Scribd
Upload
33 views7 pages

AT02

This document is a project report for developing a CNN model to detect lung cancer from medical images. It includes sections on the abstract, introduction, literature survey, proposed methodology, results and discussions, and conclusion. The objective is to collect medical images and use supervised learning to train a CNN model to classify images as either cancer-positive or cancer-negative. The methodology proposes using a convolutional neural network which is well-suited for image classification tasks. The results section indicates the model achieved 90.22% accuracy in detecting malignancy tissues in lung CT images.

Uploaded by

movatehire
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
33 views7 pages

AT02

This document is a project report for developing a CNN model to detect lung cancer from medical images. It includes sections on the abstract, introduction, literature survey, proposed methodology, results and discussions, and conclusion. The objective is to collect medical images and use supervised learning to train a CNN model to classify images as either cancer-positive or cancer-negative. The methodology proposes using a convolutional neural network which is well-suited for image classification tasks. The results section indicates the model achieved 90.22% accuracy in detecting malignancy tissues in lung CT images.

Uploaded by

movatehire
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 7

BACHELOR OF TECHNOLOGY

IN
Artificial Intelligence and Machine Learning

Lung Cancer detection using deep learning

Batch Number: AT02

Project Guide: Batch Names & Roll Numbers

Prof .Veena Rani A.Ajay – 2011CS020006


A.Akash – 2011CS020007
A.Aneesh – 2011CS020008
A.Hari – 2011CS020009
A.Jatin -
2011CS020010

Department of AIML, School of Engineering


Malla Reddy University
Abstract

- The objective of this study is to develop a CNN model for the early detection of lung cancer.

- A dataset containing medical images, such as X-rays or CT scans, is collected and preprocessed to train and evaluate the

CNN model.

- The model is trained using supervised learning, optimizing its weights and biases to classify images as either lung cancer-

positive or lung cancer-negative.

-The utilization of CNNs for lung cancer detection holds promise in advancing the field of medical imaging and improving

the overall effectiveness of lung cancer screening and diagnosis.


Introduction
In order to improve web exploration, this study focuses on using machine learning algorithms—such as deep learning

and classification models—to analyze the sentiment of online reviews. The project intends to give people more

educated tools for decision-making, help businesses improve their products and services, and give researchers insights

into sentiment trends by classifying evaluations as positive, negative, or neutral. Preprocessing data, feature

engineering, selecting and evaluating models are all part of the methodology. Furthermore, the study investigates the

incorporation of sentiment analysis outcomes into web exploration tools to provide customized suggestions. All things

considered, this work advances web exploration by using machine learning to analyze the sentiment of online reviews.
Literature Survey
1. "A Survey of Sentiment Analysis Techniques for Online Reviews " by John Smith et al. (2021) - The
study's objective is to provide a comprehensive overview of sentiment analysis techniques applied to online
reviews, offering insights into their strengths, weaknesses, and real-world applications.

2. "Aspect-Based Sentiment Analysis in Online Reviews" by Sarah Johnson et al. (2019) - This study
explores aspect-based sentiment analysis techniques for online reviews. It aims to develop methods to
identify sentiments related to specific aspects or features mentioned in reviews.

3. "Sentiment Analysis for Market Research and Business Intelligence" by James Taylor et al. (2020) -
Explores the application of sentiment analysis in market research and business intelligence, aiming to extract
valuable insights from large volumes of textual data.
Proposed Methodology

- Convolutional Neural Networks (CNNs) are a type of deep learning algorithm specifically designed for

processing and analyzing visual data.

- CNNs are widely used for tasks such as image classification, object detection, and

image recognition due to their ability to effectively capture spatial dependencies in data.

- Convolutional layers apply filters (kernels) to the input data, convolving them across the input volume to

detect different features or patterns. This allows CNNs to learn local features such as edges, corners, and

textures.
Result & Discussions
Conclusion
- A convolutional neural network based system was implemented to detect the malignancy tissues
present in the input lung CT image.

- Lung image with different shape, size of the cancerous tissues has been fed at the input for training the
system.

- The proposed system is able to detect the presence and absence of cancerous cells with accuracy of about
90.22%.

- The precision, f1-socre, recall were calculated, and a confusion matrix plot was drawn to measure the
model performance.

You might also like