learning rate reduction strategy is used to increase the
training efficiency. However, this approach encounters several problems,
including training instability, regime collapse (where the generator produces
limited diversity), hyperparameter sensitivity, and the need for significant
computational resources due to its intensive nature.

Abien et.al[5] explores an experimental approach that combines SVM

and CNN for image classification. This hybrid architecture uses SVM for
binary classification, which determines the optimal hyperplane for
separating two classes. The study considers both L1-SVM and L2-SVM,
using the hinge loss as a standard loss function for SVM. However, this
paper highlights problems including a lack of comprehensive understanding,
potential bias and fairness issues, absence of moral or ethical considerations,
and long-term memory-related limitations in the classification process.

5
 Wentao Weia and Mohan Kankanhalli et.al[6]. An Image
Classification Algorithm using AlexNet, the authors present a method for
image classification using an improved version of the AlexNet convolutional
neural network (CNN). This approach solves the problem of traditional
CNNs with a high number of parameters, especially in fully connected
layers, which can lead to problems such as overfitting and increased
computational complexity. The proposed enhancement introduces
deconvolution layers into the AlexNet architecture, effectively reducing the
number of parameters, especially in the fully connected layer. However, it is
important to note that this improvement comes with increased computational
complexity, the risk of overfitting due to model complexity, and the
requirement for a significant amount of labeled training data. Achieving a
balance between these factors is essential for successful implementation of
the improved AlexNet-based image classification algorithm.

Yanan Sun, et.al[7], presented a method that uses a genetic algorithm

(GA) to automatically optimize the architecture of convolutional neural
networks (CNN). The process starts by initializing a population of CNN
architectures, encoding them using skip and pooling layers and omitting
fully connected layers. Although this approach appears promising, it faces
challenges, including reproducibility issues, domain knowledge requirement,
cross-domain transferability difficulties, generalizability limitations, and
data and time resource requirements.

Shengyi Zhao, et.al[8] presented an attention module to improve

model performance with minimal computational cost. This module uses the
Squeeze-and-Excitation Networks (SENet) method, which automatically

6
assigns weight coefficients to feature channels based on their importance.
This recalibration process reinforces relevant feature channels while
suppressing irrelevant ones. However, this approach comes with problems,
including computational complexity, reduced interpretability, and the need
for careful hyperparameter tuning.

Li X, Xu Z, Shen X et.al[9], In Improved Classification of MRI

Images for Cervical Cancer Using CONVOLUTIONAL NEURAL
NETWORKS the paper presents an approach for the automatic identification
of hepatocellular carcinoma. It uses an ensemble learning strategy with
seven machine learning algorithms and uses collaborative representation
classification with a boosting technique to categorize hyperspectral images.
However, this method faces challenges, including a lack of domain
knowledge and potential limitations in portability to different domains.

Yiwen Liu, et.al[10] presented the paper that outlines the

methodology for identifying crop diseases and insect pests. It uses transfer
learning with VGG16 and Inception-ResNet-v2 (CNN) convolutional neural
networks. However, this approach faces challenges, including resource
intensiveness, the need for model updates, and complexity associated with
fine-tuning.
Sota Kato, et.al[11] proposed a study involving 50 cell images with
ground truth provided by Kyoto University. These images are obtained using
a fluorescent marker on the cell membrane and nucleus of mouse liver and
are 256×256 pixels in size. Among these images, 40 were used for training,
five for validation, and the remaining five for testing. However, it should be

7
noted that the proposed method did not significantly improve the cell
membrane segmentation accuracy.

Fetulhak Abdurahm et.al[12], proposed Image Processing for Malaria

Screening Using Deep Learning . The study aims to improve the detection of
P. falciparum in thick-smear microscopic images using an advanced deep
learning object . detection models. The aim is to address the challenges that
were previously identified in this context. To achieve this, the paper
proposes a tile-based image processing approach that enables better
detection of small objects in high-resolution images that exceed the input
resolution limits of the network. However, it should be noted that this
method may not achieve a very high level of detection performance,
especially when resizing the high-resolution input image for detection.

Md. Ashiq Mahmood and Tamal Joyti Roy et.al[13], conducted an

experiment involving image analysis to establish an assessment process for
identifying COVID-19-related lung infection. This approach first involves
analyzing the images without converting them into binary segments.
Subsequently, the authors convert normal images into binary and collect the
relevant values. The experiment also uses parameter-based neural networks.
However, one of the challenges facing this study is the availability of
insufficient datasets for comprehensive analysis. Image division is controlled
by local segmentation.

Soto Kato and Kazuhiro Hotta et.al [14], proposed a study using 50
cell images that come with ground truth data provided by Kyoto University.
These images are captured using a fluorescent marker on the cell membrane

8
and nucleus of a mouse liver with a size of 256×256 pixels. Of these images,
40 were allocated for training, five for validation and the remaining five for
testing. However, it was observed that the proposed method did not
significantly improve the cell membrane segmentation accuracy.

Kumar, et.al[14] proposed a facial recognition system using Local

Binary Pattern algorithm; it focuses on local patterns, comparing each pixel
to its neighbors and encoding the results into a binary format. This method
might be sensitive to change in the lighting and the change in poses. While
efficientNetB3 being a deep learning model can learn the hierarchical
features in an efficient way, and can handle the change in pose, expressions
and lighting.

Bai B, Du Y, Liu P et.al [15]. Convolutional Neural Network with

Wavelet Domain Inputs[15] the model starts with an RGB input that
transforms images into 448x448 YCbCr format. It then applies a 3-level
Wavelet Packet Transform (WPT) or Dual-Tree Complex Wavelet
Transform (DTCWT) to generate 192 channels. To mitigate noise and
computational complexity, it selects and consolidates key channels into a
Cx56x56 tensor. This modified tensor is then processed by the ResNet-50
model, which adapts to the changing C to improve the classification
performance, especially focusing on low-frequency information. A challenge
highlighted in the study is the absence of a suitable data set for this approach
and insufficient frequency.

9
Ahmad Yahya Dawod, Aniwat Phaphuangwittayakul and Salita
Angkurawaranon et.al[16] , in 2022 involves a series of steps, including
image acquisition, preprocessing, Simple Linear Iterative Clustering (SLIC)
, edge detection, region growing, dilation and hybrid method. However, this
approach has certain drawbacks, including resource-intensiveness, the need
for model updates, and the complexity associated with fine-tuning the
methodology.

10
 CHAPTER 3

SYSTEM DESIGN

3.1 INTRODUCTION
The primary objective of this new system is to reduce the challenges
associated with human error in medical image diagnosis. This solution
includes an user-friendly interface to improve accessibility and speed up the
diagnostic process. Basically, the system uses a deep learning model that
combines the powerful EfficientNetB3 architecture with Convolutional
Neural Networks (CNN). By using these technologies, the system aims to
dramatically increase the accuracy and efficiency of medical image
interpretation, ultimately leading to better patient outcomes and a more
robust diagnostic process.

3.2 SYSTEM OVERVIEW

The web application for medical image diagnosis leverages a
technology stack that combines the front-end capabilities of React.js for a
responsive and dynamic user interface with the back-end powered by
Python, utilizing Flask as the web framework, and TensorFlow for deep
learning with the EfficientNetB3 model. This seamlessly integrated tech
stack enables users to upload medical images and submit relevant
information, and the system's Flask-based server facilitates the interaction
between the front-end and the deep learning model, allowing for efficient
image processing and diagnosis, while also ensuring data security and
scalability.

11
 Figure 3.1 Flow of the project

3.3 DEVELOPMENT ENVIRONMENT

3.3.1 HARDWARE REQUIREMENT

In order to ensure optimal performance of the proposed secondary
diagnostic tool using CNN with EfficientNetB3, careful attention must be
paid to the hardware requirements. A robust computing infrastructure that
includes powerful GPUs is essential to accelerate the complex computations
involved in training and operating deep neural networks. The
computationally intensive EfficientNetB3 architecture benefits from GPUs
with parallel processing capabilities. In addition, sufficient RAM is essential
to efficiently work with large datasets and model parameters. The storage
capacity should accommodate the storage of extensive medical imaging
data.

12
 Component SPECIFICATION

GPU 4GB or Higher

RAM 8GB or Higher

Storage Minimum 256GB

Monitor Higher Definition Monitor

Table 3.1 Hardware Requirements

3.3.2 SOFTWARE REQUIREMENT

Software requirements are key because they define the necessary

components and conditions for the successful development and deployment
of a secondary diagnostic tool. It guides the choice of operating system,
programming language, deep learning frameworks and web development
tools, ensuring compatibility and optimal performance. The choice of
software components directly affects the tool's functionality, user interface
and overall reliability.

13
 Component SPECIFICATION

OS Windows, Macos, or Linux

Front-end React.js and Material UI

Backend Python and MongoDB

Middleware Flask and Node.js

Table 3.2 Software Requirements

3.4 SYSTEM WORKFLOW

The user will not have the option to register, which is done to prevent
unwanted access. With the help of the login credentials, the user can log in
to the system. After logging in, the user can select an imaging scan based on
the illness. Subsequently, the user will choose which disease to diagnose.
The user must upload the image scan, and the uploaded image will be sent to
the backend using a Python deep-learning model with the assistance of
middleware. The API is developed with Flask. Following this, the prediction
is made, and the predicted result is then presented to the user in a format that
is easily readable.

14
 Figure 3.2 System Workflow

3.4.1 USER LOGIN

Upon accessing the application, users are presented with the login
screen. Here, users input their credentials, typically consisting of an email
address and password, which are securely verified for authentication. Once
successfully logged in, users gain access to the application's features.

15
3.4.2 HOMEPAGE AND IMAGE UPLOAD

Upon successful login, users are directed to the application's

homepage, which serves as the central hub for initiating the diagnosis
process. The homepage is designed to be intuitive and user-friendly,
featuring a conspicuous Upload Image button or area where users can easily
select and submit their medical images for analysis. This step is crucial for
initiating the diagnosis process and streamlining the user experience.

3.4.3 IMAGE UPLOAD AND PROCESSING

The image upload and processing stage is a critical part of the

workflow, ensuring that the system can efficiently analyze medical images.
Users are guided to click the Upload Image button, followed by the selection
of a medical image from their device. Once uploaded, the system proceeds
to process the image for further analysis. This preprocessing may include
resizing and normalization to ensure the image is in the appropriate format
and size required by the machine learning model.

3.4.4 DIAGNOSIS PROCESS

After the image is submitted, the image is handed over to the deep
learning model, EfficientNetB3, for the actual diagnosis. The model
analyzes the image to generate a prediction for the medical condition and
produces a confidence score to assess the certainty of the diagnosis. This
step is the core of the application, where the machine learning model
leverages its capabilities to provide valuable medical insights.

16
3.4.5. RESULT PRESENTATION

The diagnosis results are presented to the user in a user-friendly and

understandable format. This presentation includes the predicted medical
condition, the associated confidence score.

3.4.6. DATA SAFETY AND PRIVACY

Throughout the workflow, robust data safety and privacy measures are
upheld. This includes secure data transmission protocols, temporary data
storage during the user's session, and user authentication. The application
prioritizes data protection to safeguard sensitive patient information and
medical images, following industry standards and regulations to ensure user
data remains confidential and secure.

3.4.7 LOGOUT AND USER MANAGEMENT

Users have the option to log out of their accounts when they have
completed the diagnosis.The application offers user management features
that empower users to maintain their accounts, including the ability to reset
passwords and configure account settings. This provides a seamless and
user-centric experience while allowing users to have control over accounts.

17
 CHAPTER 4

PROJECT DESCRIPTION

4.1 METHODOLOGY

The Flow of the project diagram depicts how different frameworks

interact with each other, and how it is effective in achieving the desired
result. It helps in understanding how the response is sent and and response is
sent to the user. The System workflow diagram is used to achieve the
understanding of how different components interact with each other. It helps
the stakeholders to understand how the different components of the system
work.

It helps in understanding how the errors are handled and how the data
flows, and how the system will interact with the user when a failure occurs.
It is helpful when development is underway.

4.1.1 DATA COLLECTION

Collecting medical images for feeding into an AI model is a

fundamental step in developing healthcare diagnostic or analytical tools.
This process initiates with the acquisition of medical images using
specialized equipment, like X-ray machines, MRI scanners, or ultrasound
devices. Ensuring equipment accuracy and quality through regular
maintenance and calibration is critical to obtain reliable data. Alongside the
images, patient data, including demographic details, medical history, and
clinical context, must be collected while adhering to healthcare regulations
and ethical standards to protect patient privacy and data security.

18
4.1.2 DATA LABELING

Manual annotation is often required for medical images, involving the

identification of regions of interest (ROIs) and abnormalities. Expert
radiologists or trained annotators typically perform this task to ensure the
quality and accuracy of labeled data. Establishing ground truth data with
accurate annotations and diagnoses for each image is crucial, forming the
basis for training the AI model and enabling it to make diagnostic
predictions.

4.1.3 DATA PREPROCESSING

Data preprocessing techniques, such as noise reduction,normalization,

and augmentation, are employed to enhance image quality and standardize
the data. Medical images can be noisy due to various factors, and mitigating
noise is essential for model accuracy. Ensuring consistent intensity and
resolution across images is necessary for accurate analysis. Data
augmentation techniques like rotation and brightness adjustments increase
dataset diversity, aiding the AI model in making more reliable predictions.
Image registration is also applied when dealing with multiple image
modalities or images taken at different times.

19
4.2 MODEL DEVELOPMENT AND TRAINING

4.2.1 EfficientNet B3

EfficientNet is a family of CNN architectures designed for efficient

and effective deep learning. EfficientNet B3 is known for its good balance
between model size and performance, making it suitable for a wide range of
computer vision tasks, including medical image analysis.

Fig 4.1 EfficientNetB3 Architecture

4.2.2 TRANSFER LEARNING

Leveraging pre-trained models like EfficientNet B3 is a common

approach in deep learning. You can use weights from pre-trained models on
large image datasets (e.g., ImageNet) as a starting point for your medical
image analysis task. This can significantly speed up training and potentially
improve performance, especially if you have limited labeled medical data.

4.2.3 FINE-TUNING

After initializing your model with pre-trained weights, fine-tuning the

model on your medical image dataset is essential. Adjust the top layers of
the model to adapt it to your specific task. You might need to modify the
output layer to match the number of classes in your diagnostic task.

20
4.2.4 DATA AUGMENTATION

Augment your dataset during training by applying transformations

like rotation, scaling, and flipping. Data augmentation helps your model
generalize better and become robust to variations in input data.

4.2.5 REGULARIZATION

To prevent overfitting, consider adding regularization techniques such

as dropout and weight decay to the model. EfficientNet B3 has a significant
number of parameters, and regularization can help improve generalization.

4.3. USER INTERFACE DEVELOPMENT

4.3.1 FRONT-END DEVELOPMENT

In the context of this project, front-end development entails creating a

web-based user interface using React.js. The primary focus is on designing a
responsive, user-friendly layout that accommodates various devices and
screen sizes, making it easy for healthcare professionals to navigate the
system, upload medical images, and access diagnostic results efficiently.

21
4.3.2 BACK-END INTEGRATION

The integration of the React.js front-end with the Flask back-end is a

crucial aspect of this project, ensuring secure data transfer during image
uploads and subsequent processing. This integration involves establishing
API endpoints for communication between the two components, enabling
actions such as image upload and result retrieval. Additionally, it may
facilitate real-time updates to provide users with timely feedback as the
system processes and analyzes medical images.

4.3.3 DATA HANDLING

The front-end user interface is responsible for facilitating user

interactions with medical images and diagnostic results. It allows users to
intuitively upload medical images, offering clear instructions for this
process. Moreover, it presents diagnostic outcomes in a comprehensible
format. User feedback mechanisms may be integrated to enable users to
report issues or provide comments, enhancing user engagement and
contributing to ongoing system quality improvement.

22
4.4 MODULE DESCRIPTION

4.4.1 USER AUTHENTICATION MODULE

In this module the user authentication is being implemented, in which
the user can login using the email, and the password. The credentials will be
provided. The password of the users is hashed so that it’s secured. And the
Registration process is removed so that the unwanted access can be
prevented. The user authentication will be implemented using Node.js and
MongoDB, and for security JWT tokens are used to prevent unwanted
access.

4.4.2 PHOTO UPLOAD MODULE

After selecting the imaging scan the user will have to select the
diagnosis. After which the user can select a single image which should be
uploaded to the server. And the image will be previewed in the front-end.
The front-end is developed using a Javascript library React.js. The uploading
of the image is done after the validation of the image type in the front-end.

4.4.3 IMAGE PROCESSING MODULE

After submitting the image, it is transmitted to the backend using a
Python model, and the transmission is facilitated through a middleware. The
image transmission is secured and encrypted. The transmitted image
undergoes processing in the convolutional layer, where kernels detect
patterns and study features. Subsequently, the activation function is applied
to the feature map to introduce non-linearity. Dimensions are reduced in the
pooling layer. The feature map is then flattened and forwarded to the fully
connected layer, which learns high-level features and patterns. Finally, the

23
output layer produces the final result.

Figure 4.2 Image Processing Model

24
 CHAPTER 5

RESULT AND DISCUSSION

After logging into the system, the user will be led to the homepage. Where
the user gets to know about our website. Once they click on then upload
your scan button it leads to a page where you can select an imaging scan for
the appropriate imaging. The front-end is done using the Javascript library
react.js and MaterialUI.

Figure 5.1 Landing Page

25
 Figure 5.2 Home Page

After selecting the imaging the user has to select which diseases to diagnose.
The diagnoses are specific to the imaging scans and they each have their
own AI model trained and running in the background.

Figure 5.3 List of diagnosis

The image is selected in the front-end. The image is submitted which is sent
to the back-end python model, through the flask middle-ware which is
hosted on the web. The python model is trained using CNN and efficientB3
and the weights of the pre-trained imagenet weights .

26
 Figure 5.4 Image-upload field

The predictions are shown to the user in a presentable way, in a human

readable format. The image is sent to the server and the result is obtained
using the standard api calls.

27
 Figure 5.5 result of prediction

Figure 5.6 Line Graph Comparison

We evaluated the performance of EfficientNetB3, a smaller version of

EfficientNet, and ResNet-50 on the CIFAR-10 dataset. EfficientNetB3
achieved an accuracy of 79%, while ResNet-50 attained an accuracy of 77%.
EfficientNetB3 demonstrated a higher efficiency with an accuracy close to
the larger EfficientNet-B3 but trained considerably faster than ResNet-50.
This suggests that EfficientNetB3 strikes a balance between model
complexity and performance, offering competitive accuracy with improved
efficiency compared to both larger EfficientNet variants and ResNet-50.

Figure 5.7 Training the Model

28
 Figure 5.8 Testing the Model

Figure 5.9 Prediction with normal liver MRI

Figure 5.10 Prediction with cancerous liver MRI

When the model was tested with Liver MRIs it yielded an accuracy of 87%,
and the prediction accuracy was 84%. The dataset used had 317 even
distributed images for both test and train data.

29
 CHAPTER 6

CONCLUSION AND FUTURE WORK

6.1 CONCLUSION

In the culmination of this project, we have successfully developed a

user-centric medical image diagnosis web application. By removing the
registration step, we have ensured a user-friendly and expedited login
process, allowing users to quickly access the application's features. This
streamlined workflow, coupled with efficient image processing and clear
result presentation, facilitates prompt and comprehensive medical image
diagnoses. The integration of the EfficientNetB3 deep learning model
enhances the accuracy and reliability of the results, contributing to informed
healthcare decisions. As we move forward, ongoing monitoring and
maintenance will be essential to uphold the application's continued reliability
and accuracy. This project exemplifies the delicate balance between
user-friendliness and data security, underlining its potential as a valuable
tool in the realm of healthcare, benefiting both medical professionals and
patients.

6.2 FUTURE WORK

In the future we would like to expand the idea to a phase where it will also
detect the stage of the disease, and book appointments to the relevant section
based on the severity. And the user can set reminders based on the
medications and appointments. We would like to make this system smart
enough to recommend diagnosis in the future.

30
 APPENDIX
SAMPLE CODE:
The below code is the model that was used to train the models for this project. The
model has EfficientNetB3 architecture, as the base model.

base_model = tf.keras.applications.EfficientNetB3(weights='imagenet',
input_shape=(224, 224, 3), include_top=False)

for layer in base_model.layers:

layer.trainable=False
model = Sequential()
model.add(base_model)
model.add(GaussianNoise(0.25))
model.add(GlobalAveragePooling2D())
model.add(Dense(256,activation='relu'))
model.add(BatchNormalization())
model.add(GaussianNoise(0.25))
model.add(Dropout(0.25))
model.add(Dense(2, activation='softmax'))
from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping
es=EarlyStopping(patience=3,monitor='val_loss')
filepath='best_model.h5'
checkpoint = ModelCheckpoint(filepath, monitor='val_accuracy', verbose=1,
save_best_only=True, mode='max')
history = model.fit(
train_generator,
epochs=15,

31
 validation_data=validation_generator,
steps_per_epoch= 10,
callbacks=checkpoint
)
model = tf.keras.models.load_model('/content/best_model.h5')
model.evaluate(validation_generator)

32
 REFERENCES

[1] Lin, Tsung-Yu and Subhransu Maji. “Improved Bilinear Pooling with
CNNs.” ArXiv abs/1707.06772, 2017

[2] Ishani Dabral,Maheep Singh,Krishan Kumar, “Cancer Detection using

CNN ”, Volume.175, pp. 290-298.

[3] Hu Y, Wong Y, Wei W, Du Y, Kankanhalli M, Geng W (2018) A novel

attention-based hybrid CNN-RNN architecture for sEMG-based gesture
recognition. PLoS ONE 13(10): e0206049.

[4] Wei Fang, Feihong Zhang1, Victor S. Sheng3 and Yewen Ding1. A
Method for Improving CNN-Based Image Recognition Using DCGAN, vol.
57, pp. 167–178, 2018

[5] Agarap, Abien Fred. “An Architecture Combining Convolutional Neural

Network (CNN) and Support Vector Machine (SVM) for Image
Classification.” ArXiv abs/1712.03541, 2017

[6] Shaojuan Li, Lizhi Wang, Jia Li and Yuan Yao. Image Classification
Algorithm Based on Improved AlexNet. 2020 International Conference on
Modeling, Big Data Analytics and Simulation (MBDAS2020) 20-21
December 2020, Xiamen, China

33
[7] Y. Sun, B. Xue, M. Zhang, G. G. Yen and J. Lv, "Automatically
Designing CNN Architectures Using the Genetic Algorithm for Image
Classification," in IEEE Transactions on Cybernetics, vol. 50, no. 9, pp.
3840-3854, Sept. 2020, doi: 10.1109/TCYB.2020.2983860.

[8] Zhao, S.; Peng, Y.; Liu, J.; Wu, S. Tomato Leaf Disease Diagnosis Based
on Improved Convolution Neural Network by Attention Module. Agriculture
2021, 11, 651. https://doi.org/10.3390/agriculture 11070651

[9] S. Gowri, Judith Justin and R. Vanithamani. S. Gowri, Judith Justin and
R. Vanithamani. AN IMPROVED CLASSIFICATION OF MR IMAGES
FOR CERVICAL CANCER USING CONVOLUTIONAL NEURAL
NETWORKS DOI: 10.21917/ijivp.2021.0369

[10] Liu Y, Zhang X, Gao Y, Qu T, Shi Y. Improved CNN Method for Crop
Pest Identification Based on Transfer Learning. Comput Intell Neurosci.
2022 Mar 16;2022:9709648. doi: 10.1155/2022/9709648. PMID: 35341164;
PMCID: PMC8942633.

[11] Sota Kato Kazuhiro Hotta Cell Segmentation by Image-to-Image

Translation using Multiple Different Discriminators. published in 2022,
DOI:10.5220/0009170103300335

[12] Fetulhak Abdurahm Kinde Anlay Fante. Tile-based microscopic image

processing for malaria screening using deep learning approach. BMC Med

34
Imaging. 2023; 23: 39. Published online 2023 Mar 22. doi:
10.1186/s12880-023-00993-9

[13] Md. Ashiq Mahmood, Tamal Joyti Roy, Md Ashiqul Amin, Diti Roy,
Aninda Mohanta and Fatama Fayez Dipty,“A Hybrid Approach to Find
COVID-19 Related Lung Infection Utilizing 2 Bit Image Processing”,
International Conference on Innovative Computing and Communications.
Advances in Intelligent Systems and Computing (ICICC 2022), 2022

[14] K. P, S. L. T. A and S. R, "Face Recognition Attendance System Using

Local Binary Pattern Algorithm," 2023 2nd International Conference on
Vision Towards Emerging Trends in Communication and Networking
Technologies (ViTECoN), Vellore, India, 2023, pp.1-6, doi:
10.1109/ViTECoN58111.2023.10157843.

[15] Wang, L. and Sun, Y. (2022). Image classification using convolutional

neural networks with wavelet domain inputs. IET Image Processing, 16(8),
2037-2048. https://doi.org/10.1049/ipr2.12466

[16] Ahmad Yahya Dawod Aniwat Phaphuangwittayakul Salita

Angkurawaranon. A hybrid method for traumatic brain injury lesion
segmentation. v12i2. pp1437-1448

35
 PUBLICATION

PHASE-I

P. Shanmugam , Keshav SR, Mithilesh Kumaar JS (2024), “Improve Medical

Image Diagnosis in Healthcare Utilizing a Framework for the Web
Application”, International Conference on Smart Technology, Artificial
Intelligence and Computer Engineering (ICSTAICE-2023), paper got accepted
and published.

36
 PHASE-II

P. Shanmugam , Keshav SR, Mithilesh Kumaar JS (2024), “Medical Image

Diagnosis In Healthcare Utilizing A Web Application”, was submitted to
5th IEEE India Council International Subsections Conference 2024.

37
REPORT PLAGIARISM:

38
 Improve Medical Image Diagnosis In
Healthcare Utilizing A Framework For The
Web Application

Dr.P.Shanmugam Keshav SR Mithilesh Kumaar JS

Assistant Professor Student Student
Department of Department of Department of
Computer Science and Computer Science and Computer Science and
Engineering Engineering Engineering
Rajalakshmi Engineering Rajalakshmi Engineering Rajalakshmi Engineering
College Chennai, India College Chennai, India College Chennai, India
[email protected] [email protected]. [email protected].
du.in in in

ABSTRACT: The need for precise and effective medical diagnosis has grown in importance in the healthcare industry in
today's fast-paced world.. The core concept driving clinical diagnosis is to minimize human error in medical settings, a
principle that extends beyond healthcare to other domains such as earth observation via satellites and comprehending
activities in outer space. The primary motivation behind the development of our project lies in providing doctors with a
reliable tool to predict and address potential health issues through a user-friendly web platform. Additionally, we aim to
enhance the overall user experience by implementing features that manage user history and preferences. The technologies at
the heart of our solution involve cutting-edge convolutional neural networks (CNN) and the powerful EfficientNet B3 for
image processing, combined with the versatility of React.js for crafting an interactive web front-end. Our project is firmly
grounded in image data, addressing common challenges in image processing, including overfitting, hyperparameter
sensitivity, and time consumption. By tackling these issues head-on, we aim to empower medical professionals with rapid and
accurate diagnostic results, aligning with their need for swift decision-making and optimal patient care.

INTRODUCTION and advanced techniques to enhance, analyze and interpret

medical images. It includes a variety of imaging scans from
In today's world, medical imaging uses digital technology X-rays to MRI and CT scans, and facilitates operations

39
such as segmentation, feature extraction and that captures pairwise interactions. When these two features
computer-aided diagnosis. The combination of machine are identical, it leads to the creation of symmetric B-CNNs,
learning and deep learning helps in recognizing the reminiscent of second-order pooling (O2P), a common
disease, plan treatment and predict outcomes. technique used in semantic segmentation However, this
approach comes with some limitations, including
The main purpose behind image processing techniques is to sensitivity to hyperparameters, risk of overfitting, limited
revolutionize healthcare by improving the accuracy, applicability to specific scenarios and problems in
efficiency and usability of medical imaging. These systems achieving interpretable functions.
enable early detection of the disease, allowing timely and
accurate diagnosis. It supports individualized treatment
plans, reduces procedural complications and improves Cancer Detection Using CNN (2018)[2] by Ishani Dabral
patient outcomes. Medical imaging also extends medical et.al proposed a convolutional neural network (CNN)
care to areas underserved by telemedicine and contributes architecture for cancer detection focusing on the Invasive
to research and medical education. By integrating Ductal Carcinoma (IDC) dataset. This innovative
intelligence, these systems help inform decision-making, architecture combines convolutional, dropout, and fully
increase efficiency, engage patients, and ultimately control connected layers along with specific data preprocessing
healthcare costs. The main goal is to improve the quality of steps. However, it faces challenges such as the demand for
patient care, diagnosis and treatment while making a large dataset, model complexity, excessive risks, and the
healthcare more efficient and patient-focused. complexity of implementing transfer learning techniques.

Technologies used in this project are CNN and In A Novel Attention-Based CNN-RNN Hybrid
EfficientNet. The next column explains the technologies we Architecture for sEMG-Based Gesture Recognition
use. (2018)[3], the proposed architecture combines
convolutional neural networks (CNNs) and recurrent neural
Convolutional Neural Network (CNN) greatly helps with networks (RNNs) with an attentional mechanism that
image processing and pattern recognition. It uses recognizes gestures based on surface electromyography
convolutional layers to automatically learn hierarchical signals (sEMG). CNNs extract features from images, while
features of data. CNNs perform the most accurate and RNNs, especially Long Short-Term Memory (LSTM) units,
adaptive computer vision tasks. model temporal dependencies in data. An attention
mechanism is introduced to highlight relevant information
EfficientNet is a family of convolutional neural networks in sEMG signals. The architecture uses a combination of
(CNN) optimized for computer vision. It uses a loss functions, including attention loss and target
combination of various techniques to balance depth, width replication loss.
and resolution, making the model effective with accuracy.
EfficientNet is well-known in the deep learning community Challenges in this approach include the vanishing and
for its ability to deliver high performance while using fewer exploding gradient problem, which can hinder training and
computational resources. make it difficult to effectively capture long-range
dependencies in sequences. RNNs also face limitations
This article aims to provide an overview of the system by related to their short-term memory, excelling at tasks with
touching on its architecture, functionality and benefits. By relatively short sequences but struggling to remember
exploring its potential and practical applications, we aim to information from distant past events.
demonstrate the transformative power of this technology,
which integrates the highest level of intelligence with
humans to edit medical images. Through this research, we Wei Fang et.al[4] proposed a Deep Convolutional
aim to demonstrate the potential of this system to transform Generative Adversarial Network (DCGAN) including a
customer loyalty and error-free operation in healthcare, discriminative network and a generative network, both
ushering in a new era of efficiency and consumer analysis. consisting of four layers. The generator transforms noise
vectors into realistic samples, while the discriminator
distinguishes between real and generated data. The training
2. RELATED WORKS process involves a non-convex game, and an adaptive
learning rate reduction strategy is used to increase the
Tsung-Yu Lin et.al[1], discussed the architecture bilinear training efficiency. However, this approach encounters
pooling to combine the outer product of two features several problems, including training instability, regime
through global averaging, resulting in a covariance matrix collapse (where the generator produces limited diversity),

40
hyperparameter sensitivity, and the need for significant need for careful hyperparameter tuning.
computational resources due to its intensive nature.

Abien et.al[5] explores an experimental approach that In Improved Classification of MRI Images for Cervical
combines SVM and CNN for image classification. This Cancer Using CONVOLUTIONAL NEURAL
hybrid architecture uses SVM for binary classification, NETWORKS [9] the paper presents an approach for the
which determines the optimal hyperplane for separating automatic identification of hepatocellular carcinoma. It
two classes. The study considers both L1-SVM and uses an ensemble learning strategy with seven machine
L2-SVM, using the hinge loss as a standard loss function learning algorithms and uses collaborative representation
for SVM. However, this paper highlights problems classification with a boosting technique to categorize
including a lack of comprehensive understanding, potential hyperspectral images. However, this method faces
bias and fairness issues, absence of moral or ethical challenges, including a lack of domain knowledge and
considerations, and long-term memory-related limitations potential limitations in portability to different domains.
in the classification process.
Yiwen Liu, et.al[10] presented the paper that outlines the
An Image Classification Algorithm using AlexNet [6], the methodology for identifying crop diseases and insect pests.
authors present a method for image classification using an It uses transfer learning with VGG16 and
improved version of the AlexNet convolutional neural Inception-ResNet-v2 (CNN) convolutional neural
network (CNN). This approach solves the problem of networks. However, this approach faces challenges,
traditional CNNs with a high number of parameters, including resource intensiveness, the need for model
especially in fully connected layers, which can lead to updates, and complexity associated with fine-tuning.
problems such as overfitting and increased computational
complexity. The proposed enhancement introduces Sota Kato, et.al[11] proposed a study involving 50 cell
deconvolution layers into the AlexNet architecture, images with ground truth provided by Kyoto University.
effectively reducing the number of parameters, especially These images are obtained using a fluorescent marker on
in the fully connected layer. However, it is important to the cell membrane and nucleus of mouse liver and are
note that this improvement comes with increased 256×256 pixels in size. Among these images, 40 were used
computational complexity, the risk of overfitting due to for training, five for validation, and the remaining five for
model complexity, and the requirement for a significant testing. However, it should be noted that the proposed
amount of labeled training data. Achieving a balance method did not significantly improve the cell membrane
between these factors is essential for successful segmentation accuracy.
implementation of the improved AlexNet-based image
classification algorithm. Image Processing for Malaria Screening Using a Deep
Learning Approach [12] by Fetulhak Abdurahm, et.al. The
Yanan Sun, et.al, presented a method that uses a genetic study aims to improve the detection of P. falciparum in
algorithm (GA) to automatically optimize the architecture thick-smear microscopic images using an advanced deep
of convolutional neural networks (CNN). The process starts learning object . detection models. The aim is to address the
by initializing a population of CNN architectures, encoding challenges that were previously identified in this context.
them using skip and pooling layers and omitting fully To achieve this, the paper proposes a tile-based image
connected layers. Although this approach appears processing approach that enables better detection of small
promising, it faces challenges, including reproducibility objects in high-resolution images that exceed the input
issues, domain knowledge requirement, cross-domain resolution limits of the network. However, it should be
transferability difficulties, generalizability limitations, and noted that this method may not achieve a very high level of
data and time resource requirements. detection performance, especially when resizing the
high-resolution input image for detection.
Shengyi Zhao, et.al[8] presented an attention module to
improve model performance with minimal computational Md. Ashiq Mahmood and Tamal Joyti Roy[13], conducted
cost. This module uses the Squeeze-and-Excitation an experiment involving image analysis to establish an
Networks (SENet) method, which automatically assigns assessment process for identifying COVID-19-related lung
weight coefficients to feature channels based on their infection. This approach first involves analyzing the images
importance. This recalibration process reinforces relevant without converting them into binary segments.
feature channels while suppressing irrelevant ones. Subsequently, the authors convert normal images into
However, this approach comes with problems, including binary and collect the relevant values. The experiment also
computational complexity, reduced interpretability, and the uses parameter-based neural networks. However, one of the

41
challenges facing this study is the availability of
insufficient datasets for comprehensive analysis. Image
division is controlled by local segmentation.

Soto Kato and Kazuhiro Hotta[14], proposed a study using

50 cell images that come with ground truth data provided
by Kyoto University. These images are captured using a
fluorescent marker on the cell membrane and nucleus of a
mouse liver with a size of 256×256 pixels. Of these images,
40 were allocated for training, five for validation and the 3.1 SYSTEM ARCHITECTURE
remaining five for testing. However, it was observed that
the proposed method did not significantly improve the cell 3.1.1 SYSTEM DESIGN
membrane segmentation accuracy.

Convolutional Neural Network with Wavelet Domain

Inputs[15] the model starts with an RGB input that
transforms images into 448x448 YCbCr format. It then
applies a 3-level Wavelet Packet Transform (WPT) or
Dual-Tree Complex Wavelet Transform (DTCWT) to
generate 192 channels. To mitigate noise and computational
complexity, it selects and consolidates key channels into a
Cx56x56 tensor. This modified tensor is then processed by
the ResNet-50 model, which adapts to the changing C to System Design
improve the classification performance, especially focusing
on low-frequency information. A challenge highlighted in Users will receive login credentials, to prevent unwanted
the study is the absence of a suitable data set for this access. Then after the user logs in, they will be provided
approach and insufficient frequency. with a homepage that will have the Diagnoses that are
The method described in the article [16] by Ahmad Yahya available, then in that particular diagnosis, the user can
Dawod, Aniwat Phaphuangwittayakul and Salita upload an image, which is passed to the model from there,
Angkurawaranon in 2022 involves a series of steps, after which the result is presented to the user.
including image acquisition, preprocessing, Simple Linear
Iterative Clustering (SLIC) , edge detection, region
growing, dilation and hybrid method. However, this
approach has certain drawbacks, including
resource-intensiveness, the need for model updates, and the
3.1.2 SYSTEM OVERVIEW
complexity associated with fine-tuning the methodology.
The web application for medical image diagnosis leverages
3. PROPOSED WORK a technology stack that combines the front-end capabilities
We have used a model which will have a base model as an of React.js for a responsive and dynamic user interface with
EfficientNetB3 and using the imageNet weights. The input the back-end powered by Python, utilizing Flask as the web
which a image of any imaging scan is sent into the model, framework, and TensorFlow for deep learning with the
after which the convolution operation done on the image, EfficientNetB3 model. This seamlessly integrated tech
and the features are highlighted. Then we apply some noise stack enables users to upload medical images, and the
to the data for regularization, to prevent overfitting, and to system's Flask-based server facilitates the interaction
help the model to focus on only the essential part. Then we between the front-end and the deep learning model,
use batchNormalization that normalizes the activation of allowing for efficient image processing and diagnosis.
each layer.

42
 Collecting medical images data for feeding into an AI
model is a fundamental step in developing healthcare
diagnostic or analytical tools. This process initiates with the
acquisition of medical images using specialized equipment,
like X-ray machines, MRI scanners, or ultrasound devices.
Ensuring equipment accuracy and quality through regular
maintenance and calibration is critical to obtain reliable
data.

3.2.2 DATA LABELING:

System
flow
Medical images often require manual annotation, which
3.1.3 USER INTERFACE DESIGN: includes identifying regions of interest (ROIs) and
abnormalities. Expert radiologists or trained annotators
In the user interface for the medical image diagnosis web
usually perform this task to ensure the quality and accuracy
application, the primary input is an image upload feature.
of annotated data. Establishing ground truth data with
The homepage will feature a list of diagnosis, upon
accurate annotations and diagnoses for each image is
selecting one diagnosis, they are sent to a page which will
critical as it forms the basis for training the AI ​model and
feature an Upload Image button that allows users to easily
allowing it to make diagnostic predictions.
select and submit medical images for diagnosis. Once the
image is uploaded, the interface presents the image for
review and subsequently displays the diagnosis results, 3.2.3 DATA PREPROCESSING:
offering a streamlined and user-friendly experience focused
solely on image-based Diagnosis To standardize the data and to improve the image quality
we use data preprocessing techniques such as noise
reduction, normalization and augmentation. Medical
images can be noisy due to various factors, and noise
mitigation is essential for model accuracy. Ensuring
consistent intensity and resolution across images is
essential for accurate analysis. Data augmentation
techniques like rotating the data and brightness
adjustments increase the amount of data in the dataset and
helps the AI ​model make more reliable predictions. Image
registration is also used when working with multiple image
modalities or images taken at different times.

3.3 MODEL DEVELOPMENT AND TRAINING

3.3.1 EfficientNet B3

EfficientNet is a family of CNN architectures designed for

efficient and effective deep learning. It is trained on
ImageNet-1K at a resolution of 300X300. It uses simple
User interface design
compound coefficients to achieve better results.
EfficientNet B3 is known for its good balance between
model size and performance, making it suitable many
computer vision tasks,
3.2. DATA COLLECTION AND
PREPROCESSING
3.3.2 Transfer Learning
3.2.1 COLLECTION OF DATA
Leveraging pre-trained models like EfficientNet B3 is a
common approach in deep learning. Pre-trained model

43
weights can be used in large datasets as a starting point for 3.4.3 IMAGE UPLOAD AND PROCESSING:
many medical image analysis tasks. This can significantly
speed up training and potentially improve performance, The image upload and processing stage is a critical part of
especially if you have limited labeled medical data. the workflow, ensuring that the system can efficiently
analyze medical images. Users are guided to click the
3.3.3 Fine-Tuning: Upload Image button, followed by the selection of a
medical image from their device. Once uploaded, the
After initializing the model with pre-trained weights, system proceeds to process the image for further analysis.
fine-tuning the model on the medical image dataset is This preprocessing may include resizing and normalization
essential. Adjust the top layers of the model to adapt it to to ensure the image is in the appropriate format and size
your specific task. The output layer needs to be modified to required by the machine learning model.
the number of output classes for the diagnostic task.
3.4.4 DIAGNOSIS PROCESS:
3.3.4 Data Augmentation:
After the image is submitted, the image is handed over to
Augmenting dataset during training by applying the deep learning model, EfficientNetB3, for the actual
transformations like rotation, scaling, and flipping we can diagnosis. The model analyzes the image to generate a
get a wider variety of data for training which will help in prediction for the medical condition and produces a
generalizing the model and prevent overfitting. Data confidence score to assess the certainty of the diagnosis.
augmentation helps the model become robust to variations This step is the core of the application, where the machine
in input data. learning model leverages its capabilities to provide
valuable medical insights.

3.3.5 Regularization:
3.4.5. RESULT PRESENTATION:

To prevent overfitting, we have added regularization

techniques such as dropout and weight decay to the model. The diagnosis results are presented to the user in a
EfficientNet B3 has a significant number of parameters, user-friendly and understandable format. This presentation
and regularization can help improve generalization. includes the predicted medical condition, the associated
confidence score.

3.4. SYSTEM WORKFLOW

3.4.6. DATA SAFETY AND PRIVACY:

3.4.1 USER LOGIN:

Throughout the workflow, robust data safety and privacy
measures are upheld. This includes secure data
Upon accessing the application, users are presented with transmission protocols, temporary data storage during the
the login screen. Here, users input their credentials, user's session, and user authentication. The application
typically consisting of an email address and password, prioritizes data protection to safeguard sensitive patient
which are securely verified for authentication. Once information and medical images, following industry
successfully logged in, users gain access to the application's standards and regulations to ensure user data remains
features. confidential and secure.

3.4.2 HOMEPAGE AND IMAGE UPLOAD : 3.4.7 LOGOUT AND USER MANAGEMENT:

Upon successful login, users are directed to the Users have the option to log out of their accounts when
application's homepage, which serves as the central hub for they have completed the diagnosis. Additionally, the
initiating the diagnosis process. The homepage is designed application offers user management features that empower
to be intuitive and user-friendly, featuring a conspicuous users to maintain their accounts, including the ability to
Upload Image button or area where users can easily select reset passwords and configure account settings. This
and submit their medical images for analysis. This step is provides a seamless and user-centric experience while
crucial for initiating the diagnosis process and streamlining allowing users to have control over their accounts.
the user experience.

44
4. CONCLUSION [7] Yanan Sun, Bing Xue, Mengjie Zhang, Gary and
Jiancheng Lv, “Automatically Designing CNN
In the culmination of this project, we have successfully Architectures Using Genetic Algorithms for Image
developed a user-centric medical image diagnosis web Classification”. arXiv:1808.03818v3, [cs.NE], 27 march
application. By removing the individual user registration 2020
process we have made sure that there is no unauthorized
access to the tool. This streamlined workflow, coupled with [8] Shengyi Zhao, Yun Peng, Jizhan Liu * and Shuo Wu.
efficient image processing and clear result presentation, “Tomato Leaf Disease Diagnosis Based on Improved
facilitates prompt and comprehensive medical image Convolution Neural Network by Attention Module”.
diagnoses. The integration of the EfficientNetB3 deep Agriculture 2021, 11, 651. 11 July 2021
learning model enhances the accuracy and reliability of the
results, contributing to informed healthcare decisions. As [9] S. Gowri, Judith Justin and R. Vanithamani. S. Gowri,
we move forward, ongoing monitoring and maintenance Judith Justin and R. Vanithamani. “An Improved
will be essential to uphold the application's continued Classification of Mr Images for Cervical Cancer Using
reliability and accuracy. This project exemplifies the Convolutional Neural Networks”. ICTACT journal on
delicate balance between user-friendliness and data image and video processing, volume: 12, issue: 02,
security, underlining its potential as a valuable tool in the november 2021
realm of healthcare, benefiting both medical professionals
and patients.
[10] Yiwen Liu , Xian Zhang, Yanxia Gao,Taiguo Qu, and
Yuanquan Shi. “Improved CNN Method for Crop Pest
Identification Based on Transfer Learning”. Hindawi
Computational Intelligence and Neuroscience Volume
REFERENCE: 2022, Article ID 9709648, Published 16 March 2022

[1] Tsung-Yu LIN, Subhransu Maji, Improved Bilinear [11] Sota Kato Kazuhiro Hottal, “Cell Segmentation by
Pooling with CNNs, arXiv:1707.06772v1 [cs.CV], 21 july Image-to-Image Translation using Multiple Different
2017 Discriminators''.DOI: 10.5220/0009170103300335, Volume
4: BIOSIGNALS, published in 2022

[2] Ishani Dabral,Maheep Singh,Krishan Kumar, Cancer

Detection using CNN, published in 2018 [12] Fetulhak Abdurahm Kinde Anlay Fante. “Tile-based
microscopic image processing for malaria screening using
deep learning approach”. April 19th, 2022
[3] Yu HuID1, Yongkang WongID2, Wentao Wei1, Yu
Du1, Mohan Kankanhalli3, Weidong GengID1, “A novel
attention-based hybrid CNN-RNN architecture for [13] Md. Ashiq Mahmood Tamal Joyti Roy. “A Hybrid
sEMG-based gesture recognition”. PLoS ONE 13(10): Approach to Find COVID-19 Related Lung Infection
e0206049. October 30, 2018 Utilizing 2 Bit Image Processing, 19 February 2022.

[4] Wei Fang, Feihong Zhang1, Victor S. Sheng3 and [14] Sota Kato Kazuhiro Hotta. Cell Segmentation by
Yewen Ding1. “A Method for Improving CNN-Based Image-to-Image Translation using Multiple Different
Image Recognition Using DCGAN”. CMC, vol.57, no.1, Discriminators. DOI: 10.5220/0009170103300335, Volume
pp.167-178, 2018 4: BIOSIGNALS, published in 2022

[5] Abien Fred M. Agarap. “An Architecture Combining [15] Luyuan Wang Yankui Sun Image classification using
Convolutional Neural Network(CNN) and Support Vector convolutional neural network with wavelet domain inputs.
Machine (SVM) for Image Classification.” IET Image Process, DOI: 10.1049/ipr2.12466, 21 February
arXiv:1712.03541v2, 7 Feb 2019 2022

[6] Shaojuan Li, Lizhi Wang, Jia Li and Yuan Yao. “Image [16] Ahmad Yahya Dawod Aniwat Phaphuangwittayakul
Classification Algorithm Based on Improved AlexNet”. Salita Angkurawaranon. A hybrid method for traumatic
Shaojuan Li et al 2021 J. Phys.: Conf. Ser. 1813 012051 brain injury lesion segmentation. International Journal of
Electrical and Computer Engineering (IJECE) Vol.12,
No.2, April 2022, pp.1437~1448

45
PLAGIARISM REPORT FOR PHASE 1 PAPER

46
 Medical Image Diagnosis In Healthcare
Utilizing A Web Application

Dr.P.Shanmugam Keshav S.R Mithilesh Kumaar J.S

Assistant Professor Student Student
Department of Department of Department of
Computer Science and Computer Science and Computer Science and
Engineering Engineering Engineering
Rajalakshmi Engineering Rajalakshmi Engineering Rajalakshmi Engineering
College Chennai, India College Chennai, India College Chennai, India
[email protected] [email protected]. [email protected].
du.in in in

Abstract:
In today's fast-paced world, the need for accurate and effective diagnoses in the healthcare industry has become increasingly
important. The main idea behind diagnostics is to reduce human error in medicine; This is a principle that extends medicine
to other fields, such as satellite Earth observation and understanding operations in space. The main purpose in developing
our work is to provide doctors with reliable tools to predict and solve customers' health problems on the online platform. We
also aim to improve the overall user experience by implementing functions to manage user history and preferences. The core
technologies of our solution include the powerful EfficientNet B3 for neural networks (CNN) and image processing, as well
as extensive use of React.js to create an interactive web front end. Our work focuses on image data and solves problems such
as overhead, hyperparameter sensitivity, and time consumption in image processing. By addressing these issues, our goal is to
provide physicians with fast, accurate results that meet their rapid decision-making and care needs, good patients.

Related Work overuse, limited use for certain situations, and problems
Tsung-Yu Lin et al. [1] discussed the design of bilinear with the use of defined roles.
pooling, which combines the products of two faces with
global competition to form a different matrix leading to the Sing CNN for Cancer Detection (2018) [2] Ishani Dabral et
interaction effect. Although these two features are similar, al. proposed a neural network (CNN) architecture for
they lead to the parallelism of B-CNN, reminiscent of cancer diagnosis targeting the Invasive Ductal Cancer
second-order (O2P), a technique used in semantic (IDC) dataset. This innovation combines convolution,
classification. However, this approach suffers from several output and deconvolution techniques with custom data
limitations, such as sensitivity to hyperparameters, risk of priors. However, it faces problems such as the need for

47
large data sets, complex models, excessive risk, and A method using the image classification algorithm AlexNet
difficulty in implementing the transformation process. [6], the author proposed a method using the development of
AlexNet convolutional neural network (CNN) for image
A tracking system that recognizes gestures based on gesture classification. This method solves many inconsistency
recognition and surface electromyographic signals (sEMG) problems of traditional CNN, especially in the fully
based on the CNN-RNN hybrid architecture (2018). While connected process, which will cause excessive interference
CNNs extract features from images, RNNs, especially and increase the complexity of the process. This
short-term (LSTM) units, model the body of the object. development introduced the deconvolution process into the
Tracking techniques have been introduced to highlight AlexNet architecture, specifically reducing the number of
important information in sEMG signals. The architecture parameters in all layers. However, it is worth noting that
uses a combination of redundancy, including shock and this development also brings with it an increase in
target redundancy. computer complexity, the risk of overfitting due to model
complexity, and the need for large amounts of training data.
Challenges with this approach include fading and breakage Achieving a balance of these factors is critical for the
gradient issues, which can disrupt training and make successful development of the AlexNet-based image
long-term progress difficult to make. RNNs also face classification algorithm.
limitations regarding short time intervals; They are good at
working with short segments but have difficulty Yanan Sun et al. proposed a method to optimize the
remembering information about events in the distant past. performance of convolutional neural networks (CNN) using
genetic algorithms (GA). The process starts by initializing a
set of CNN architectures, coding them layer by layer and
Wei Fang et al. The generator transforms noise vectors into removing entire layers. Although this approach seems
real patterns, while the operator distinguishes between real promising, it faces challenges such as reproducibility
and generated data. Training methods include non-convex issues, information requirements, flexible adaptations,
games and adaptive learning reduction strategies are used overall limits, material and time requirements.
to improve learning performance. However, this approach
suffers from several problems such as training instability, Shengyi Zhu et al. This model uses the Compression and
poor performance (the generator is diverse), excessive Excitation Network (SENet) method to assign weight
hyperparameter sensitivity, and requires significant coefficients to channels based on their importance. This
computer services due to its severe nature. recalibration process improves the performance of the film
without any particular problems. However, this approach
Abien et al[5] discussed an experimental method still suffers from many problems, such as computational
combining SVM and CNN for image classification. This complexity, reduced interpretability, and the need for
hybrid architecture uses SVM for binary classification to careful tuning of hyperparameters.
determine the best hyperplane separating two classes. This
work considers both L1-SVM and L2-SVM by using hinge In improving the classification of Cervical Cancer MRI
loss as the loss model for SVM. However, this article Images Using Convolutional Neural Networks [9] A report
highlights issues such as lack of understanding of the on a method for identifying Hepatocellular carcinoma. It
distribution process, issues of injustice and justice, ethics or uses a learning concept combined with seven machine
lack thereof, and limitations with long-term memory. learning algorithms and uses collaborative representation
classification and optimization techniques to classify

48
hyperspectral images. However, this approach faces for analysis. Image segmentation is controlled by local
challenges such as lack of information and the ability to segmentation.
limit movement between different locations.
Soto Kato and Kazuhiro Hotta[14] presented a study using
Yiwen Liu et al. It uses VGG16 and Inception-ResNet-v2 50 cell images with baseline data from Kyoto University.
(CNN) convolutional neural networks for transfer learning. Images were captured using fluorescent markers of mouse
However, this approach faces challenges such as resource liver cell membranes and nuclei and are 256 x 256 pixels in
consumption, need for updated models, and difficulties size. 40 of these images were used for training, 5 for
with optimization. validation, and the remaining 5 for testing. However, it was
found that the proposed method did not improve the cell
Sota Kato et al. [11] presented a study from Kyoto membrane segmentation accuracy.
University involving 50 mobile phones. Images were
obtained using fluorescent markers of mouse liver cell Convolutional Neural Network with Wavelet Domain Input
membranes and nuclei and were 256 x 256 pixels in size. [15] This model starts with RGB input and converts the
40 of these images were used for training, 5 for validation, image to 448x448 YCbCr format. It then uses the 3rd-order
and the remaining 5 for testing. However, it is worth noting wavelet packet transform (WPT) or double-tree complex
that the scheme cannot improve the accuracy of cell wavelet transform (DTCWT) to create 192 channels. It
membrane segmentation. selects the main channels and combines them into Cx56x56
tensors to reduce noise and computational complexity. This
Image processing for malaria screening using deep learning modified tensor is then processed by the ResNet-50 model;
[12], Fetulhak Abdurahm et al. This study aims to use deep This model modifies C to improve the performance of
learning material to improve the detection of Plasmodium classification by paying special attention to low-frequency
falciparum in thick smear microscopy. Sample check. The data. The biggest challenge in research is the lack of
aim is to solve previously identified problems in this area. suitable and insufficient data for this approach.
To achieve this goal, the reporting process is based on
images that can see small objects in higher resolution The process described in the article [16] published by
images that exceed the resolution of the network. However, Ahmad Yahya Dawod, Aniwat Phaphuangwittayakul and
it should be noted that this approach may not achieve a Salita Angkurawaranon in 2022 involves several steps,
high level of detection performance, especially when including finding images, first simple linear iterative
changing the image to be detected. clustering (SLIC), edge detection, growing region,
expansion . and hybrid methods. However, this approach
Art. Ashiq Mahmood and Tamal Joyti Roy [13] conducted has some disadvantages, such as resource usage, the need
an experiment with image analysis to develop an for up-to-date models, and difficulties with quality systems.
assessment system to identify COVID-19-associated lung
diseases. This method primarily involves analyzing images 3. PROPOSED WORK
without converting them into binary parts. Then the authors
The model we will use will be EfficientNetB3 as the base
converted the normal image to binary and recorded the
model and we will mainly use imageNet. Transfer an image
corresponding results. This experiment also uses
from scanning to an input on the model; this then convolves
parameter-based neural networks. However, one of the
the image and highlights features. We then apply some
problems faced by this study is that there is not enough data
regular noise to the data to prevent overfitting and help the
model focus on only important values. We then use

49
BatchNormalization to normalize the performance of each
layer.

3.1 SYSTEM ARCHITECTURE

Fig 3. System flow
3.1.1 SYSTEM DESIGN
3.1.3 USER INTERFACE DESIGN:

The main concept in the user interface of the medical

imaging diagnostic web application is the image upload
function. A list of diagnoses will be displayed on the home
page, and once a diagnosis is selected, they will be sent to a
page with image uploads, allowing users to easily select
and upload medical images for diagnosis. Once the image
is loaded, the interface displays the image for review and
then displays diagnostic results, providing links and user
experience.
Fig 1. System Design

Users will be issued a login certificate to prevent

unauthorized access. Then, once the user logs in, they are
presented with a home page with available diagnoses and
then on a particular diagnosis the user can send images
from there which are transferred to the model and the
results are then presented to the user.

3.1.2 SYSTEM OVERVIEW

The web application for medical diagnostics uses a set of

technologies that combine the front-end capabilities of
React.js to respond to user interactions with the back-end
driven by Python using Flask as a web platform and
TensorFlow for deep learning. EfficientNetB3 model. This
integrated technology allows users to transmit medical
images, and the Flask-based server system, front-end and
absorption of dynamic learning models facilitate the
interaction of image processing and diagnostics.
Fig 2. User interface design

3.2. DATA COLLECTION AND PREPROCESSING

3.2.1 COLLECTION OF DATA

Collecting clinical data to feed cognitive models is an

important step in the development of a diagnosis or
diagnostic tool. The process begins with capturing medical

50
images using specialized equipment such as x-ray It is important to weight the model before training and then
machines, MRI scanners or ultrasound equipment. Ensuring adjust the model based on clinical data. Customize the top
product accuracy and performance through regular layer of the template to fit your specific project. For
monitoring and calibration is essential to obtain reliable diagnosis, the urine method must be adjusted according to
data. the number of urine groups.

3.2.2 DATA LABELING: 3.3.4 Data Augmentation:

Medical imaging often requires manual guidance that By improving the data during training using
includes identifying regions of interest (ROIs) and transformations such as rotation, scaling, and translation,
abnormalities. This work is usually done by an electrician we can obtain more training data, which will help make the
or trained scribe to ensure the quality and accuracy of the model larger and avoid collisions. Data augmentation helps
recorded data. Establishing a ground truth with accurate the model make changes to the input data.
descriptions and diagnoses for each image is important
because this forms the basis for training the AI ​model and
3.3.5 Regularization:
allows it to make future diagnoses earlier.

3.2.3 DATA PREPROCESSING: To prevent overfitting, we add regularization parameters

such as dropout and weighting to the model. EfficientNet
B3 has many parameters and continuous operation helps
We use data processing techniques such as noise reduction,
increase overall efficiency.
normalization and enhancement to create data and improve
image quality. Medical images can be noisy for a variety of
reasons, and it is important to reduce noise for accurate 3.4. SYSTEM WORKFLOW
samples. Keeping the image consistent and resolved is
important for accurate analysis. Data enhancement 3.4.1 USER LOGIN:
techniques such as data transformation and brightness
adjustment increase the information in the dataset and help Once in the application, users will see the login screen.
AI models make more reliable predictions. The registration Here, users enter credentials that are checked for
form can also be used when taking different types of authentication, usually including email address and
photographs or photographs taken at different times. password. After successfully logging in, the user can access
the functions of the application.
3.3 MODEL DEVELOPMENT AND TRAINING
3.4.2 HOMEPAGE AND IMAGE UPLOAD :
3.3.1 EfficientNet B3
Upon successful login, the user is sent to the main page of
EfficientNet is a family of CNN architectures designed for the application and this forms the basis for starting the
deep and efficient learning. Trained on ImageNet-1K at diagnostic process. The homepage design is intuitive and
300X300 resolution. It uses simple coefficients to get better user-friendly, featuring a prominent image upload button or
results. EfficientNet B3 is known for its good balance area where users can easily select medical images and
between model size and performance, making it suitable for submit them for analysis. This step is important to start the
many computer vision systems. diagnostic process and improve the user experience.

3.3.2 Transfer Learning 3.4.3 IMAGE UPLOAD AND PROCESSING:

Using advanced learning models such as EfficientNet B3 is The image loading and processing phase is the main work
one method in deep learning. Pre-trained weight models to ensure that the system can analyze the medical image
can be used as a starting point for many types of image well. Tell users to click the "Upload Image" button and
analysis on large data sets. This can increase training speed select a medical image from their device. Once uploaded,
and potentially improve performance, especially if you the system continues to process images for further analysis.
have limited clinical experience. This preprocessing may include transforming and
normalizing to ensure that the image is in the appropriate
3.3.3 Fine-Tuning: format and size required by the machine learning model.

51
3.4.4 DIAGNOSIS PROCESS:

After the image is sent, the image is sent to the

EfficientNetB3 deep learning model for actual diagnosis.
This model evaluates images to generate predictions of
clinical conditions and increases confidence in assessing
the accuracy of diagnosis. This step is the main part of the
application where the machine learning model uses its
ability to provide treatment recommendations.

3.4.5. RESULT PRESENTATION:

Diagnostic results are presented to users in a user-friendly After that, the user will have to select the diseases they are
and easy-to-understand format. This display includes willing to diagnose. There will be a list available form
predicted treatments and confidence scores. which the user can select.

3.4.6. DATA SAFETY AND PRIVACY:

We comply with data security and confidentiality measures

throughout our work. This includes security data transfers,
temporary data storage during user sessions, and user
authentication. The app focuses on data protection to
protect patient data and medical images in accordance with
industry standards and regulations to ensure the privacy and
security of user data.
Then there will be a dialog where the user can select the
3.4.7 LOGOUT AND USER MANAGEMENT: image, and upload it to the server which will give the result
in a human readable format.
Once the diagnosis is complete, users can cancel their
account. In addition, the app provides user management
features that allow users to manage their accounts,
including resetting passwords and creating accounts. This
allows users to manage their money while providing
consistency and a great user experience.

4. IMPLEMENTATION AND RESULT

After the login there is the Dashboard in which all the

medical image diagnoses are present. The user can select In the above image, the X Ray is selected. Where there is a
from the listed diagnoses. list of diseases that can be diagnosed with the X ray. Then
The user should upload the image of a chest X ray.

52
 [1] Tsung-Yu LIN, Subhransu Maji, Improved Bilinear
Pooling with CNNs, arXiv:1707.06772v1 [cs.CV], 21 july
2017

[2] Ishani Dabral,Maheep Singh,Krishan Kumar, Cancer

Detection using CNN, published in 2018

[3] Yu HuID1, Yongkang WongID2, Wentao Wei1, Yu

Du1, Mohan Kankanhalli3, Weidong GengID1, “A novel
attention-based hybrid CNN-RNN architecture for
sEMG-based gesture recognition”. PLoS ONE 13(10):
e0206049. October 30, 2018

[4] Wei Fang, Feihong Zhang1, Victor S. Sheng3 and

Yewen Ding1. “A Method for Improving CNN-Based
Then when the image is set to the server. Where the model Image Recognition Using DCGAN”. CMC, vol.57, no.1,
predicts the disease and then the result is sent in a human pp.167-178, 2018
readable format.
[5] Abien Fred M. Agarap. “An Architecture Combining
Convolutional Neural Network(CNN) and Support Vector
Machine (SVM) for Image Classification.”
arXiv:1712.03541v2, 7 Feb 2019

[6] Shaojuan Li, Lizhi Wang, Jia Li and Yuan Yao. “Image
Classification Algorithm Based on Improved AlexNet”.
Shaojuan Li et al 2021 J. Phys.: Conf. Ser. 1813 012051

[7] Yanan Sun, Bing Xue, Mengjie Zhang, Gary and

Jiancheng Lv, “Automatically Designing CNN
Architectures Using Genetic Algorithms for Image
Classification”. arXiv:1808.03818v3, [cs.NE], 27 march
2020

5. CONCLUSION
[8] Shengyi Zhao, Yun Peng, Jizhan Liu * and Shuo Wu.
“Tomato Leaf Disease Diagnosis Based on Improved
With the completion of this project, we completed the Convolution Neural Network by Attention Module”.
development of the client's web analytics application. By Agriculture 2021, 11, 651. 11 July 2021
removing the user registration process, we ensure that there
is no unauthorized access to the device. This simple
[9] S. Gowri, Judith Justin and R. Vanithamani. S. Gowri,
process, combined with image processing and presentation
Judith Justin and R. Vanithamani. “An Improved
of clear results, facilitates timely and successful diagnoses.
Classification of Mr Images for Cervical Cancer Using
Integration of the EfficientNetB3 deep learning model
Convolutional Neural Networks”. ICTACT journal on
helps make clinical decisions by increasing the accuracy
image and video processing, volume: 12, issue: 02,
and reliability of results. As we move forward, ongoing
november 2021
monitoring and maintenance is critical to maintain the
reliability and accuracy of the application. By
demonstrating the balance between user-friendliness and [10] Yiwen Liu , Xian Zhang, Yanxia Gao,Taiguo Qu, and
information security, the project demonstrates its potential Yuanquan Shi. “Improved CNN Method for Crop Pest
to be a useful, important tool in medicine for doctors and Identification Based on Transfer Learning”. Hindawi
patients. Computational Intelligence and Neuroscience Volume
2022, Article ID 9709648, Published 16 March 2022
REFERENCE:

53
[11] Sota Kato Kazuhiro Hottal, “Cell Segmentation by [15] Luyuan Wang Yankui Sun Image classification using
Image-to-Image Translation using Multiple Different convolutional neural network with wavelet domain inputs.
Discriminators''.DOI: 10.5220/0009170103300335, Volume IET Image Process, DOI: 10.1049/ipr2.12466, 21 February
4: BIOSIGNALS, published in 2022 2022

[12] Fetulhak Abdurahm Kinde Anlay Fante. “Tile-based [16] Ahmad Yahya Dawod Aniwat Phaphuangwittayakul
microscopic image processing for malaria screening using Salita Angkurawaranon. A hybrid method for traumatic
deep learning approach”. April 19th, 2022 brain injury lesion segmentation. International Journal of
Electrical and Computer Engineering (IJECE) Vol.12,
[13] Md. Ashiq Mahmood Tamal Joyti Roy. “A Hybrid No.2, April 2022, pp.1437~1448
Approach to Find COVID-19 Related Lung Infection
Utilizing 2 Bit Image Processing, 19 February 2022.

[14] Sota Kato Kazuhiro Hotta. Cell Segmentation by

Image-to-Image Translation using Multiple Different
Discriminators. DOI: 10.5220/0009170103300335, Volume
4: BIOSIGNALS, published in 2022

54
PLAGIARISM REPORT FOR PHASE 2 PAPER

55
 CO-PO MAPPING

CO PO ATTAINMENT FOR PROJECT

1. On completion the students are capable of executing the proposed plan and
become aware of and overcome the bottlenecks throughout every stage.

2. On completion of the project work students could be in a role to take in any

difficult sensible issues and locate answers through formulating the right
methodology.

3. Students will attain a hands-on level in changing a small novel idea / method
right into an operating model / prototype related to multidisciplinary abilities and /
or understanding and operating in a team.

4. Students will be able to interpret the outcome of their project. Students will take
on the challenges of teamwork, prepare a presentation in a professional manner,
and document all aspects of design work.

5. Students will be able to publish or release the project to society.

56
PROJECT WORK COURSE OUTCOME (COs):

CO1: On completion the students are capable of executing the proposed plan and
become aware of and overcome the bottlenecks throughout every stage.

CO2: On completion of the project work students could be in a role to take on any
difficult sensible issues and locate answers through formulating the right
methodology.

CO3: Students will attain a hands-on level in changing a small novel idea / method
right into an operating model / prototype related to multi- disciplinary abilities and
/ or understanding and operating in a team.

CO4: Students will be able to interpret the outcome of their project. Students will
take on the challenges of teamwork, prepare a presentation in a professional
manner, and document all aspects of design work.

CO5: Students will be able to publish or release the project to society.

57
PROGRAM OUTCOMES (POs):
PO1: Engineering knowledge: Apply the knowledge of mathematics, science,
engineering fundamentals, and an engineering specialization to the solution of
complex engineering problems.
PO2: Problem analysis: Identify, formulate, review research literature, and analyze
complex engineering problems reaching substantiated conclusions using first
principles of mathematics, and engineering sciences.
PO3: Design / development of solutions: Design solutions for complex
engineering problems and design system components or processes that meet the
specified needs with appropriate consideration for the patients health and safety,
and medical needs.
PO4: Conduct investigations of complex problems: Use research - based
knowledge and research methods including design of experiments, analysis and
interpretation of data, and synthesis of the information to provide valid
conclusions.
PO5: Modern tool usage: Create, select, and apply appropriate techniques,
resources, and modern engineering and IT tools including prediction and modeling
to complex engineering activities with an understanding of the limitations.

58
PO6:The engineer and society: Apply reasoning informed by the contextual
knowledge to assess societal, health, safety, legal and cultural issues and the
consequent responsibilities relevant to the professional engineering practice and
medical practices.
PO7: Environment and sustainability: Understand the impact of the professional
engineering solutions in societal and environmental contexts, and demonstrate the
knowledge of, and need for sustainable development.
PO8: Ethics: Apply ethical principles and commit to professional ethics and
responsibilities and norms of the engineering practice.
PO9: Individual and team work: Function effectively as an individual, and as a
member or leader in diverse teams, and in multidisciplinary settings.
PO10: Communication: Communicate effectively on complex engineering
activities with the engineering community and with society at large, such as, being
able to comprehend and write effective reports and design documentation, make
effective presentations, and give and receive clear instructions.
PO11: Project management and finance: Demonstrate knowledge and
understanding of the engineering and management principles and apply these to
one’s own work, as a member and leader in a team, to manage projects and in
multidisciplinary environments.
PO12: Life-long learning: Recognize the need for, and have the preparation and
ability to engage in independent and life-long learning in the broadest context of
technological change.
PO13: Learning: Recognize the need for, and have the preparation and ability to
engage in independent and life-long learning in the broadest context of
technological change.

59
PROGRAM SPECIFIC OUTCOMES (PSOs)
PSO1: Foundation Skills: Ability to understand, analyze and develop computer
programs in the areas related to algorithms, system software, web design, machine
learning, data analytics, and networking for efficient design of computer-based
systems of varying complexity. Familiarity and practical competence with a broad
range of programming languages and open-source platforms.

PSO2: Problem-Solving Skills: Ability to apply mathematical methodologies to

solve computational tasks, model real world problems using appropriate data
structure and suitable algorithms. To understand the Standard practices and
strategies in software project development using open-ended programming
environments to deliver a quality product that has been done.

PSO3: Successful Progression: Ability to apply knowledge in various domains to

identify research gaps and to provide solutions to new ideas, inculcate passion
towards higher studies, creating innovative career paths to be an entrepreneur and
evolve as an ethically socially responsible computer science professional.

0/PS PO PO PO PO PO PO PO PO PO PO PSO PSO PSO

OCO 1 2 3 4 5 6 7 9 11 12 1 2 3
CO1 3 3 3 3 3 1 2 2 2 2 - 1 2
CO2 2 1 3 1 2 1 2 1 2 1 1 2 1
CO3 3 2 3 1 2 3 2 1 2 - 3 2 1
CO4 3 1 3 2 1 2 3 1 2 3 1 2 2
CO5 2 3 1 2 3 1 2 3 1 1 2 2 3
average 2.6 2 2.6 1.8 2.2 1.6 2.2 1.6 1.8 1.4 1.4 1.8 1.8

60
61