Analysis of breast region segmentation in thermal images using U-Net deep neural network variants
Frontiers in Bioinformatics · 10.10.2025 · 5
DOI: 10.3389/fbinf.2025.1609004 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Bioinformatics, online erschienen am 10.10.2025. Verfasst von Rafhanah Shazwani Rosli und 3 weiteren Autor:innen. Beteiligte Einrichtung: IoT and Wireless Communication Protocols Laboratory, Department of Electrical and Computer Engineering, International Islamic University Malaysia (II…. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Breast cancer detection using thermal imaging relies on accurate segmentation of the breast region from adjacent body areas. Reliable segmentation is essential to improve the effectiveness of computer-aided diagnosis systems.
Methods
This study evaluated three segmentation models—U-Net, U-Net with Spatial Attention, and U-Net++—using five optimization algorithms (ADAM, NADAM, RMSPROP, SGDM, and ADADELTA). Performance was assessed through k-fold cross-validation with metrics including Intersection over Union (IoU), Dice coefficient, precision, recall, sensitivity, specificity, pixel accuracy, ROC-AUC, PR-AUC, and Grad-CAM heatmaps for qualitative analysis.
Results
The ADAM optimizer consistently outperformed the others, yielding superior accuracy and reduced loss. Among the models, the baseline U-Net, despite being less complex, demonstrated the most effective performance, with precision of 0.9721, recall of 0.9559, specificity of 0.9801, ROC-AUC of 0.9680, and PR-AUC of 0.9472. U-Net also achieved higher robustness in breast region overlap and noise handling compared to its more complex variants. The findings indicate that greater architectural complexity does not necessarily lead to improved outcomes.
Discussion
This research highlights that the original U-Net, when trained with the ADAM optimizer, remains highly effective for breast region segmentation in thermal images. The insights contribute to guiding the selection of suitable deep learning models and optimizers for medical image analysis, with the potential to enhance the efficiency and accuracy of breast cancer diagnosis using thermal imaging.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- IoT and Wireless Communication Protocols Laboratory, Department of Electrical and Computer Engineering, International Islamic University Malaysia (IIUM), Kuala Lumpur, Malaysia.
- Faculty of Computer Studies, Arab Open University (AOU), Muscat, Oman.
Zitieren
APA
Rosli, R. S., Habaebi, M. H., Islam, M. R., & Al Hussaini, M. A. S. (2025). Analysis of breast region segmentation in thermal images using U-Net deep neural network variants. Frontiers in Bioinformatics, 5. https://doi.org/10.3389/fbinf.2025.1609004
Vancouver
Rosli RS, Habaebi MH, Islam MR, Al Hussaini MAS. Analysis of breast region segmentation in thermal images using U-Net deep neural network variants. Frontiers in Bioinformatics. 2025;5. doi:10.3389/fbinf.2025.1609004
BibTeX
@article{Rosli2025,
author = {Rosli, Rafhanah Shazwani and Habaebi, Mohamed Hadi and Islam, Md Rafiqul and Al Hussaini, Mohammed Abdulla Salim},
title = {Analysis of breast region segmentation in thermal images using U-Net deep neural network variants},
journal = {Frontiers in Bioinformatics},
year = {2025},
volume = {5},
doi = {10.3389/fbinf.2025.1609004}
}
EUVIMED