{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T06:24:29Z","timestamp":1787293469899,"version":"build-2736575974"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"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. Cell Dev. Biol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Ultrasound-based thyroid nodule segmentation remains challenging because of blurred boundaries, complex echo noise, and subtle morphological differences between benign and malignant lesions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose a benign-malignant-aware segmentation framework based on SegFormer, incorporating adaptive semantic prototype calibration (ASPC) for class-level semantic discrimination and class-conditional boundary refinement (CCBR) for ambiguous contour correction. The model performs three-class segmentation of background, benign, and malignant regions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experiments on the public TN3K dataset and an in-house clinical dataset demonstrate consistent performance under both external transfer and supervised evaluation settings. The proposed method achieved PA, mIoU, mDice, and mPrecision of 0.9449, 0.6427, 0.7517, and 0.8147 on TN3K; 0.7793, 0.5016, 0.6374, and 0.7089 under direct external transfer; and 0.8521, 0.6124, 0.7328, and 0.7996 under supervised in-house evaluation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Ablation studies and Grad-CAM visualization further confirm that ASPC and CCBR improve semantic discrimination, boundary refinement, and model interpretability, supporting the effectiveness of the proposed framework for thyroid nodule segmentation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcell.2026.1879094","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T05:38:12Z","timestamp":1787290692000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Intelligent segmentation of thyroid nodule ultrasound images based on benign\u2013malignant-aware semantic prototype calibration and class-conditional boundary refinement"],"prefix":"10.3389","volume":"14","author":[{"given":"Bin","family":"Luo","sequence":"first","affiliation":[{"name":"Department of General Surgery, Panzhihua Central Hospital","place":["Panzhihua, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runwen","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Vascular Diseases, Panzhihua Central Hospital","place":["Panzhihua, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Panzhihua Central Hospital","place":["Panzhihua, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1176","DOI":"10.1007\/s12559-024-10289-x","article-title":"Cil-net: densely connected context information learning network for boosting thyroid nodule segmentation using ultrasound images","volume":"16","author":"Ali","year":"2024","journal-title":"Cogn. Comput."},{"key":"B2","doi-asserted-by":"publisher","first-page":"107614","DOI":"10.1016\/j.cmpb.2023.107614","article-title":"Bpat-unet: boundary preserving assembled transformer unet for ultrasound thyroid nodule segmentation","volume":"238","author":"Bi","year":"2023","journal-title":"Comput. Methods Programs Biomedicine"},{"key":"B3","doi-asserted-by":"publisher","first-page":"6277","DOI":"10.1109\/access.2024.3525065","article-title":"Transdeep: transformer-Integrated deeplabv3+ for image semantic segmentation","volume":"13","author":"Chai","year":"2025","journal-title":"IEEE Access"},{"key":"B4","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Chen","year":"2018"},{"key":"B5","doi-asserted-by":"publisher","first-page":"106514","DOI":"10.1016\/j.compbiomed.2022.106514","article-title":"Fde-net: frequency-Domain enhancement network using dynamic-scale dilated convolution for thyroid nodule segmentation","volume":"153","author":"Chen","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"B6","doi-asserted-by":"publisher","first-page":"107898","DOI":"10.1016\/j.compbiomed.2023.107898","article-title":"Mlmseg: a multi-view learning model for ultrasound thyroid nodule segmentation","volume":"169","author":"Chen","year":"2024","journal-title":"Comput. Biology Medicine"},{"key":"B7","first-page":"1290","article-title":"Masked-attention mask transformer for universal image segmentation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Cheng","year":"2022"},{"key":"B8","doi-asserted-by":"publisher","first-page":"3925","DOI":"10.1007\/s00371-024-03639-1","article-title":"Clac-net: a composite medical image segmentation framework using self-attention and cross-layer asymmetric connections","volume":"41","author":"Feng","year":"2025","journal-title":"Vis. Comput."},{"key":"B9","first-page":"19077","article-title":"Segman: omni-Scale context modeling with state space models and local attention for semantic segmentation","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"Fu","year":"2025"},{"key":"B10","doi-asserted-by":"publisher","first-page":"106389","DOI":"10.1016\/j.compbiomed.2022.106389","article-title":"Thyroid region prior guided attention for ultrasound segmentation of thyroid nodules","volume":"155","author":"Gong","year":"2023","journal-title":"Comput. Biology Medicine"},{"key":"B11","first-page":"493","volume-title":"PraNet-V2: dual-supervised reverse attention for medical image segmentation. Comput. Vis. Media.","author":"Hu","year":"2026"},{"key":"B12","doi-asserted-by":"publisher","first-page":"102443","DOI":"10.1016\/j.media.2022.102443","article-title":"Thyroid nodule segmentation and classification in ultrasound images through intra-and inter-task consistent learning","volume":"79","author":"Kang","year":"2022","journal-title":"Med. Image Analysis"},{"key":"B13","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.ultrasmedbio.2022.09.017","article-title":"A novel model of thyroid nodule segmentation for ultrasound images","volume":"49","author":"Li","year":"","journal-title":"Ultrasound Med. and Biol."},{"key":"B14","doi-asserted-by":"publisher","first-page":"104636","DOI":"10.1016\/j.bspc.2023.104636","article-title":"Fusing enhanced transformer and large kernel cnn for malignant thyroid nodule segmentation","volume":"83","author":"Li","year":"","journal-title":"Biomed. Signal Process. Control"},{"key":"B15","doi-asserted-by":"publisher","first-page":"128409","DOI":"10.1016\/j.eswa.2025.128409","article-title":"Secnet: spatially enhanced channel-shuffled network with interactive contextual aggregation for medical image segmentation","volume":"290","author":"Li","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"B16","doi-asserted-by":"publisher","first-page":"106472","DOI":"10.1016\/j.bspc.2024.106472","article-title":"Enhanced-transunet for ultrasound segmentation of thyroid nodules","volume":"95","author":"Ozcan","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"B17","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","volume-title":"International Conference on Medical Image Computing and computer-assisted Intervention","author":"Ronneberger","year":"2015"},{"key":"B18","first-page":"7262","article-title":"Segmenter: transformer for semantic segmentation","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Strudel","year":"2021"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1904.04514","article-title":"High-resolution representations for labeling pixels and regions","author":"Sun","year":"2019","journal-title":"arXiv Preprint arXiv:1904"},{"key":"B20","doi-asserted-by":"publisher","first-page":"106600","DOI":"10.1016\/j.cmpb.2021.106600","article-title":"Tnsnet: thyroid nodule segmentation in ultrasound imaging using soft shape supervision","volume":"215","author":"Sun","year":"2022","journal-title":"Comput. Methods Programs Biomedicine"},{"key":"B21","doi-asserted-by":"publisher","first-page":"105917","DOI":"10.1016\/j.bspc.2023.105917","article-title":"Crsanet: class representations self-attention network for the segmentation of thyroid nodules","volume":"91","author":"Sun","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"B22","first-page":"19529","article-title":"Pidnet: a real-time semantic segmentation network inspired by pid controllers","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Xu","year":"2023"},{"key":"B23","doi-asserted-by":"publisher","first-page":"108972","DOI":"10.1016\/j.compbiomed.2024.108972","article-title":"Dac-net: a light-weight u-shaped network based efficient convolution and attention for thyroid nodule segmentation","volume":"180","author":"Yang","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"B24","first-page":"2881","article-title":"Pyramid scene parsing network","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Zhao","year":"2017"}],"container-title":["Frontiers in Cell and Developmental Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2026.1879094\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T05:38:15Z","timestamp":1787290695000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2026.1879094\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,21]]},"references-count":24,"alternative-id":["10.3389\/fcell.2026.1879094"],"URL":"https:\/\/doi.org\/10.3389\/fcell.2026.1879094","relation":{},"ISSN":["2296-634X"],"issn-type":[{"value":"2296-634X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,21]]},"article-number":"1879094"}}