Cardiomegaly Prediction using Transfer Learning
International Journal of Creative and Open Research in Engineering and Management · 06.05.2026 · 02 (05) · 1-9
DOI: 10.55041/ijcope.v2i4.754 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Creative and Open Research in Engineering and Management, online erschienen am 06.05.2026. Verfasst von Sachin Sharma und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Cardiomegaly, commonly known as enlargement of the heart, is an important clinical indicator associated with various cardiovascular disorders. Early and accurate detection of this condition is essential to prevent severe complications and improve patient outcomes. In conventional clinical practice, chest X-ray analysis is performed manually by radiologists, which can be time-consuming and may lead to variability in diagnosis due to human interpretation. In this study, we present a comparative analysis of multiple deep learning approaches for automated cardiomegaly detection using chest X-ray images. Specifically, Convolutional Neural Networks (CNNs), U-Net, Vision Transformers, and a proposed hybrid model combining EfficientNetB0 and DenseNet are evaluated. The hybrid approach is designed to leverage EfficientNet’s efficient feature scaling along with DenseNet’s ability to reuse features, thereby improving learning efficiency and prediction performance
Zitieren
APA
Sharma, S., Dubey, R. K., Saini, R., & Choudhary, R. (2026). Cardiomegaly Prediction using Transfer Learning. International Journal of Creative and Open Research in Engineering and Management, 02(05), 1-9. https://doi.org/10.55041/ijcope.v2i4.754
Vancouver
Sharma S, Dubey RK, Saini R, Choudhary R. Cardiomegaly Prediction using Transfer Learning. International Journal of Creative and Open Research in Engineering and Management. 2026;02(05):1-9. doi:10.55041/ijcope.v2i4.754
BibTeX
@article{Sharma2026,
author = {Sharma, Sachin and Dubey, Rohit Kumar and Saini, Rohan and Choudhary, Riya},
title = {Cardiomegaly Prediction using Transfer Learning},
journal = {International Journal of Creative and Open Research in Engineering and Management},
year = {2026},
volume = {02},
number = {05},
pages = {1--9},
doi = {10.55041/ijcope.v2i4.754}
}
EUVIMED