{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:11:04Z","timestamp":1760105464393,"version":"build-2065373602"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioinform."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>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.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This study evaluated three segmentation models\u2014U-Net, U-Net with Spatial Attention, and U-Net++\u2014using 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.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>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.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>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.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fbinf.2025.1609004","type":"journal-article","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:30:26Z","timestamp":1760103026000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Analysis of breast region segmentation in thermal images using U-Net deep neural network variants"],"prefix":"10.3389","volume":"5","author":[{"given":"Rafhanah Shazwani","family":"Rosli","sequence":"first","affiliation":[]},{"given":"Mohamed Hadi","family":"Habaebi","sequence":"additional","affiliation":[]},{"given":"Md Rafiqul","family":"Islam","sequence":"additional","affiliation":[]},{"given":"Mohammed Abdulla Salim","family":"Al Hussaini","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,10,10]]},"reference":[{"key":"B1","first-page":"88","article-title":"Automatic image segmentation of breast thermograms","author":"Adel","year":"2018"},{"key":"B2","doi-asserted-by":"publisher","first-page":"8752","DOI":"10.3390\/app13158752","article-title":"Influence of tissue thermophysical characteristics and situ-cooling on the detection of breast cancer","volume":"13","author":"Al Husaini","year":"2023","journal-title":"Appl. Sci."},{"key":"B3","doi-asserted-by":"publisher","first-page":"49","DOI":"10.33545\/26633582.2022.v4.i1a.68","article-title":"Breast cancer detection based on thermographic images using machine learning and deep learning algorithms","volume":"4","author":"Allugunti","year":"2022","journal-title":"Int. J. Eng. Comput. Sci."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.14830","article-title":"Medical image segmentation review: the success of u-net","author":"Azad","year":"2022","journal-title":"ArXiv Prepr. ArXiv221114830"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/tpami.2016.2644615","article-title":"Segnet: a deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B6","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1080\/21681163.2022.2040053","article-title":"U-Net convolutional neural networks for breast IR imaging segmentation on frontal and lateral view","volume":"11","author":"Carlos de Carvalho","year":"2023","journal-title":"Comput. Methods Biomech. Biomed. Eng. Imaging Vis."},{"key":"B7","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","volume-title":"Computer vision \u2013 ECCV 2018Lecture notes in computer science","author":"Chen","year":"2018"},{"key":"B8","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1177\/1063293x221080518","article-title":"Computer-aided diagnosis for breast cancer detection and classification using optimal region growing segmentation with MobileNet model","volume":"30","author":"Dafni Rose","year":"2022","journal-title":"Concurr. Eng."},{"key":"B9","first-page":"11953","article-title":"Scaling up your kernels to 31\u00d731: revisiting large kernel design in CNNs","author":"Ding","year":"2022"},{"key":"B10","volume-title":"Incorporating nesterov momentum into adam","author":"Dozat","year":"2016"},{"key":"B11","doi-asserted-by":"publisher","first-page":"3516","DOI":"10.3390\/electronics11213516","article-title":"Segmentation of retinal blood vessels using U-Net++ architecture and disease prediction","volume":"11","author":"Gargari","year":"2022","journal-title":"Electronics"},{"key":"B12","doi-asserted-by":"publisher","first-page":"108223","DOI":"10.1016\/j.compeleceng.2022.108223","article-title":"Adaptive enhanced swin transformer with U-net for remote sensing image segmentation","volume":"102","author":"Gu","year":"2022","journal-title":"Comput. Electr. Eng."},{"key":"B13","first-page":"1","article-title":"Segmentation of thermal breast images using convolutional and deconvolutional neural networks","author":"Guan","year":"2018"},{"key":"B14","first-page":"1236","article-title":"SA-UNet: spatial attention U-Net for retinal vessel segmentation","author":"Guo","year":"2021"},{"key":"B15","first-page":"2961","article-title":"Mask r-cnn","author":"He","year":"2017"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1009681","DOI":"10.3389\/fonc.2023.1009681","article-title":"Densely convolutional spatial attention network for nuclei segmentation of histological images for computational pathology","volume":"13","author":"Islam Sumon","year":"2023","journal-title":"Front. Oncol."},{"key":"B17","unstructured":"Adam: a method for stochastic optimization\n          \n          \n            \n              Kingma\n              D. P.\n            \n            \n              Ba\n              J.\n            \n          \n          \n          2014"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tgrs.2022.3217168","article-title":"SSAU-Net: a spectral\u2013spatial attention-based U-Net for hyperspectral image fusion","volume":"60","author":"Liu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"B19","first-page":"1","article-title":"Segmentation of infrared breast images using MultiResUnet neural networks","author":"Lou","year":"2019"},{"key":"B20","first-page":"111","article-title":"Roi extraction in thermographic breast images using genetic algorithms","author":"Mendes","year":"2020"},{"key":"B21","doi-asserted-by":"publisher","first-page":"125523","DOI":"10.1109\/access.2021.3111131","article-title":"Exploring the u-net++ model for automatic brain tumor segmentation","volume":"9","author":"Micallef","year":"2021","journal-title":"IEEE Access"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e0276523","DOI":"10.1371\/journal.pone.0276523","article-title":"A novel CNN pooling layer for breast cancer segmentation and classification from thermograms","volume":"17","author":"Mohamed","year":"2022","journal-title":"PLOS ONE"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.14569\/ijacsa.2023.01406119","article-title":"Brain tumor semantic segmentation using residual U-Net++ encoder-decoder architecture","volume":"14","author":"Mokhtar","year":"2023","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"B24","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/s00138-022-01280-3","article-title":"RCA-IUnet: a residual cross-spatial attention-guided inception U-Net model for tumor segmentation in breast ultrasound imaging","volume":"33","author":"Punn","year":"2022","journal-title":"Mach. Vis. Appl."},{"key":"B25","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/s0893-6080(98)00116-6","article-title":"On the momentum term in gradient descent learning algorithms","volume":"12","author":"Qian","year":"1999","journal-title":"Neural Netw."},{"key":"B26","doi-asserted-by":"publisher","first-page":"191","DOI":"10.2298\/sjee2302191r","article-title":"An automatic segmentation of breast ultrasound images using U-Net model","volume":"20","author":"Radhi","year":"2023","journal-title":"SJEE"},{"key":"B27","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"B28","doi-asserted-by":"publisher","first-page":"53","DOI":"10.13053\/rcs-147-11-5","article-title":"Automatic segmentation in breast thermographic images based on local pattern variations","volume":"147","author":"S\u00e1nchez-Ruiz","year":"2018","journal-title":"Res. Comput. Sci."},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1610.02391","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2016"},{"key":"B30","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1166\/jmihi.2014.1226","article-title":"A new database for breast research with infrared image","volume":"4","author":"Silva","year":"2014","journal-title":"J. Med. Imaging Health Inf."},{"key":"B31","doi-asserted-by":"publisher","first-page":"15273","DOI":"10.1007\/s11042-018-7113-z","article-title":"Automated approaches for ROIs extraction in medical thermography: a review and future directions","volume":"79","author":"Singh","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"B32","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/rbme.2022.3185292","article-title":"Image segmentation for MR brain tumor detection using machine learning: a review","volume":"16","author":"Soomro","year":"2022","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"B33","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"Ca. Cancer J. Clin."},{"key":"B34","doi-asserted-by":"publisher","first-page":"2818","DOI":"10.1109\/CVPR.2016.308","article-title":"Rethinking the inception architecture for computer vision","volume":"2016","author":"Szegedy","year":"2016","journal-title":"Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit."},{"key":"B35","first-page":"6105","article-title":"Efficientnet: rethinking model scaling for convolutional neural networks","volume-title":"Presented at the International conference on machine learning","author":"Tan","year":"2019"},{"key":"B36","first-page":"26","article-title":"Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman","year":"2012","journal-title":"COURSERA Neural Netw. Mach. Learn."},{"key":"B37","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1080\/03772063.2023.2194277","article-title":"Automated breast boundary segmentation to improve the accuracy of identifying abnormalities in breast thermograms","volume":"70","author":"Venkatachalam","year":"2023","journal-title":"IETE J. Res."},{"key":"B38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/4189781","article-title":"U-Net-Based medical image segmentation","volume":"2022","author":"Yin","year":"2022","journal-title":"J. Healthc. Eng."},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1212.5701","article-title":"Adadelta: an adaptive learning rate method","author":"Zeiler","year":"2012","journal-title":"ArXiv Prepr. ArXiv12125701"},{"key":"B40","doi-asserted-by":"publisher","first-page":"8691","DOI":"10.1007\/s11042-022-12067-z","article-title":"Segmentation of skin lesions image based on U-Net++","volume":"81","author":"Zhao","year":"2022","journal-title":"Multimed. Tools Appl."},{"key":"B41","first-page":"3","article-title":"Unet++: a nested u-net architecture for medical image segmentation","author":"Zhou","year":"2018"}],"container-title":["Frontiers in Bioinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2025.1609004\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:30:29Z","timestamp":1760103029000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2025.1609004\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,10]]},"references-count":41,"alternative-id":["10.3389\/fbinf.2025.1609004"],"URL":"https:\/\/doi.org\/10.3389\/fbinf.2025.1609004","relation":{},"ISSN":["2673-7647"],"issn-type":[{"value":"2673-7647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,10]]},"article-number":"1609004"}}