{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T08:32:41Z","timestamp":1778574761927,"version":"3.51.4"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:00:00Z","timestamp":1750204800000},"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. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Breast cancer is a severe illness predominantly affecting women, and in most cases, it leads to loss of life if left undetected. Early detection can significantly reduce the mortality rate associated with breast cancer. Ultrasound imaging has been widely used for effectively detecting the disease, and segmenting breast ultrasound images aid in the identification and localization of tumors, thereby enhancing disease detection accuracy. Numerous computer-aided methods have been proposed for the segmentation of breast ultrasound images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A deep learning-based architecture utilizing a ConvMixer-based encoder and ConvNeXT-based decoder coupled with convolution-enhanced multihead attention has been proposed for segmenting breast ultrasound images. The enhanced ConvMixer modules utilize spatial filtering and channel-wise integration to efficiently capture local and global contextual features, enhancing feature relevance and thus increasing segmentation accuracy through dynamic channel recalibration and residual connections. The bottleneck with the attention mechanism enhances segmentation by utilizing multihead attention to capture long-range dependencies, thus enabling the model to focus on relevant features across distinct regions. The enhanced ConvNeXT modules with squeeze and excitation utilize depthwise convolution for efficient spatial filtering, layer normalization for stabilizing training, and residual connections to ensure the preservation of relevant features for accurate segmentation. A combined loss function, integrating binary cross entropy and dice loss, is used to train the model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The proposed model has an exceptional performance in segmenting intricate structures, as confirmed by comprehensive experiments conducted on two datasets, namely the breast ultrasound image dataset (BUSI) dataset and the BrEaST dataset of breast ultrasound images. The model achieved a Jaccard index of 98.04% and 94.84% and a Dice similarity coefficient of 99.01% and 97.35% on the BUSI and BrEaST datasets, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The ConvMixer and ConvNeXT modules are integrated with convolution-enhanced multihead attention, which enhances the model's ability to capture local and global contextual information. The strong performance of the model on the BUSI and BrEaST datasets demonstrates the robustness and generalization capability of the model.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2025.1572433","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:49:49Z","timestamp":1750225789000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["HMA-Net: a hybrid mixer framework with multihead attention for breast ultrasound image segmentation"],"prefix":"10.3389","volume":"8","author":[{"given":"Soumya","family":"Sara Koshy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L. Jani","family":"Anbarasi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"106438","DOI":"10.1016\/j.compbiomed.2022.106438","article-title":"An open-access breast lesion ultrasound image database: applicable in artificial intelligence studies","volume":"152","author":"Abbasian Ardakani","year":"2023","journal-title":"Comput. Biol. Med"},{"key":"B2","first-page":"1","article-title":"\u201cConvMixer-UNet: a lightweight network for breast lesion segmentation in ultrasound images\u201d","volume-title":"2023 20th ACS\/IEEE International Conference on Computer Systems and Applications","author":"AbdElhakem","year":"2023"},{"key":"B3","first-page":"40","author":"Adrian","year":"2022"},{"key":"B4","doi-asserted-by":"publisher","first-page":"104863","DOI":"10.1016\/j.dib.2019.104863","article-title":"Dataset of breast ultrasound images","volume":"28","author":"Al-Dhabyani","year":"2020","journal-title":"Data Brief"},{"key":"B5","author":"Almajalid","year":"2018"},{"key":"B6","doi-asserted-by":"publisher","first-page":"119939","DOI":"10.1016\/j.eswa.2023.119939","article-title":"DSEU-net: A novel deep supervision SEU-net for medical ultrasound image segmentation","volume":"223","author":"Chen","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"B7","doi-asserted-by":"publisher","first-page":"10273","DOI":"10.1016\/j.jksuci.2022.10.020","article-title":"Deep Learning-based Multi-stage segmentation method using ultrasound images for breast cancer diagnosis","volume":"34","author":"Cho","year":"2022","journal-title":"J. King Saud Univers.-Comp. Inform. Sci"},{"key":"B8","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1001\/jamaoncol.2023.4837","article-title":"Global stage distribution of breast cancer at diagnosis: a systematic review and meta-analysis","volume":"10","author":"Fuentes","year":"2024","journal-title":"JAMA Oncol."},{"key":"B9","first-page":"2195","article-title":"\u201cMultimodal multi-head convolutional attention with various kernel sizes for medical image super-resolution,\u201d","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Georgescu","year":"2023"},{"key":"B10","doi-asserted-by":"publisher","first-page":"106629","DOI":"10.1016\/j.compbiomed.2023.106629","article-title":"HCTNet: a hybrid CNN-transformer network for breast ultrasound image segmentation","volume":"155","author":"He","year":"2023","journal-title":"Comp. Biol. Med."},{"key":"B11","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1118\/1.1386426","article-title":"Automatic segmentation of breast lesions on ultrasound","volume":"28","author":"Horsch","year":"2001","journal-title":"Med. Phys"},{"key":"B12","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.neucom.2021.04.012","article-title":"Semantic segmentation of breast ultrasound image with fuzzy deep learning network and breast anatomy constraints","volume":"450","author":"Huang","year":"2021","journal-title":"Neurocomputing"},{"key":"B13","doi-asserted-by":"publisher","first-page":"101657","DOI":"10.1016\/j.media.2020.101657","article-title":"Segmentation of breast ultrasound image with semantic classification of superpixels","volume":"61","author":"Huang","year":"2020","journal-title":"Med. Image Analy."},{"key":"B14","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1016\/j.ultrasmedbio.2003.12.001","article-title":"Watershed segmentation for breast tumor in 2-D sonography","volume":"30","author":"Huang","year":"2004","journal-title":"Ultrasound Med. Biol."},{"key":"B15","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1016\/j.bbe.2021.05.007","article-title":"A method for segmentation of tumors in breast ultrasound images using the variant enhanced deep learning","volume":"41","author":"Ilesanmi","year":"2021","journal-title":"Biocybernet. Biomed. Eng."},{"key":"B16","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1016\/j.bbe.2023.09.001","article-title":"A dual-stage transformer and MLP-based network for breast ultrasound image segmentation","volume":"43","author":"Lin","year":"2023","journal-title":"Biocybernet. Biomed. Eng."},{"key":"B17","first-page":"11976","article-title":"\u201cA convnet for the 2020s,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Liu","year":"2022"},{"key":"B18","doi-asserted-by":"publisher","first-page":"104425","DOI":"10.1016\/j.bspc.2022.104425","article-title":"AMS-PAN: Breast ultrasound image segmentation model combining attention mechanism and multi-scale features","volume":"81","author":"Lyu","year":"2023","journal-title":"Biomed. Signal Proc. Cont."},{"key":"B19","doi-asserted-by":"publisher","first-page":"042901","DOI":"10.1118\/1.4869264","article-title":"Tumor detection in automated breast ultrasound images using quantitative tissue clustering","volume":"41","author":"Moon","year":"2014","journal-title":"Med. Phys."},{"key":"B20","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1038\/s41597-024-02984-z","article-title":"Curated benchmark dataset for ultrasound based breast lesion analysis","volume":"11","author":"Paw\u0142owska","year":"2024","journal-title":"Scient. Data"},{"key":"B21","doi-asserted-by":"publisher","first-page":"6105","DOI":"10.1002\/mp.12538","article-title":"Open access database of raw ultrasonic signals acquired from malignant and benign breast lesions","volume":"44","author":"Piotrzkowska-Wr\u00f3blewska","year":"2017","journal-title":"Med. Phys"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2262","DOI":"10.3390\/healthcare10112262","article-title":"Estan: Enhanced small tumor-aware network for breast ultrasound image segmentation","volume":"10","author":"Shareef","year":"2022","journal-title":"Healthcare"},{"key":"B23","doi-asserted-by":"crossref","DOI":"10.1109\/ISBI53787.2023.10230609","article-title":"\u201cCMU-NET: a strong convmixer-based medical ultrasound image segmentation network,\u201d","volume-title":"2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)","author":"Tang","year":"2023"},{"key":"B24","doi-asserted-by":"publisher","first-page":"102721","DOI":"10.1016\/j.bspc.2021.102721","article-title":"Improved U-net MALF model for lesion segmentation in breast ultrasound images","volume":"68","author":"Tong","year":"2021","journal-title":"Biomed. Signal Proc. Cont."},{"key":"B25","doi-asserted-by":"publisher","author":"Trockman","year":"2022","DOI":"10.48550\/arXiv.2201.09792"},{"key":"B26","doi-asserted-by":"publisher","first-page":"105707","DOI":"10.1016\/j.bspc.2023.105707","article-title":"Convmixer-based encoder and classification-based decoder architecture for breast lesion segmentation in ultrasound images","volume":"89","author":"\u00dczen","year":"2024","journal-title":"Biomed. Signal Proc. Cont."},{"key":"B27","doi-asserted-by":"publisher","first-page":"2819","DOI":"10.1016\/j.ultrasmedbio.2020.06.015","article-title":"Attention-enriched deep learning model for breast tumor segmentation in ultrasound images","volume":"46","author":"Vakanski","year":"2020","journal-title":"Ultrasound Med. Biol"},{"key":"B28","doi-asserted-by":"publisher","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":"Xu","year":"2023","journal-title":"IEEE Access"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1218","DOI":"10.1109\/JBHI.2017.2731873","article-title":"Automated breast ultrasound lesions detection using convolutional neural networks","volume":"22","author":"Yap","year":"2017","journal-title":"IEEE J. Biomed. Health Informat."},{"key":"B30","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1016\/j.neucom.2022.04.021","article-title":"ASS-GAN: asymmetric semi-supervised GAN for breast ultrasound image segmentation","volume":"493","author":"Zhai","year":"2022","journal-title":"Neurocomputing"},{"key":"B31","doi-asserted-by":"publisher","first-page":"105427","DOI":"10.1016\/j.bspc.2023.105427","article-title":"HAU-Net: Hybrid CNN-transformer for breast ultrasound image segmentation","volume":"87","author":"Zhang","year":"2024","journal-title":"Biomed. Signal Proc. Cont."},{"key":"B32","doi-asserted-by":"publisher","first-page":"e13863","DOI":"10.1002\/acm2.13863","article-title":"Fully automatic tumor segmentation of breast ultrasound images with deep learning","volume":"24","author":"Zhang","year":"2023","journal-title":"J. Appl. Clini. Med. Phys"},{"key":"B33","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1177\/0161734614524735","article-title":"Semi-automatic breast ultrasound image segmentation based on mean shift and graph cuts","volume":"36","author":"Zhou","year":"2014","journal-title":"Ultrasonic Imag."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1572433\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:49:51Z","timestamp":1750225791000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1572433\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,18]]},"references-count":33,"alternative-id":["10.3389\/frai.2025.1572433"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1572433","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,18]]},"article-number":"1572433"}}