EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Transfer-Learned Convolutional Networks for Multiclass Recognition of Myocardial Infarction and Cardiac Abnormalities in ECG Images

Zia-ur Rehman, Farhat Abbas, Syed Zeeshan Mahmood Shah, Ghulam Ali

Computational Systems and Artificial Intelligence · 08.11.2026 · 2 (1) · 38-44

DOI: 10.69882/adba.csai.2026016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational Systems and Artificial Intelligence, online erschienen am 08.11.2026. Verfasst von Zia-ur Rehman und 3 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate interpretation of electrocardiograms (ECGs) is central to the early recognition of myocardial infarction and other cardiac abnormalities, yet visual assessment may be affected by subtle inter-class similarities, recording artifacts, and reader-dependent variability. This study presents a controlled comparison of three transfer-learned convolutional neural networks, ResNet-50, ConvNeXt-Tiny, and DenseNet-201, for four-class classification of ECG images. The dataset comprised 3,951 images assigned to abnormal heartbeat, history of myocardial infarction, myocardial infarction, and normal ECG categories. A stratified split allocated 3,159 images to training, 393 to validation, and 399 to independent testing. All models were initialized with ImageNet weights, fine-tuned at an input resolution of 224 × 224 pixels, and assessed using accuracy, macro-averaged precision, recall, F1-score, parameter count, floating-point operations, and inference latency. DenseNet-201 achieved the strongest diagnostic performance, with 99.50% accuracy, 99.48% precision, 99.29% recall, and a 99.37% F1-score, while using 18.10 million trainable parameters. ResNet-50 produced closely comparable accuracy (99.25%) and the lowest latency (0.6949 ms per image), indicating a favorable option for time-sensitive deployment. ConvNeXt-Tiny reached 66.67% accuracy and showed substantially weaker generalization under the common training protocol. The findings indicate that dense feature reuse is particularly effective for preserving subtle ECG morphology, whereas residual learning offers an advantageous accuracy–latency balance. External, patient-level validation remains necessary before clinical use, especially because highly accurate image classifiers may exploit dataset-specific acquisition cues in addition to physiologically meaningful patterns.

Zitieren

APA

Rehman, Z., Abbas, F., Shah, S. Z. M., & Ali, G. (2026). Transfer-Learned Convolutional Networks for Multiclass Recognition of Myocardial Infarction and Cardiac Abnormalities in ECG Images. Computational Systems and Artificial Intelligence, 2(1), 38-44. https://doi.org/10.69882/adba.csai.2026016

Vancouver

Rehman Z, Abbas F, Shah SZM, Ali G. Transfer-Learned Convolutional Networks for Multiclass Recognition of Myocardial Infarction and Cardiac Abnormalities in ECG Images. Computational Systems and Artificial Intelligence. 2026;2(1):38-44. doi:10.69882/adba.csai.2026016

BibTeX
@article{Rehman2026,
  author = {Rehman, Zia-ur and Abbas, Farhat and Shah, Syed Zeeshan Mahmood and Ali, Ghulam},
  title = {Transfer-Learned Convolutional Networks for Multiclass Recognition of Myocardial Infarction and Cardiac Abnormalities in ECG Images},
  journal = {Computational Systems and Artificial Intelligence},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {38--44},
  doi = {10.69882/adba.csai.2026016}
}
Kostenlos starten →