Copyright © 2025 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{181801,
        author = {SUJATHA S and MENAKADEVI T},
        title = {Innovative ANN Framework for Cardiac Image Segmentation in Automatic Cardiovascular Disease Diagnosis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {6163-6174},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181801},
        abstract = {Cardiovascular diseases (CVDs) continue to be a significant health challenge globally, responsible for the highest number of deaths annually. Early and accurate diagnosis is crucial for effective treatment and management of these conditions. Recent advancements in medical imaging and computational techniques have paved the way for innovative approaches in diagnosing CVDs. Among these, cardiac image segmentation plays a pivotal role, as it allows for detailed analysis of heart structures and functions. This research focuses on developing an advanced framework leveraging Artificial Neural Networks (ANN) for improved cardiac image segmentation and automatic CVD diagnosis. The proposed algorithm, ResUNet-ANN (RUNN), amalgamates Residual Networks (ResNet) with U-Net for superior image segmentation, complemented by ANN levels for accurate disease diagnosis. Implemented using TensorFlow and PyTorch, RUNN demonstrates significant improvements in segmentation accuracy and diagnostic precision. Extensive simulations were conducted to evaluate the performance of RUNN against existing algorithms. Appropriate simulation metrics were employed to assess segmentation quality, while diagnostic accuracy and computational efficiency were also analyzed. Results indicate that RUNN outperforms the comparative models, achieving higher segmentation precision and enhanced diagnostic accuracy, thereby proving its efficacy for clinical applications. The findings underscore the potential of ResUNet-ANN in transforming cardiac image analysis and automatic CVD diagnosis. Future work will explore real-time implementation and further optimization to integrate RUNN into clinical workflows.},
        keywords = {Artificial Neural Networks, Cardiac Image Segmentation, Diagnostic Precision, Image Segmentation, Residual Networks, Segmentation Accuracy},
        month = {July},
        }