Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{171837,
        author = {Srishti Priya and Aman Jha and Dr. Baranidharan B},
        title = {Deep Learning Based Cardiac Health Detection  Using MRI Data Scans and Neural Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {8},
        pages = {1128-1138},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=171837},
        abstract = {Cardiovascular diseases (CVDs) continue to be a primary cause of death worldwide, underscoring the importance of fast and precise diagnostic methods. This study proposes an automated deep learning system designed to detect cardiac anomalies in MRI scans using the ACDC (Automated Cardiac Diagnosis Challenge) dataset. The model utilizes Convolutional Neural Networks (CNNs) along with U-Net architectures to accurately segment and classify different cardiac structures, including the left and right ventricles and the myocardium. To overcome challenges such as class imbalance, high-dimensional data, and MRI artifacts, techniques like data augmentation and dimensionality reduction are applied. The results reveal promising accuracy in the segmentation of cardiac structures and the diagnosis of conditions like myocardial infarction, cardiomyopathy, and right ventricular dysfunction. The proposed approach shows considerable potential for clinical use, providing fast and accurate cardiac diagnoses. We enhance the data set using various augmentation methods, including},
        keywords = {Deep Learning, Cardiac MRI, U-Net, CNN, ACDC Dataset, Cardiovascular Disease},
        month = {January},
        }