{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T06:16:31Z","timestamp":1783577791218,"version":"3.55.0"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"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. Med. Technol."],"abstract":"<jats:p>Breast cancer is a leading cause of death for women worldwide. There is a critical need for an early and accurate diagnosis to improve survival rates. This study evaluates the performance of transfer learning-based MobileNetV2 and ResNet50 architectures for binary breast cancer classification using mammography images. To enhance channel-wise feature learning, the Squeeze-and-Excitation (SE) attention mechanism was integrated into the network and partial fine tuning was performed by only freezing the early layers of the model. Furthermore, gradient-weighted class activation mapping was applied to visualize the important regions of mammogram images responsible for the model\u2019s predictions. The performance evaluation was carried out on the Contrast Limited Adaptive Histogram Equalization (CLAHE) binary, Digital Database for Screening Mammography (DDSM), INbreast, and Mammographic Image Analysis Society (MIAS) datasets using stratified k-fold cross-validation. The experimental results demonstrate that one of the proposed frameworks, MobileNetV2-SE, achieved mean classification accuracies of 99.14%, 93.53%, 92.35%, and 96.33% on the DDSM, INbreast, MIAS, and CLAHE-binary datasets, respectively. In comparison, the ResNet50-SE model attained mean accuracies of 100%, 88.89%, 71.60%, and 97.98% on the same datasets. The experimental results demonstrate that the frameworks achieve reliable and competitive performance for breast cancer detection under realistic evaluation conditions and improve the diagnostic accuracy of mammogram classification. This work contributes to the field of medical image analysis and computer-aided diagnosis. Future work should focus on applying advanced class balancing methods to improve diagnostic accuracy and model robustness in a variety of medical imaging applications.<\/jats:p>","DOI":"10.3389\/fmedt.2026.1842859","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:36:48Z","timestamp":1783575408000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An attention-based transfer learning framework for breast cancer classification in mammography under limited data conditions"],"prefix":"10.3389","volume":"8","author":[{"given":"Niketa","family":"Banyal","sequence":"first","affiliation":[{"name":"Department of Electronics and Communication Engineering, National Institute of Technology Hamirpur","place":["Hamirpur, Himachal Pradesh, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aman","family":"Kumar","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, National Institute of Technology Hamirpur","place":["Hamirpur, Himachal Pradesh, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"key":"B1","year":""},{"key":"B2","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.jmir.2021.12.002","article-title":"A review of screening mammography: benefits and guidelines","volume":"14","author":"Hooshmand","year":"2022","journal-title":"Breast Cancer Targets Therapy"},{"key":"B3","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1109\/TNB.2018.2845103","article-title":"Classification of whole mammogram and tomosynthesis images using deep convolutional neural networks","volume":"17","author":"Zhang","year":"2018","journal-title":"IEEE Trans NanoBiosci"},{"key":"B4","doi-asserted-by":"publisher","first-page":"11893","DOI":"10.1038\/s41598-024-62324-4","article-title":"AI for interpreting screening mammograms: implications for missed cancer in double reading practices and challenging-to-locate lesions","volume":"14","author":"Jiang","year":"2024","journal-title":"Sci Rep"},{"key":"B5","doi-asserted-by":"publisher","first-page":"81643","DOI":"10.1109\/access.2025.3566353","article-title":"An intelligent smart dynamic feature analysis based approach by utilizing deep learning to improve the breast cancer detection","volume":"13","author":"Shim","year":"2025","journal-title":"IEEE Access"},{"key":"B6","doi-asserted-by":"publisher","first-page":"4815","DOI":"10.1109\/ACCESS.2024.3524633","article-title":"Optimizing breast cancer mammogram classification through a dual approach: a deep learning framework combining ResNet50, SMOTE, and fully connected layers for balanced and imbalanced data","volume":"13","author":"Alshamrani","year":"2025","journal-title":"IEEE Access"},{"key":"B7","doi-asserted-by":"publisher","first-page":"12495","DOI":"10.1038\/s41598-019-48995-4","article-title":"Deep learning to improve breast cancer detection on screening mammography","volume":"9","author":"Shen","year":"2019","journal-title":"Sci Rep"},{"key":"B8","author":"Sumaiyya","year":""},{"key":"B9","doi-asserted-by":"publisher","first-page":"107914","DOI":"10.1016\/j.compbiomed.2023.107914","article-title":"Fusion of transfer learning models with LSTM for detection of breast cancer using ultrasound images","volume":"169","author":"Lanjewar","year":"2024","journal-title":"Comput Biol Med"},{"key":"B10","doi-asserted-by":"publisher","first-page":"100105","DOI":"10.1109\/ACCESS.2025.3576825","article-title":"Advancing breast cancer detection: SE-conformer framework for malignancy detection in histopathology images","volume":"13","author":"Nair","year":"2025","journal-title":"IEEE Access"},{"key":"B11","first-page":"8","article-title":"Enhanced breast cancer tumor classification using MobileNetV2: a detailed exploration on image intensity, error mitigation, and streamlit-driven real-time deployment","volume":"10","author":"Surya","year":"2024","journal-title":"Butler J Undergrad Res"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ACCESS.2025.3594827","article-title":"Enhanced DL-based breast cancer diagnosis and classification using modified DenseNet-121, DenseNet-201, and MobileNetV2: optimized architectures and refined activation functions","volume":"13","author":"Taifi","year":"2025","journal-title":"IEEE Access"},{"key":"B13","doi-asserted-by":"publisher","first-page":"561","DOI":"10.37385\/jaets.v6i1.4836","article-title":"A combined MobileNetV2 and CBAM model to improve classifying the breast cancer ultrasound images","volume":"6","author":"Rakha","year":"2024","journal-title":"J Appl Eng Technol Sci"},{"key":"B14","doi-asserted-by":"publisher","first-page":"108121","DOI":"10.1016\/j.cmpb.2024.108121","article-title":"MOB-CBAM: a dual-channel attention-based deep learning generalizable model for breast cancer molecular subtypes prediction using mammograms","volume":"248","author":"Nissar","year":"2024","journal-title":"Comput Methods Programs Biomed"},{"key":"B15","doi-asserted-by":"publisher","first-page":"106258","DOI":"10.1016\/j.bspc.2024.106258","article-title":"FCCS-Net: Breast cancer classification using multi-level fully convolutional-channel and spatial attention-based transfer learning approach","volume":"95","author":"Maurya","year":"2024","journal-title":"Biomed Signal Process Control"},{"key":"B16","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1007\/s11548-024-03317-6","article-title":"Attention-guided erasing for enhanced transfer learning in breast abnormality classification","volume":"20","author":"Panambur","year":"2025","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"B17","doi-asserted-by":"publisher","first-page":"823","DOI":"10.32604\/cmes.2022.017030.","article-title":"ResNet50-based effective model for breast cancer classification using histopathology images","volume":"130","author":"Behar","year":"2022","journal-title":"Comput Model Eng Sci"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2411","DOI":"10.3390\/tomography8050200","article-title":"Improving performance of breast lesion classification using a ResNet50 model optimized with a novel attention mechanism","volume":"8","author":"Islam","year":"2022","journal-title":"Tomography"},{"key":"B19","doi-asserted-by":"publisher","first-page":"10753","DOI":"10.1038\/s41598-024-60245-w","article-title":"Fine tuning deep learning models for breast tumor classification","volume":"14","author":"Heikal","year":"2024","journal-title":"Sci Rep"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1067","DOI":"10.3390\/diagnostics13061067","article-title":"Classification of breast lesions on DCE-MRI data using fine-tuned MobileNet models","volume":"13","author":"Wang","year":"2023","journal-title":"Diagnostics"},{"key":"B21","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2019","journal-title":"Int J Comput Vis"},{"key":"B22","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1186\/s41747-024-00478-6","article-title":"Deep transfer learning for detection of breast arterial calcifications on mammograms: a comparative study","volume":"8","author":"Mobini","year":"2024","journal-title":"Eur Radiol Exp"},{"key":"B23","doi-asserted-by":"publisher","first-page":"5029","DOI":"10.32604\/cmc.2024.052531","article-title":"Spatial attention integrated EfficientNet architecture for breast cancer classification with explainable AI","volume":"80","author":"Chakravarthy","year":"2024","journal-title":"Comput Mater Contin"},{"key":"B24","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/s10791-025-09785-x","article-title":"Identification of nail diseases using DenseNet169 with leaky ReLu and LSTM with data balancing method","volume":"28","author":"Panchbhai","year":"2025","journal-title":"Multimed Tools Appl"},{"key":"B25","year":""},{"key":"B26","year":""},{"key":"B27","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1109\/TCYB.2024.3483068","article-title":"Fast transfer learning method using random layer freezing and feature refinement strategy","volume":"55","author":"Zhang","year":"2025","journal-title":"IEEE Trans Cybern"},{"key":"B28","doi-asserted-by":"publisher","first-page":"101136","DOI":"10.1016\/j.jrras.2024.101136","article-title":"Advanced deep learning strategies for breast cancer image analysis","volume":"17","author":"Slimi","year":"2024","journal-title":"J Radiat Res Appl Sci"},{"key":"B29","doi-asserted-by":"publisher","first-page":"5481","DOI":"10.11591\/ijece.v14i5.pp5481-5488","article-title":"Detection and classification of breast cancer types using VGG16 and ResNet50 deep learning techniques","volume":"14","author":"Ashwini","year":"2024","journal-title":"Int J Electr Comput Eng"},{"key":"B30","doi-asserted-by":"publisher","first-page":"26","DOI":"10.70968\/ijeaca.v1i2.1","article-title":"Deep learning for improved breast cancer detection: ResNet-50 vs VGG16","volume":"1","author":"Patil","year":"2024","journal-title":"Int J Electron Comput Appl"},{"key":"B31","doi-asserted-by":"publisher","first-page":"105489","DOI":"10.1016\/j.cmpb.2020.105489","article-title":"Classification of breast density categories based on SE-attention neural networks","volume":"193","author":"Deng","year":"2020","journal-title":"Comput Methods Programs Biomed"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1734","DOI":"10.1007\/s10278-024-01271-y","article-title":"MobileNet-v2: an enhanced skin disease classification by attention and multi-scale features","volume":"38","author":"Nirupama","year":"2024","journal-title":"J Imaging Inform Med"},{"key":"B33","doi-asserted-by":"publisher","first-page":"e0214587","DOI":"10.1371\/journal.pone.0214587","article-title":"Breast cancer histopathological image classification using convolutional neural networks with small SE-ResNet module","volume":"14","author":"Jiang","year":"2019","journal-title":"PLoS One"},{"key":"B34","doi-asserted-by":"publisher","first-page":"3668","DOI":"10.3390\/cancers16213668","article-title":"Grad-CAM enabled breast cancer classification with a 3D inception-ResNet v2: empowering radiologists with explainable insights","volume":"16","author":"Talaat","year":"2024","journal-title":"Cancers"},{"key":"B35","doi-asserted-by":"publisher","first-page":"70825","DOI":"10.1109\/ACCESS.2024.3401729","article-title":"FastLeakyResNet-CIR: a novel deep learning framework for breast cancer detection and classification","volume":"12","author":"Zeng","year":"2024","journal-title":"IEEE Access"},{"key":"B36","doi-asserted-by":"publisher","first-page":"2896","DOI":"10.3390\/diagnostics14242896","article-title":"The challenge of deep learning for the prevention and automatic diagnosis of breast cancer: a systematic review","volume":"14","author":"P\u00e9rez-N\u00fa\u00f1ez","year":"2024","journal-title":"Diagnostics"},{"key":"B37","doi-asserted-by":"publisher","first-page":"683","DOI":"10.3390\/diagnostics13040683","article-title":"Accuracy analysis of deep learning methods in breast cancer classification: a structured review","volume":"13","author":"Yusoff","year":"2023","journal-title":"Diagnostics"},{"key":"B38","doi-asserted-by":"publisher","first-page":"2395","DOI":"10.3390\/healthcare10122395","article-title":"Breast cancer dataset, classification and detection using deep learning","volume":"10","author":"Iqbal","year":"2022","journal-title":"Healthcare"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1402","DOI":"10.3390\/diagnostics14131402","article-title":"Attention-based deep learning approach for breast cancer histopathological image multi-classification","volume":"14","author":"Aldakhil","year":"2024","journal-title":"Diagnostics"},{"key":"B40","doi-asserted-by":"publisher","first-page":"133703","DOI":"10.1109\/ACCESS.2024.3461360","article-title":"High performance breast cancer diagnosis from mammograms using mixture of experts with EfficientNet features (MoEffNet)","volume":"12","author":"Ahmed","year":"2024","journal-title":"IEEE Access"}],"container-title":["Frontiers in Medical Technology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmedt.2026.1842859\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:36:49Z","timestamp":1783575409000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmedt.2026.1842859\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,9]]},"references-count":40,"alternative-id":["10.3389\/fmedt.2026.1842859"],"URL":"https:\/\/doi.org\/10.3389\/fmedt.2026.1842859","relation":{},"ISSN":["2673-3129"],"issn-type":[{"value":"2673-3129","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,9]]},"article-number":"1842859"}}