Diagnosis Support Model of Cardiomegaly based on CNN using ResNet and Explainable Feature Map

Project Code :TCMAPY1041


The objective of this project is to develop a Diagnosis Support Model for Cardiomegaly based on Convolutional Neural Networks (CNN) using the ResNet architecture, while incorporating Explainable Feature Maps. This model aims to enhance the accuracy and interpretability of cardiomegaly diagnosis in medical imaging, ultimately assisting healthcare professionals in making more informed decisions.


This study presents a Diagnosis Support Model for Cardiomegaly using Convolutional Neural Networks (CNNs) with a focus on the Residual Network (ResNet) architecture, enhanced by Explainable Feature Maps. Cardiomegaly is a critical cardiac condition characterized by an enlarged heart, and early detection is vital for timely intervention. This research aims to leverage deep learning techniques to automatically classify X-ray images and provide clinicians with an efficient diagnostic tool. By incorporating Explainable Feature Maps, the model enhances interpretability, assisting medical professionals in understanding the key visual cues driving the classification decisions. The proposed model holds promise for accurate and transparent Cardiomegaly diagnosis.

Keywords: Deep learning, Cardiomegaly, image classification, Resnet, mobilenet

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.

Block Diagram



Processor - I3/Intel Processor

Hard Disk - 160GB

Key Board - Standard Windows Keyboard

Mouse - Two or Three Button Mouse

Monitor - SVGA



Operating System :  Windows 7/8/10

Server side Script :  HTML, CSS, Bootstrap & JS

Programming Language :  Python

Libraries :  Flask, Pandas, Mysql.connector, Os, Smtplib, Numpy

IDE/Workbench :  PyCharm

Technology :  Python 3.6+

Server Deployment :  Xampp Server

Demo Video

Request Video

Related Projects

Final year projects