{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T18:08:16Z","timestamp":1789668496005,"version":"4.0.1"},"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:00:00Z","timestamp":1789603200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Breast ultrasound (BU) imaging is widely used for detecting breast abnormalities because it is cost-effective, non-invasive, and suitable for dense breast tissue. However, multi-class classification of BU images is considered a challenging task due to low contrast, speckle noise, and overlapping visual patterns between benign and malignant tumours. To address this issue, we develop a segmentation-guided CNN and Vision Transformer based feature fusion framework for efficient multi-class BU image classification. The framework first applies a lesion segmentation model to identify the region of interest by using Fusion-Enhanced Transformer (FET) Unet model. The FET Unet model uses CNNs and Swin Transformers integrated and constructs a UNet-like architecture. In the second step, CNN-based and Vision Transformer-based features are extracted from the segmented lesion regions. In the third step, the CNN and Vision Transformer features are fused to generate a robust feature representation. A deep neural network classifier comprising four dense layers with 1,024, 512, 256, and 128 neurons, respectively, followed by a softmax output layer, is then developed using the fused features to classify breast ultrasound images into benign, malignant, and normal categories. The proposed framework was evaluated using the publicly available Breast Ultrasound Images (BUSI) dataset, which contains 780 ultrasound images collected from women aged 25\u201375 years, including 437 benign, 210 malignant, and 133 normal cases. Numerical results show that the proposed framework showed 95.11% of accuracy, 95.66% of sensitivity and 97.63% of specificity and F1 score of 0.944644. Based on the classification accuracy, the effectiveness of the proposed hybrid framework is demonstrated in comparison with previously reported methods for multi-class breast ultrasound image classification.<\/jats:p>","DOI":"10.1371\/journal.pone.0353628","type":"journal-article","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T17:36:14Z","timestamp":1789666574000},"page":"e0353628","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["A segmentation-guided CNN\u2013Vision transformer feature fusion framework for multi-class breast ultrasound image classification"],"prefix":"10.1371","volume":"21","author":[{"given":"Meiru","family":"Wu","sequence":"first","affiliation":[{"name":"The Fifth People\u2019s Hospital of Shanxi Province, Shanxi Provincial Geriatric Hospital","place":["Taiyuan, Shanxi, China"],"department":["Department of Ultrasound"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4592-5653","authenticated-orcid":true,"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Jinan Maternity and Child Care Hospital Affiliated to Shandong First Medical University","place":["Jinan, ShanDong, China"],"department":["Department of Breast Surgery"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"pone.0353628.ref001","doi-asserted-by":"crossref","first-page":"78242","DOI":"10.1109\/ACCESS.2022.3174599","article-title":"An Automatic Detection of Breast Cancer Diagnosis and Prognosis Based on Machine Learning Using Ensemble of Classifiers","volume":"10","author":"U Naseem","year":"2022","journal-title":"IEEE Access"},{"issue":"6","key":"pone.0353628.ref002","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1002\/jemt.23222","article-title":"Cloud-based decision support system for the detection and classification of malignant cells in breast cancer using breast cytology images","volume":"82","author":"T Saba","year":"2019","journal-title":"Microsc Res Tech"},{"key":"pone.0353628.ref003","volume-title":"Breast cancer cases and deaths are projected to rise globally","author":"International Agency for Research on Cancer","year":"2025"},{"key":"pone.0353628.ref004","doi-asserted-by":"crossref","first-page":"104863","DOI":"10.1016\/j.dib.2019.104863","article-title":"Dataset of breast ultrasound images","volume":"28","author":"W Al-Dhabyani","year":"2019","journal-title":"Data Brief"},{"issue":"4","key":"pone.0353628.ref005","first-page":"1917","article-title":"Deep learning approaches for classification of breast cancer in ultrasound (US) images","volume":"12","author":"\u0130 Pa\u00e7al","year":"2022","journal-title":"Journal of the Institute of Science and Technology"},{"issue":"17","key":"pone.0353628.ref006","doi-asserted-by":"crossref","first-page":"2235","DOI":"10.3390\/diagnostics15172235","article-title":"Multi-Class Classification of Breast Ultrasound Images Using Vision Transformer-Based Ensemble Learning","volume":"15","author":"TT Y\u0131ld\u0131r\u0131m","year":"2025","journal-title":"Diagnostics (Basel)"},{"key":"pone.0353628.ref007","doi-asserted-by":"crossref","DOI":"10.65278\/IJTACI.2025.16","article-title":"Enhanced Feature Selection for Imbalanced Microarray Cancer Gene Classification Using Chaotic Salp Swarm Algorithm","volume":"2025","author":"B Shehu Aliyu","year":"2025","journal-title":"IJTACI"},{"issue":"11","key":"pone.0353628.ref008","first-page":"5041","article-title":"Extraction of breast border and removal of pectoral muscle in wavelet domain","volume":"28","author":"B Mughal","year":"2017","journal-title":"Biomedical Research"},{"key":"pone.0353628.ref009","doi-asserted-by":"crossref","first-page":"1","DOI":"10.65278\/IJTACI.2026.1","article-title":"Machine Learning\u2013Based Classification Framework for Human Health Care Monitoring","volume":"2026","author":"SZ Kurdi","year":"2026","journal-title":"IJTACI"},{"issue":"5","key":"pone.0353628.ref010","doi-asserted-by":"crossref","DOI":"10.14569\/IJACSA.2019.0100579","article-title":"Deep Learning Approaches for Data Augmentation and Classification of Breast Masses using Ultrasound Images","volume":"10","author":"W Al-Dhabyani","year":"2019","journal-title":"IJACSA"},{"key":"pone.0353628.ref011","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In: 2021."},{"key":"pone.0353628.ref012","first-page":"480","article-title":"Vision Transformers for Classification of Breast Ultrasound Images","volume":"2022","author":"B Gheflati","year":"2022","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"issue":"8","key":"pone.0353628.ref013","doi-asserted-by":"crossref","first-page":"10439","DOI":"10.1007\/s11063-023-11333-x","article-title":"EfficientU-Net: A Novel Deep Learning Method for Breast Tumor Segmentation and Classification in Ultrasound Images","volume":"55","author":"MF Dar","year":"2023","journal-title":"Neural Process Lett"},{"issue":"1","key":"pone.0353628.ref014","doi-asserted-by":"crossref","first-page":"22422","DOI":"10.1038\/s41598-024-72712-5","article-title":"Attention based UNet model for breast cancer segmentation using BUSI dataset","volume":"14","author":"A Sulaiman","year":"2024","journal-title":"Sci Rep"},{"issue":"9","key":"pone.0353628.ref015","doi-asserted-by":"crossref","first-page":"5057","DOI":"10.3390\/curroncol31090374","article-title":"A Novel Deep Learning Model for Breast Tumor Ultrasound Image Classification with Lesion Region Perception","volume":"31","author":"J Wei","year":"2024","journal-title":"Curr Oncol"},{"key":"pone.0353628.ref016","doi-asserted-by":"crossref","first-page":"1672488","DOI":"10.3389\/frai.2025.1672488","article-title":"HED-Net: a hybrid ensemble deep learning framework for breast ultrasound image classification","volume":"8","author":"SS Koshy","year":"2026","journal-title":"Front Artif Intell"},{"issue":"1","key":"pone.0353628.ref017","doi-asserted-by":"crossref","DOI":"10.1186\/s43055-025-01659-y","article-title":"Hybrid deep learning models for automatic segmentation and classification of breast lesions in ultrasound images","volume":"56","author":"A Rahimnezhad","year":"2025","journal-title":"Egypt J Radiol Nucl Med"},{"key":"pone.0353628.ref018","doi-asserted-by":"crossref","first-page":"104871","DOI":"10.1016\/j.bspc.2023.104871","article-title":"Breast UltraSound Image classification using fuzzy-rank-based ensemble network","volume":"85","author":"SD Deb","year":"2023","journal-title":"Biomedical Signal Processing and Control"},{"issue":"11","key":"pone.0353628.ref019","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2023.e22406","article-title":"Breast cancer classification based on convolutional neural network and image fusion approaches using ultrasound images","volume":"9","author":"M Alotaibi","year":"2023","journal-title":"Heliyon"},{"key":"pone.0353628.ref020","doi-asserted-by":"crossref","first-page":"100555","DOI":"10.1016\/j.mlwa.2024.100555","article-title":"Enhancing breast cancer segmentation and classification: An Ensemble Deep Convolutional Neural Network and U-net approach on ultrasound images","volume":"16","author":"MR Islam","year":"2024","journal-title":"Machine Learning with Applications"},{"key":"pone.0353628.ref021","doi-asserted-by":"crossref","first-page":"104969","DOI":"10.1016\/j.ejmp.2025.104969","article-title":"FET-UNet: Merging CNN and transformer architectures for superior breast ultrasound image segmentation","volume":"133","author":"H Zhang","year":"2025","journal-title":"Phys Med"},{"key":"pone.0353628.ref022","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et al. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 2021. 9992\u201310002. https:\/\/doi.org\/10.1109\/iccv48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"pone.0353628.ref023","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 770\u20138. https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"pone.0353628.ref024","doi-asserted-by":"crossref","first-page":"108319","DOI":"10.1016\/j.compbiomed.2024.108319","article-title":"Multi-task learning for segmentation and classification of breast tumors from ultrasound images","volume":"173","author":"Q He","year":"2024","journal-title":"Comput Biol Med"},{"key":"pone.0353628.ref025","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015"},{"key":"pone.0353628.ref026","unstructured":"Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H. Encoder\u2013Decoder with Atrous Separable Convolution for Semantic Image Segmentation. In: Proceedings of the European Conference on Computer Vision. 801\u201318."},{"key":"pone.0353628.ref027","doi-asserted-by":"crossref","unstructured":"Lou M, Meng J, Qi Y, Zhao M, Liu J, Xu Y. MCRNet: Multi-level Context Refinement Network for Semantic Segmentation in Breast Ultrasound Imaging. 470:154\u201369.","DOI":"10.1016\/j.neucom.2021.10.102"},{"issue":"2","key":"pone.0353628.ref028","first-page":"203","article-title":"nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"F Isensee","year":"2021","journal-title":"Medical Image Computing and Computer-Assisted Intervention"},{"issue":"1","key":"pone.0353628.ref029","first-page":"123","article-title":"AAU-Net: An Adaptive Attention U-Net for Breast Lesions Segmentation in Ultrasound Images","volume":"29","author":"G Chen","year":"2023","journal-title":"Journal of Medical Imaging"},{"key":"pone.0353628.ref030","unstructured":"Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y. TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation. https:\/\/doi.org\/arXiv:2102.04306"},{"key":"pone.0353628.ref031","first-page":"102327","article-title":"FAT-Net: Feature Adaptive Transformers for Automated Skin Lesion Segmentation","volume":"76","author":"H Wu","year":"2023","journal-title":"J Biomed Opt"},{"key":"pone.0353628.ref032","first-page":"106533","article-title":"ATFE-Net: Axial Transformer and Feature Enhancement-Based CNN for Ultrasound Breast Mass Segmentation","volume":"153","author":"Z Ma","year":"2023","journal-title":"Ultrasound Med Biol"},{"key":"pone.0353628.ref033","unstructured":"Cao H, Wang Y, Chen J, Jiang D, Zhang X, Tian Q. Swin-Unet: UNet-Like Pure Transformer for Medical Image Segmentation. https:\/\/doi.org\/arXiv:2105.05537"},{"key":"pone.0353628.ref034","doi-asserted-by":"crossref","first-page":"181","DOI":"10.65278\/IJTACI.2025.21","article-title":"Feature Selection Methods in Big Medical Databases:A Comprehensive Survey","author":"M Karimi","year":"2025","journal-title":"IJTACI"},{"key":"pone.0353628.ref035","doi-asserted-by":"crossref","first-page":"105361","DOI":"10.1016\/j.cmpb.2020.105361","article-title":"Computer-aided diagnosis of breast ultrasound images using ensemble learning from convolutional neural networks","volume":"190","author":"WK Moon","year":"2020","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0353628.ref036","doi-asserted-by":"crossref","unstructured":"Xu M, Huang K, Qi X. Multi-Task Learning with Context-Oriented Self-Attention for Breast Ultrasound Image Classification and Segmentation. In: 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), 2022. 1\u20135. https:\/\/doi.org\/10.1109\/isbi52829.2022.9761685","DOI":"10.1109\/ISBI52829.2022.9761685"},{"key":"pone.0353628.ref037","doi-asserted-by":"crossref","first-page":"5377","DOI":"10.1109\/ACCESS.2023.3236693","article-title":"A Regional-Attentive Multi-Task Learning Framework for Breast Ultrasound Image Segmentation and Classification","volume":"11","author":"M Xu","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0353628.ref038","doi-asserted-by":"crossref","first-page":"1517278","DOI":"10.3389\/fonc.2025.1517278","article-title":"Identification of benign and malignant breast nodules on ultrasound: comparison of multiple deep learning models and model interpretation","volume":"15","author":"X Wen","year":"2025","journal-title":"Front Oncol"},{"key":"pone.0353628.ref039","article-title":"Application of YOLO-v7 and YOLO-v8 Transfer Learning Models in Breast Lesion Classification and Diagnosis","volume":"22","author":"K Jiang","year":"2026","journal-title":"Curr Med Imaging"},{"key":"pone.0353628.ref040","doi-asserted-by":"crossref","unstructured":"Ali MD, Saleem A, Elahi H, Khan MA, Khan MI, Yaqoob MM. Breast cancer classification through meta-learning ensemble technique using convolution neural networks. 13:2242.","DOI":"10.3390\/diagnostics13132242"},{"key":"pone.0353628.ref041","doi-asserted-by":"crossref","unstructured":"Xiong G, Li L, Xiong Z. BUSI Classification Based on Singularity-Exponent-Domain Image Feature Transform and Deep Neural Network. In: 2023 8th International Conference on Signal and Image Processing (ICSIP), 2023. 360\u20134. https:\/\/doi.org\/10.1109\/icsip57908.2023.10271078","DOI":"10.1109\/ICSIP57908.2023.10271078"},{"key":"pone.0353628.ref042","unstructured":"Montaha S, Azam S, Bhuiyan M, Chowa S, Mukta S, Jonkman M. Malignancy pattern analysis of breast ultrasound images using clinical features and a graph convolutional network."},{"key":"pone.0353628.ref043","first-page":"12047","article-title":"Few-shot classification of ultrasound breast cancer images using meta-learning algorithms","volume":"36","author":"G Isik","year":"2023","journal-title":"Journal of Biomedical Optics"},{"key":"pone.0353628.ref044","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":"C Aumente-Maestro","year":"2025","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0353628.ref045","doi-asserted-by":"crossref","unstructured":"Saini M, Hassanzadeh S, Musa B, Fatemi M, Alizad A. Variational mode directed deep learning framework for breast lesion classification using ultrasound imaging;15:14300.","DOI":"10.1038\/s41598-025-99009-5"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T17:36:28Z","timestamp":1789666588000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353628"}},"subtitle":[],"editor":[{"given":"Wei","family":"Song","sequence":"first","affiliation":[{"name":"Northeastern University","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,17]]},"references-count":45,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,17]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0353628","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,17]]}}}