{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T04:49:34Z","timestamp":1782103774425,"version":"3.54.5"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"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. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Background and objective<\/jats:title>\n                    <jats:p>In Palestine, breast cancer is the leading cancer in women, constituting more than 34% of all cancer cases in women and 12% of all cancer related deaths. The Palestinian health care system is suffering from shortages, lack of advanced diagnostic equipment, among other issues. This study proposes a new two-step deep learning method for breast cancer detection in mammograms, with a particular focus on the potential of using it in low-resource settings like Palestine. The framework categorizes the tumor and adds a cost-effective and scalable diagnostic support tool that differentiates benign from malignant tumors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The proposed framework operates in two sequential stages. First, a U-Net architecture with a VGG16 encoder backbone, trained from scratch on the CBIS-DDSM mammography dataset, performs lesion segmentation. The CBIS-DDSM training set comprised 2,206 mammograms and the test set 576 images, all with ground truth binary masks. Second, a VGG16 classification model initialized with ImageNet pretrained weights classifies the segmented regions as benign or malignant. The classifier was tested on a subset of 34 patients from the Palestine Hospital dataset (12 benign, 22 malignant), which was used exclusively for external testing, in which no Palestine data were used in training or validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The U-Net segmentation model achieved a mean IoU of 0.70, Dice coefficient of 0.74, precision of 0.78, and recall of 0.71 on the CBIS-DDSM test set. The VGG16 classifier achieved 91% accuracy, 0.91 precision, 0.95 recall (malignant class), and AUC of 0.97 on the Palestine evaluation subset. Comparison against ResNet50 (85% accuracy) and MobileNet (82%) confirms the superiority of the proposed approach.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The present study proposes a promising proof-of-concept deep learning pipeline for breast cancer detection. The results show that it is feasible in a low-resource environment, but would need to be validated on a larger annotated local dataset before deployment. The framework provides a guidance for scalable and cost-effective diagnostic assistance in underserved areas.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1828664","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T04:33:49Z","timestamp":1782102829000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep transfer learning for breast cancer detection in underserved regions"],"prefix":"10.3389","volume":"16","author":[{"given":"Mahmoud","family":"Obaid","sequence":"first","affiliation":[{"name":"Computer System Engineering Department, Arab American University","place":["Jenin, Palestine"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suhail M.","family":"Odeh","sequence":"additional","affiliation":[{"name":"Software Engineering Department, Bethlehem University","place":["Bethlehem, Palestine"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huthaifa I.","family":"Ashqar","sequence":"additional","affiliation":[{"name":"AI and Data Science Department, Arab American University","place":["Jenin, Palestine"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Allam","family":"Abumwais","sequence":"additional","affiliation":[{"name":"Computer System Engineering Department, Arab American University","place":["Jenin, Palestine"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rami","family":"Hodrob","sequence":"additional","affiliation":[{"name":"Computer System Engineering Department, Arab American University","place":["Jenin, Palestine"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3390\/app112210753","article-title":"Existing and emerging breast cancer detection technologies and its challenges: a review","volume":"11","author":"Abdul Halim","year":"2021","journal-title":"Appl Sci"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1002\/cnr2.1764","article-title":"Technological advancements in cancer diagnostics: improvements and limitations","volume":"6","author":"Pulumati","year":"2023","journal-title":"Cancer Rep"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/s0960-9776(21)00048-5","article-title":"Global challenges in breast cancer detection and treatment","volume":"62","author":"Barrios","year":"2022","journal-title":"Breast"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09716-5","article-title":"Deep learning-based breast cancer classification through medical imaging modalities: state of the art and research challenges","volume":"53","author":"Murtaza","year":"2020","journal-title":"Artif Intell Rev"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13111944","article-title":"A new deep-learning-based model for breast cancer diagnosis from medical images","volume":"13","author":"Zakareya","year":"2023","journal-title":"Diagnostics"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.31557\/apjcp.2021.22.7.1987","article-title":"Breast cancer risk from modifiable and non-modifiable risk factors among Palestinian women: a systematic review and meta-analysis","volume":"22","author":"Arafat","year":"2021","journal-title":"Asian Pacific J Cancer Prev"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1200\/go.22.00087","article-title":"Awareness of Palestinian women about breast cancer risk factors: a national cross-sectional study","volume":"8","author":"Elshami","year":"2022","journal-title":"JCO Global Oncol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"295","DOI":"10.21203\/rs.3.rs-1067757\/v1","article-title":"Risk of developing depression among breast cancer patients in Palestine","volume":"22","author":"Sadaqa","year":"2022","journal-title":"BMC Cancer"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/7484631","article-title":"Practice and barriers toward breast self-examination among Palestinian women in Gaza City, Palestine","volume":"2020","author":"Baloushah","year":"2020","journal-title":"Sci World J"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejon.2022.102223","article-title":"Policymakers\u2019 and patients\u2019 perspectives on breast cancer management in the Gaza Strip-Palestine: a qualitative study","volume":"61","author":"Abu-Odah","year":"2022","journal-title":"Eur J Oncol Nurs"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-10707-4","article-title":"Medical image analysis based on deep learning approach","volume":"80","author":"Puttagunta","year":"2021","journal-title":"Multimedia Tools Appl"},{"key":"B12","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41746-021-00438-z","article-title":"Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis","volume":"4","author":"Aggarwal","year":"2021","journal-title":"NPJ Digital Med"},{"key":"B13","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-33128-3_1","article-title":"Deep Learning in Medical Image Analysis","volume-title":"Deep Learning in Medical Image Analysis . Advances in Experimental Medicine and Biology","author":"Chan","year":"2020"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.26719\/emhj.20.036","article-title":"Health information systems in Jordan and Palestine: the need for health informatics training","volume":"26","author":"Jabareen","year":"2020"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1163\/18763375-14030004","article-title":"Palestinian dependence on external health services: de-development as a tool of dispossession","volume":"14","author":"Asi","year":"2022","journal-title":"Middle East Law Governance"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.04.016","article-title":"Artificial intelligence and machine learning for medical imaging: a technology review","volume":"83","author":"Barrag\u00e1n-Montero","year":"2021","journal-title":"Physica Med"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114161","article-title":"Deep and machine learning techniques for medical imaging-based breast cancer: a comprehensive review","volume":"167","author":"Houssein","year":"2021","journal-title":"Expert Syst Appl"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-021-02403-0","article-title":"An SVM approach towards breast cancer classification from H&E-stained histopathology images based on integrated features","volume":"59","author":"Aswathy","year":"2021","journal-title":"Med Biol Eng Comput"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.104089","article-title":"Application of decision tree-based ensemble learning in the classification of breast cancer","volume":"128","author":"Ghiasi","year":"2021","journal-title":"Comput Biol Med"},{"key":"B20","first-page":"3","article-title":"Classification of breast cancer tumors using a random forest on mammogram images","volume":"45","author":"Bukhori","year":"2023","journal-title":"Appl Med Inf"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104248","article-title":"Convolutional neural networks for breast cancer detection in mammography: a survey","volume":"131","author":"Abdelrahman","year":"2021","journal-title":"Comput Biol Med"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05394-5","article-title":"Convolutional neural network-based models for diagnosis of breast cancer","volume":"34","author":"Masud","year":"2022","journal-title":"Neural Comput Appl"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13886","article-title":"Deep learning modeling using normal mammograms for predicting breast cancer risk","volume":"47","author":"Arefan","year":"2020","journal-title":"Med Phys"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djac142","article-title":"Deep learning vs traditional breast cancer risk models to support risk-based mammography screening","volume":"114","author":"Lehman","year":"2022","journal-title":"J Natl Cancer Institute"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3071301","article-title":"Deep learning in medical ultrasound image analysis: a review","volume":"9","author":"Wang","year":"2021","journal-title":"IEEE Access"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102629","article-title":"A review on deep-learning algorithms for fetal ultrasound-image analysis","volume":"83","author":"Fiorentino","year":"2023","journal-title":"Med Image Anal"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106073","article-title":"Breast cancer detection using deep learning: datasets, methods, and challenges ahead","volume":"149","author":"Dar","year":"2022","journal-title":"Comput Biol Med"},{"key":"B28","doi-asserted-by":"crossref","DOI":"10.1109\/IBCAST61650.2024.10877027","article-title":"Beyond boundaries: a novel ensemble approach for breast cancer detection in ultrasound imaging using deep learning","author":"Butt","year":"2024"},{"key":"B29","doi-asserted-by":"publisher","first-page":"13361","DOI":"10.1038\/s41598-025-96437-1","article-title":"Predicting coronary heart disease with advanced machine learning classifiers for improved cardiovascular risk assessment","volume":"15","author":"Rehman","year":"2025","journal-title":"Sci Rep"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-7401588\/v1","article-title":"AdvancedHybridNet: an AI-powered hybrid ensemble for high-accuracy thyroid disease diagnosis using dynamic feature selection","author":"Ur","year":"2025"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-026-21583-1","article-title":"Computer-aided diagnosis for burnt skin images using deep convolutional neural network","volume":"79","author":"Khan","year":"2020","journal-title":"Multimedia Tools Appl"},{"key":"B32","doi-asserted-by":"publisher","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":"2020","journal-title":"Int J Comput Vision"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1828664\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T04:34:02Z","timestamp":1782102842000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1828664\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":32,"alternative-id":["10.3389\/fonc.2026.1828664"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1828664","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,22]]},"article-number":"1828664"}}