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{185217,
        author = {N.Ruchitha},
        title = {DETECTION OF CARDIOVASCULAR DISEASES IN ECG IMAGES USING DEEP LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {5},
        pages = {627-643},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185217},
        abstract = {cardiovascular diseases (CVDs) are the major mortality in the world, thus requiring early and precise diagnosis to deal with them effectively. ECG imaging is a highly convenient tool that is in common use and examines electrical signals of the heart. This paper introduces a complete deep learning-based system of classification of four types of cardiac related issues which include: normal, abnormal heartbeat, myocardial infarction (MI), and history of MI. The proposed system uses an enhanced set of pre-processing steps, such as Daubechies wavelet filtering, baseline drift correction and the augmentation of synthetic data based on a generative adversarial network (GAN). A hybrid framework of extracting features is used, comprising of Convolutional neural networks (CNNs), Long short-term memory (LSTMs) and Transformers-based encoders that perform aptly to capture both spatial and temporal patterns in ECG images. The architecture can also support modular storage of raw data, feature extraction, and metadata and allow a flexible deployment and expansion. Experimental evidence shows that the proposed model has a classification accuracy of 98.72; a recall of 98.65; a precision of 98.88; and an F1-score of 98.76, which is significantly high and improves all previous best practices in robustness, generalization, and diagnostic performance on all four classes.},
        keywords = {Cardiac disorder classification, DeepLearning, Electrocardiogram.},
        month = {October},
        }