AUTOMATED MYOCARDIAL INFARCTION CLASSIFICATION FROM CARDIAC MRI USING VISION TRANSFORMER ARCHITECTURE
DOI: 
SHARE THIS ARTICLE
DOWNLOAD ARTICLE
REVIEW REPORT
CITE THIS ARTICLE
One of the main causes of death globally is a myocardial infarction, also referred to as a heart attack, which is a sudden reduction in the heart's blood flow. Survival rates are significantly increased by early identification of this illness. Because MRI can reveal the heart’s internal structure with high clarity, it can detect damaged heart muscle that standard tests may miss. However, manually analyzing large numbers of MRI images is time-consuming and heavily dependent on the observer’s expertise. In this work, an automated system for myocardial infarction detection from cardiac MRI images is proposed using a Vision Transformer (ViT) based deep learning model. The EMIDEC cardiac MRI dataset, which includes both healthy subjects and patients with myocardial infarction, is used in this study.To make key cardiac structures more visible, the MRI volumes are first transformed into two-dimensional slices and then preprocessed using noise reduction, contrast enhancement, scaling, and normalization. Further visual analysis with ROC curves and confidence-based assessment bolsters the system's efficacy and stability. The system has a high test accuracy of 97.63%, which shows that most of the MRI slices were correctly identified. This proposed system shows that Vision Transformer-based models can be effectively used for automatic myocardial infarction detection from cardiac MRI images, providing doctors with a useful tool for decision-support and facilitating prompt and precise diagnosis
Keywords
Article Information
Article Metrics
HOW TO CITE
Copy
PRADEEPA, R. & C.USHARANI, (2026). Automated Myocardial Infarction Classification from Cardiac MRI using Vision Transformer Architecture. International Journal of Science, Strategic Management and Technology, 02(03). https://doi.org/10.55041/ijsmt.v2i3.248
PRADEEPA, R., and C.USHARANI. "Automated Myocardial Infarction Classification from Cardiac MRI using Vision Transformer Architecture." International Journal of Science, Strategic Management and Technology, vol. 02, no. 03, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i3.248.
PRADEEPA, R., and C.USHARANI. "Automated Myocardial Infarction Classification from Cardiac MRI using Vision Transformer Architecture." International Journal of Science, Strategic Management and Technology 02, no. 03 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i3.248.
References
2.Litjens,G.,Kooi,T.,Bejnordi,B.E.,etal.,“A survey on deep learning in medical image analysis,”Medical Image Analysis, Vol. 42, pp. 60–88, 2017.
3.Esteva, A., Kuprel, B., Novoa, R. A., et al.,“Dermatologist-level classification of skin cancer with deep neural networks,”Nature, Vol. 542, pp. 115–118, 2017.
4.Ronneberger,O.,Fischer,P.,andBrox,T.,“U-Net: Convolutional Networks for Biomedical ImageSegmentation,”MICCAI, 2015.
5.He,K.,Zhang,X.,Ren,S.,andSun,J.,“Deep Residual Learning for Image Recognition,”
Proceedings of CVPR, 2016.
6.Simonyan,K.,andZisserman,A.,“Very Deep Convolutional Networks for Large-Scale ImageRecognition,”ICLR, 2015.
7.Chen,J.,Lu,Y.,Yu,Q.,etal.,“TransUNet: Transformers Make Strong Encoders for Medical ImageSegmentation,”arXiv preprint arXiv:2102.04306, 2021.
8.Hatamizadeh, A., Nath, V., Tang, Y., et al.,“Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images,”MICCAI, 2022.
9.Isensee,F.,Petersen,J.,Kohl,S.,etal.,“nnU-Net: a self-configuring method for deep learning-basedbiomedicalimagesegmentation,”Nature Methods, Vol. 18, pp. 203–211, 2021.
10.Oktay,O.,Schlemper,J.,Folgoc,L.L.,etal.,“Attention U-Net: Learning Where to Look for the Pancreas,”arXiv preprint arXiv:1804.03999, 2018.
Ethics and Compliance
Indexed In
Similar Articles
Previous Article
