{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:57:21Z","timestamp":1783385841973,"version":"3.54.6"},"reference-count":37,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Worldwide, breast cancer is the leading cause of death in women. This emphasizes the significance of an accurate breast cancer detection system. This study presents a unified framework for segmentation of breast cancer using multimodal imaging, such as histopathology, MRI, mammogram, and ultrasound. This framework integrates the CNN with Transformer modules and has three core technical innovations. First, features are extracted using an encoder\u2013decoder design. The encoder has Residual Blocks with a base channel of 32, following feature extraction, which are progressively mapped and downsampled into four stages (32 \u2192 64 \u2192 128 \u2192 256) of channels. The spatial channel is reduced using MaxPool2d operations from 256 \u00d7 256 to 128 \u00d7 128, 64 \u00d7 64, 32 \u00d7 32, and 16 \u00d7 16. After further convolutional refinement, a Transformer encoder is used on the 16 \u00d7 16 feature maps in the bottleneck. The Transformer comprises four encoders with multi-head self-attention (eight heads) and a 4.0 MLP ratio, enabling the model to capture local and global contextual dependencies at the lowest resolution. The proposed framework is trained with a learning rate of 1 \u00d7 10\u22124, up to 50 epochs with early stopping (patience = 12), using a combined Dice and binary cross-entropy loss that balances pixel-wise accuracy and overlap-based learning. Gradient clipping with a maximum norm of 5.0 is used to ensure training stability; ReduceLROnPlateau (factor = 0.5, patience = 5) is used to dynamically adjust the learning rate; and early stopping is used to prevent overfitting. To improve generalization and enhance robustness to data variability, data augmentation techniques such as random horizontal and vertical flips, intensity variations, and small rotations (\u00b115\u00b0) are applied. Incremental learning was implemented in this study as a warm-start fine-tuning strategy, where the model was initialized based on learned weights from a previously trained model instead of training from scratch. This is done by loading saved checkpoints of the best-performing model and continuing training on a new dataset. The performance of the proposed framework is evaluated on four publicly available datasets and one local dataset, such as BUS-UCLM, BUSI, BreastDM, TNBC NucleiSegmentation, and BCSD-2024. The impressive results are achieved with Dice scores of 0.974 on ULCM, 0.975 on BUSI, 0.971 on BreastDM, 0.904 on TNBC nuclei segmentation, and 0.982 on BCSD-2024. The proposed model consistently performed better than classical U-Net models.<\/jats:p>","DOI":"10.3390\/bioengineering13050570","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T14:12:54Z","timestamp":1779286374000},"page":"570","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Sequential Transfer Learning for Multi-Domain Breast Image Segmentation Using a Transformer-Enhanced Hybrid U-Net"],"prefix":"10.3390","volume":"13","author":[{"given":"Shagufta","family":"Manzoor","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Wah, Wah Cantt 47040, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4418-1451","authenticated-orcid":false,"given":"Javaria","family":"Amin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Rawalpindi Women University, Rawalpindi 43600, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0716-3932","authenticated-orcid":false,"given":"Amad","family":"Zafar","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence and Robotics, Sejong University, Seoul 05006, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Agarwal, P., Yadav, A., and Mathur, P. (2021). Breast cancer prediction on breakhis dataset using deep cnn and transfer learning model. Data Engineering for Smart Systems: Proceedings of SSIC 2021, Springer.","DOI":"10.1007\/978-981-16-2641-8_8"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"102466","DOI":"10.1016\/j.media.2022.102466","article-title":"End-to-end diagnosis of breast biopsy images with transformers","volume":"79","author":"Mehta","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2999","DOI":"10.1002\/mp.17650","article-title":"Hybrid transformer-based model for mammogram classification by integrating prior and current images","volume":"52","author":"Jeny","year":"2025","journal-title":"Med. Phys."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/s12559-026-10554-1","article-title":"Hybrid Loss-Driven Attention Residual U-Net with Multiscale Cascaded CBAM for Breast Cancer Segmentation","volume":"18","author":"Mehwish","year":"2026","journal-title":"Cogn. Comput."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Hussain, S., Ali, M., Naseem, U., Palomo, B.A.B., Molina, M.A.M., Abdala, J.A.G., Avalos, D.B.A., Cardona-Huerta, S., Gulliver, T.A., and Pena, J.G.T. (2024). Performance evaluation of deep learning and transformer models using multimodal data for breast cancer classification. MICCAI Workshop on Cancer Prevention Through Early Detection, Springer Nature.","DOI":"10.1007\/978-3-031-73376-5_6"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"S22007","DOI":"10.1117\/1.JMI.12.S2.S22007","article-title":"Enhancing breast cancer detection on screening mammogram using self-supervised learning and a hybrid deep model of Swin Transformer and convolutional neural networks","volume":"12","author":"Chen","year":"2025","journal-title":"J. Med. Imaging"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"108116","DOI":"10.1016\/j.bspc.2025.108116","article-title":"InceptionNeXt-Transformer: A novel multi-scale deep feature learning architecture for multimodal breast cancer diagnosis","volume":"110","author":"Ishak","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Lu, Y., Sun, F., Wang, J., and Yu, K. (2025). Automatic joint segmentation and classification of breast ultrasound images via multi-task learning with object contextual attention. Front. Oncol., 15.","DOI":"10.3389\/fonc.2025.1567577"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Aslam, M.A., Naveed, A., and Ahmed, N. (2025). Hybrid Attention Network for Accurate Breast Tumor Segmentation in Ultrasound Images. arXiv.","DOI":"10.1038\/s41598-025-23213-6"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Mallina, R., and Shareef, B. (2025). XBusNet: Text-Guided Breast Ultrasound Segmentation via Multimodal Vision-Language Learning. arXiv.","DOI":"10.3390\/diagnostics15222849"},{"key":"ref_11","unstructured":"Mehmood, A., Hu, Y., and Khan, S.H. (2025). A Novel Channel Boosted Residual CNN-Transformer with Regional-Boundary Learning for Breast Cancer Detection. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Mienye, D., Swart, T.G., Obaido, G., Jordan, M., and Ilono, P. (2025). Deep convolutional neural networks in medical image analysis: A review. Information, 16.","DOI":"10.3390\/info16030195"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"109305","DOI":"10.1016\/j.bspc.2025.109305","article-title":"Wavelet-transformer hybrid network for robust breast ultrasound image segmentation with multi-scale feature fusion and global context modeling","volume":"114","author":"Jia","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_14","first-page":"664","article-title":"SwinUNet: A Hybrid Swin Transformer-CNN Architecture with Adaptive Feature Fusion for Breast Ultrasound Lesion Segmentation","volume":"4","author":"Naz","year":"2026","journal-title":"Spectr. Eng. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"108827","DOI":"10.1016\/j.bspc.2025.108827","article-title":"A multimodal ensemble framework for breast cancer segmentation and classification using genetic U-Net and HBoost","volume":"112","author":"Guru","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Peter, O.O.E., Emakporuena, D., Tunde, B.D., Abdulkarim, M., and Umar, A.B. (2025). Transformer-Based Explainable Deep Learning for Breast Cancer Detection in Mammography: The MammoFormer Framework. arXiv.","DOI":"10.11648\/j.ajcst.20250802.16"},{"key":"ref_17","unstructured":"Agbodike, O., Kuo, C.-F., and Chen, J. (2025, January 9\u201311). Deep Multi-Head CNN for Unified Breast Density Segmentation and BI-RADS Estimation in 2D Mammograms. Proceedings of the Medical Imaging with Deep Learning (MIDL 2025), Salt Lake City, UT, USA."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"KumarSaha, D., Hossain, T., Safran, M., Alfarhood, S., Mridha, M.F., and Che, D. (2024). Segmentation for mammography classification utilizing deep convolutional neural network. BMC Med. Imaging, 24.","DOI":"10.1186\/s12880-024-01510-2"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"35106","DOI":"10.1038\/s41598-025-19173-6","article-title":"TransBreastNet a CNN transformer hybrid deep learning framework for breast cancer subtype classification and temporal lesion progression analysis","volume":"15","author":"Brahmareddy","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Al Mansour, G., Alshomrani, F., Alfahaid, A., and Almutairi, A.T. (2025). MammoViT: A custom vision transformer architecture for accurate BIRADS classification in mammogram analysis. Diagnostics, 15.","DOI":"10.3390\/diagnostics15030285"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Varshney, T., Verma, K., Kaur, A., and Puri, S.K. (2024). Hybrid Fusion Approach Using CNN and Vision Transformer for Breast Cancer Classification from Mammograms. International Conference on Advances in Data-Driven Computing and Intelligent Systems, Springer.","DOI":"10.1007\/978-981-96-4536-7_39"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"77187","DOI":"10.1109\/ACCESS.2025.3563218","article-title":"A Robust Hybrid CNN+ViTFramework For Breast Cancer Classification Using Mammogram Images","volume":"13","author":"Patheda","year":"2025","journal-title":"IEEE Access"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1007\/s44163-025-00335-4","article-title":"Breast cancer classification using breast ultrasound images with a hybrid of transfer learning and Bayesian-optimized fast learning network","volume":"5","author":"Ahishakiye","year":"2025","journal-title":"Discov. Artif. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"108795","DOI":"10.1016\/j.bspc.2025.108795","article-title":"SwinEff-AttentionNet: A dual hybrid model for breast image segmentation and classification using multiple ultrasound modality","volume":"112","author":"Nissar","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1468","DOI":"10.1016\/j.ultrasmedbio.2025.05.017","article-title":"Efficient Ultrasound Breast Cancer Detection with DMFormer: A Dynamic Multi-scale Fusion Transformer","volume":"51","author":"Guo","year":"2025","journal-title":"Ultrasound Med. Biol."},{"key":"ref_26","first-page":"380","article-title":"Vision Transformer for the Categorization of Breast Cancer from H&E Histopathology Images","volume":"13","author":"Hossain","year":"2025","journal-title":"J. Image Graph."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"108138","DOI":"10.1016\/j.bspc.2025.108138","article-title":"A convolution and transformer-based method with effective stain normalization for breast cancer detection from whole slide images","volume":"110","author":"Goceri","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"109030","DOI":"10.1016\/j.cmpb.2025.109030","article-title":"Advanced multimodal for Segmentation and Classification of breast cancer with DenseNet and Optimal Attention approach","volume":"272","author":"Wang","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_29","unstructured":"Amin, J., and Manzoor, S. (2026, May 14). BCSD-2024. Mendeley Data, V1. Available online: https:\/\/data.mendeley.com\/datasets\/fc72nbt5y2\/1."},{"key":"ref_30","unstructured":"(2026, May 14). BUS-UCLM: Breast Ultrasound Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/orvile\/bus-uclm-breast-ultrasound-dataset."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"104863","DOI":"10.1016\/j.dib.2019.104863","article-title":"Dataset of breast ultrasound images","volume":"28","author":"Gomaa","year":"2020","journal-title":"Data Brief"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1109\/TMI.2018.2865709","article-title":"Segmentation of nuclei in histopathology images by deep regression of the distance map","volume":"38","author":"Naylor","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"107255","DOI":"10.1016\/j.compbiomed.2023.107255","article-title":"BreastDM: A DCE-MRI dataset for breast tumor image segmentation and classification","volume":"164","author":"Zhao","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"108540","DOI":"10.1016\/j.cmpb.2024.108540","article-title":"A multi-task framework for breast cancer segmentation and classification in ultrasound imaging","volume":"260","author":"Carlos","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"109654","DOI":"10.1016\/j.bspc.2026.109654","article-title":"Improving nuclei segmentation in histopathological images: A hybrid deep learning architecture with self-attention and Multi-Scale Residual Dilated Blocks","volume":"117","author":"Miguel","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"113216","DOI":"10.1016\/j.patcog.2026.113216","article-title":"SDC-Net: Semi-Supervised Breast Ultrasound Lesion Segmentation via Semantic Decoupling","volume":"176","author":"Zhang","year":"2026","journal-title":"Pattern Recognit."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"107757","DOI":"10.1016\/j.bspc.2025.107757","article-title":"A self-supervised representation learning paradigm with global content perception and peritumoral context restoration for MRI breast tumor segmentation","volume":"107","author":"Meng","year":"2025","journal-title":"Biomed. Signal Process. Control"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/5\/570\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T14:39:12Z","timestamp":1779287952000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/5\/570"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":37,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["bioengineering13050570"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13050570","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]}}}