{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T16:54:43Z","timestamp":1790960083646,"version":"4.1.0"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T00:00:00Z","timestamp":1750723200000},"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. Physiol."],"abstract":"<jats:p>Tongue is directly or indirectly connected to many internal organs in Traditional Chinese Medicine (TCM). In computer-aided diagnosis, tongue image segmentation is the first step in tongue diagnosis, and the precision of this segmentation is decisive in determining the accuracy of the tongue diagnosis results. Due to challenges such as insufficient available sample size and complex background, the generalization and robustness of current tongue segmentation algorithms are usually poor, which seriously hinders the practicality of tongue diagnosis. In this article, a GA-TongueNet, namely Tongue Segmentation Network for Stable Generalization Ability, based on self-attention architecture is proposed, which is a tongue segmentation network that can simultaneously have strong generalization ability and accuracy under small samples and diverse background conditions. Firstly, GA-TongueNet is built upon the transformer architecture, embedding the dilated feature pyramid (DiFP) module and the multi-dilated convolution (MDi) module proposed in this article. Secondly, the DiFP module is integrated to comprehend both the overall tongue image structure and intricate local details, while the MDi module is specifically designed to preserve a high feature resolution. Therefore, the network adeptly captures long-range dependencies, extracts high-level semantic content, and retains low-level detail information from tongue images. Moreover, it maintains decent precision and stable generalization capabilities, even when dealing with limited sample sizes. Experimental results show that the accuracy and generalization ability of GA-TongueNet in complex environments are significantly better than various existing semantic segmentation algorithms based on Convolutional Neural Networks (CNN) and Transformer architectures.<\/jats:p>","DOI":"10.3389\/fphys.2025.1617647","type":"journal-article","created":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T05:20:56Z","timestamp":1750742456000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["GA-TongueNet: tongue image segmentation network using innovative DiFP and MDi for stable generalization ability"],"prefix":"10.3389","volume":"16","author":[{"given":"Zhiyu","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yajun","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haihua","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changle","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiran","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1007\/978-3-030-87193-2_36","article-title":"A spatial guided self-supervised clustering network for medical image segmentation","volume-title":"Medical image computing and computer assisted intervention \u2013 miccai 2021","author":"Ahn","year":"2021"},{"key":"B2","article-title":"Tonge image dataset","year":"2014"},{"key":"B3","doi-asserted-by":"publisher","first-page":"102601","DOI":"10.1016\/j.displa.2023.102601","article-title":"Tsrnet: tongue image segmentation with global and local refinement","volume":"81","author":"Cai","year":"2024","journal-title":"Displays"},{"key":"B4","doi-asserted-by":"crossref","first-page":"4520","DOI":"10.1109\/BIBM58861.2023.10385570","article-title":"Tonguesam: an universal tongue segmentation model based on sam with zero-shot","volume-title":"2023 IEEE international conference on bioinformatics and biomedicine (BIBM)","author":"Cao","year":"2023"},{"key":"B5","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","volume-title":"Computer vision \u2013 eccv 2018","author":"Chen","year":"2018"},{"key":"B6","doi-asserted-by":"crossref","first-page":"6443","DOI":"10.1109\/ICASSP39728.2021.9414420","article-title":"Improving ultrasound tongue contour extraction using u-net and shape consistency-based regularizer","volume-title":"Icassp 2021 - 2021 IEEE international conference on acoustics, speech and signal processing (ICASSP)","author":"Feng","year":"2021"},{"key":"B7","doi-asserted-by":"publisher","first-page":"3611","DOI":"10.1109\/TMI.2022.3191398","article-title":"Unsupervised representation learning for tissue segmentation in histopathological images: from global to local contrast","volume":"41","author":"Gao","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B8","first-page":"1386","article-title":"Adaptive active contour model based automatic tongue image segmentation","volume-title":"2016 9th international congress on image and signal processing, BioMedical engineering and informatics","author":"Guo","year":"2016"},{"key":"B9","first-page":"1140","article-title":"Segnext: rethinking convolutional attention design for semantic segmentation","volume-title":"Advances in neural information processing systems","author":"Guo","year":"2022"},{"key":"B10","doi-asserted-by":"crossref","first-page":"15979","DOI":"10.1109\/CVPR52688.2022.01553","article-title":"Masked autoencoders are scalable vision learners","volume-title":"2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","author":"He","year":"2022"},{"key":"B11","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.cmpb.2017.12.029","article-title":"Automated tongue diagnosis on the smartphone and its applications","volume":"174","author":"Hu","year":"2019","journal-title":"Comput. Methods Programs Biomed."},{"key":"B12","doi-asserted-by":"publisher","first-page":"107426","DOI":"10.1016\/j.bspc.2024.107426","article-title":"Attention guided tongue segmentation with geometric knowledge in complex environments","volume":"104","author":"Huang","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"B13","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.neucom.2022.05.023","article-title":"A novel tongue segmentation method based on improved u-net","volume":"500","author":"Huang","year":"2022","journal-title":"Neurocomputing"},{"key":"B14","doi-asserted-by":"publisher","first-page":"112648","DOI":"10.1016\/j.knosys.2024.112648","article-title":"Qa-tsn: quickaccurate tongue segmentation net","volume":"307","author":"Jia","year":"2025","journal-title":"Knowledge-Based Syst."},{"key":"B15","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1016\/j.csbj.2019.09.005","article-title":"Computational identification of vesicular transport proteins from sequences using deep gated recurrent units architecture","volume":"17","author":"Le","year":"2019","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"B16","doi-asserted-by":"publisher","first-page":"104429","DOI":"10.1016\/j.ijmedinf.2021.104429","article-title":"Establishment of noninvasive diabetes risk prediction model based on tongue features and machine learning techniques","volume":"149","author":"Li","year":"2021","journal-title":"Int. J. Med. Inf."},{"key":"B17","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1016\/j.ins.2023.03.079","article-title":"A facial geometry based detection model for face manipulation using cnn-lstm architecture","volume":"633","author":"Liang","year":"2023","journal-title":"Inf. Sci."},{"key":"B18","doi-asserted-by":"crossref","first-page":"936","DOI":"10.1109\/CVPR.2017.106","article-title":"Feature pyramid networks for object detection","volume-title":"2017 IEEE conference on computer vision and pattern recognition (CVPR)","author":"Lin","year":"2017"},{"key":"B19","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1007\/978-3-319-95957-3_51","article-title":"Application of an improved grab cut method in tongue image segmentation","volume-title":"Intelligent computing methodologies","author":"Liu","year":"2018"},{"key":"B20","doi-asserted-by":"publisher","first-page":"8649","DOI":"10.1038\/s41598-022-12743-y","article-title":"Automatic lung segmentation in chest x-ray images using improved u-net","volume":"12","author":"Liu","year":"2022","journal-title":"Sci. Rep."},{"key":"B21","doi-asserted-by":"crossref","first-page":"9992","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","volume-title":"2021 IEEE\/CVF international conference on computer vision (ICCV)","author":"Liu","year":"2021"},{"key":"B22","doi-asserted-by":"publisher","first-page":"102371","DOI":"10.1016\/j.displa.2023.102371","article-title":"Laiu-net: a learning-to-augment incorporated robust u-net for depressed humans\u2019 tongue segmentation","volume":"76","author":"Marhamati","year":"2023","journal-title":"Displays"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1324042","DOI":"10.3389\/fphys.2023.1324042","article-title":"Melanoma skin cancer detection using mask-rcnn with modified gru model","volume":"14","author":"Monica","year":"2024","journal-title":"Front. Physiology"},{"key":"B24","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1109\/TMI.2023.3326188","article-title":"Slim unetr: scale hybrid transformers to efficient 3d medical image segmentation under limited computational resources","volume":"43","author":"Pang","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B25","doi-asserted-by":"publisher","first-page":"104271","DOI":"10.1016\/j.bspc.2022.104271","article-title":"A novel tongue feature extraction method on mobile devices","volume":"80","author":"Qiu","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"B26","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":"Ronneberger","year":"2015"},{"key":"B27","doi-asserted-by":"publisher","first-page":"11689","DOI":"10.1109\/ACCESS.2025.3528658","article-title":"Tongue-litesam: a lightweight model for tongue image segmentation with zero-shot","volume":"13","author":"Tan","year":"2025","journal-title":"IEEE Access"},{"key":"B28","doi-asserted-by":"publisher","first-page":"20552076241242773","DOI":"10.1177\/20552076241242773","article-title":"Rtc_tonguenet: an improved tongue image segmentation model based on deeplabv3","volume":"10","author":"Tang","year":"2024","journal-title":"Digit. Health"},{"key":"B29","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1021\/acs.jproteome.1c00848","article-title":"Improved prediction model of protein lysine crotonylation sites using bidirectional recurrent neural networks","volume":"21","author":"Tng","year":"2022","journal-title":"J. Proteome Res."},{"key":"B30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNB.2024.3462461","article-title":"A novel framework for tongue feature extraction framework based on sublingual vein segmentation","author":"Wan","year":"2024","journal-title":"IEEE Trans. NanoBioscience"},{"key":"B31","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1016\/j.csbj.2020.04.002","article-title":"Artificial intelligence in tongue diagnosis: using deep convolutional neural network for recognizing unhealthy tongue with tooth-mark","volume":"18","author":"Wang","year":"2020","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"B32","first-page":"12077","article-title":"Segformer: simple and efficient design for semantic segmentation with transformers","volume-title":"Advances in neural information processing systems","author":"Xie","year":"2021"},{"key":"B33","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/JBHI.2020.2986376","article-title":"Multi-task joint learning model for segmenting and classifying tongue images using a deep neural network","volume":"24","author":"Xu","year":"2020","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JBHI.2024.3446623","article-title":"Hpa-unet: a hybrid post-processing attention u-net for tongue segmentation","author":"Yao","year":"2024","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B35","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.neucom.2020.04.157","article-title":"Convolutional neural networks for medical image analysis: state-of-the-art, comparisons, improvement and perspectives","volume":"444","author":"Yu","year":"2021","journal-title":"Neurocomputing"},{"key":"B36","doi-asserted-by":"crossref","first-page":"10809","DOI":"10.1109\/CVPR52688.2022.01055","article-title":"Metaformer is actually what you need for vision","volume-title":"2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","author":"Yu","year":"2022"},{"key":"B37","doi-asserted-by":"publisher","first-page":"bbac630","DOI":"10.1093\/bib\/bbac630","article-title":"Prediction of anticancer peptides based on an ensemble model of deep learning and machine learning using ordinal positional encoding","volume":"24","author":"Yuan","year":"2023","journal-title":"Briefings Bioinforma."},{"key":"B38","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.neucom.2019.02.035","article-title":"Multi-task feature selection with sparse regularization to extract common and task-specific features","volume":"340","author":"Zhang","year":"2019","journal-title":"Neurocomputing"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1308987","DOI":"10.3389\/fphys.2023.1308987","article-title":"Pe-net: a parallel framework for 3d inferior mesenteric artery segmentation","volume":"14","author":"Zhang","year":"2023","journal-title":"Front. Physiology"},{"key":"B40","doi-asserted-by":"publisher","first-page":"126383","DOI":"10.1016\/j.eswa.2025.126383","article-title":"Multi-label body constitution recognition via hwmixer-mlp for facial and tongue images","volume":"269","author":"Zhang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"B41","doi-asserted-by":"publisher","first-page":"40569","DOI":"10.1021\/acsomega.2c05881","article-title":"Improved prediction model of protein and peptide toxicity by integrating channel attention into a convolutional neural network and gated recurrent units","volume":"7","author":"Zhao","year":"2022","journal-title":"ACS Omega"},{"key":"B42","doi-asserted-by":"publisher","first-page":"847267","DOI":"10.3389\/fphys.2022.847267","article-title":"Weakly supervised deep learning for tooth-marked tongue recognition","volume":"13","author":"Zhou","year":"2022","journal-title":"Front. Physiology"}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2025.1617647\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T05:21:00Z","timestamp":1750742460000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2025.1617647\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,24]]},"references-count":42,"alternative-id":["10.3389\/fphys.2025.1617647"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2025.1617647","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,24]]},"article-number":"1617647"}}