Scribd
Upload
6 views3 pages

Proposal

Uploaded by

Siddhartha Negi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
6 views3 pages

Proposal

Uploaded by

Siddhartha Negi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Team Name :

Deep_Learners

TEAM:

MEMBER NAME TECH STACK/ROLE DEVFOLIO ID


KARTIK ML/BACKEND Kartik0198
SIDDARTHA UI/UX/BACKEND ray_barracuda2
SUYASH AI/ML
NAVNEET UI/UX/ML NAVIBAR

Problem Statement:

The complexity and cost of traditional cancer detection methods, limited access to skilled professionals
and diagnostic tools in remote areas, and the need for accurate and timely diagnosis.

Inspiration for this Proposal:

Our team has witnessed that if there is a a lot of patients to diagnose, doctors takes a lot of time to
predict the problems and sometime due to some human error of lack of experience can cause wrong
diagnoses. Thus we are inspired to create a cancer detection project to address these challenges.

Project Description / Implementation Details:

Our application, a sophisticated Organ classifier and cancer detection system, aims to streamline patients
to diagnose for doctors. It's built on the MERN stack—MongoDB, Express.js, React Native, and Node.js—
integrating advanced technologies for a seamless user experience and robust functionality. React Native
powers the frontend, ensuring native-like performance and responsiveness across devices. Leveraging its
component-based architecture, we craft a modular UI facilitating easy navigation and interaction. On the
backend, Node.js and Express.js provide a scalable infrastructure for user authentication, data
processing, and API communication, while MongoDB offers flexibility for storing user data and plant
images. Key to our app is the integration of machine learning algorithms for organ classification and
cancer detection, developed using TensorFlow.js, enabling fast and responsive diagnosis directly on the
client-side. The image capture feature allows client to photograph their ultrasound/X-rays for anomalies
detection, with real-time analysis minimizing latency.

Impact on Society:

By automating diagnostic processes, the model can help reduce healthcare costs associated with manual
inspections and the need for specialized medical professionals to reach remote and poor populations.
This is particularly relevant in low and middle-income countries where medical imaging is not always
feasible due to the scarcity of well-trained radiologists
Technologies Used:

 Tensorflow(VGG16, RESNET50)
 React
 Node.js
 MongoDB
 Music
 Jenkins

Tentative Timetable

START DATE END DATE MILESTONES


30-03-24 05-04-24 1. Set up project
2. Research Solution
3. Define project

06-04-24 11-04-24 1. Setup Ultrasound


Model
2. Develop Initial
Webapp [user
interface]
12-04-24 18-04-24 1. Implement X-ray
Model
2. Integrate both models
3. Test & train
4. Finalize

Challenges:

Medical datasets are often scarce due to privacy concerns, restricted access, and the sensitive nature
of patient data. Overcoming these challenges involves navigating regulatory frameworks,
establishing collaborations with medical institutions, and ensuring data privacy and security
measures are in place.

Integration of multiple deep learning models to address different aspects of cancer detection. The
process may adjust input and output formats, managing model compatibility, and optimizing
computational resources for efficient inference.

Data preprocessing in the context of medical images involves cleaning, standardizing, and enhancing
the quality of image data to facilitate accurate analysis and interpretation by machine learning
algorithms.
Conclusion:

The development of our model in classifying organs and detecting cancer in ultrasound and x-ray
images. This breakthrough marks a significant advancement in medical diagnostics, showcasing AI's
potential to improve disease detection precision. Moving forward, continuous monitoring, updates,
and ethical considerations are vital to sustain the model's performance and relevance. Collaboration
with clinicians and seamless integration into clinical workflows will further optimize patient
outcomes, highlighting the transformative impact of technology on healthcare.

You might also like