AI BASED DIAGNOSTIC SYSTEMS FOR HEART ANOMOLY DETECTION USING CMR and ECG
| dc.contributor.author | ANIKET HERLE1NH21CS027 , ARPEETA SONOLI1NH21CS031 , SRUSTI HIREGOUDAR 1NH21IS158, Ananya K G 1NH21IS014 | |
| dc.date.accessioned | 2025-04-22T09:42:20Z | |
| dc.date.available | 2025-04-22T09:42:20Z | |
| dc.date.issued | 2024 | |
| dc.description.abstract | This project focuses on developing an Al-based diagnostic system for heart anomaly detection, integrating cutting-edge deep learning methodologies for both classification and segmentation tasks using Electrocardiogram (ECG) and Cardiac Magnetic Resonance (CMR) imaging data. By leveraging publicly available datasets, including ECG data from Mendeley and CMR images from the ACDC dataset, the system aims to enhance the precision and efficiency of cardiac diagnostics. The system comprises two key components: ECG Image Classification and CMR Image Segmentation. For ECG classification, convolutional neural networks (CNNs) were employed to detect and classify anomalies in ECG images into five categories: normal, myocardial infarction, dilated cardiomyopathy, hypertrophic cardiomyopathy, and abnormal right ventricle. The classification model incorporates advanced preprocessing techniques, including normalization and denoising, to ensure high-quality inputs for training. The model's output is a probability distribution across the categories, optimized using categorical cross-entropy loss and evaluated with standard metrics like accuracy and F1-score. | |
| dc.identifier.uri | http://192.168.75.5:4000/handle/123456789/17773 | |
| dc.language.iso | en | |
| dc.publisher | NHCE | |
| dc.title | AI BASED DIAGNOSTIC SYSTEMS FOR HEART ANOMOLY DETECTION USING CMR and ECG | |
| dc.type | Other |