{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T07:27:16Z","timestamp":1787729236295,"version":"build-2784847793"},"reference-count":29,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2022,2,25]],"date-time":"2022-02-25T00:00:00Z","timestamp":1645747200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["THC"],"published-print":{"date-parts":[[2022,2,25]]},"abstract":"<jats:p>BACKGROUND: Tongue inspection is vital in traditional Chinese medicine. Fissured tongue is an important feature in tongue diagnosis, and primarily corresponds to three Chinese medicine syndromes: syndrome-related hotness, blood deficiency, and insufficiency of the spleen. Diagnosis of the syndrome is significantly affected by the experience of clinicians, and it is difficult for young doctors to perform accurate diagnoses. OBJECTIVE: The syndrome not only depends on the local features based on fissured regions but also on the global features of the whole tongue; therefore, a syndrome diagnosis framework combining the global and local features of a fissured tongue image was developed in the present study to achieve a quantitative and objective diagnosis. METHODS: First, we detected the fissured region of a tongue image using a single-shot multibox detector. Second, we extracted the global and local features from a whole tongue image and a fissured region using TongueNet (developed in-house). Third, we developed a classifier to determine the final syndrome. RESULTS: Based on an experiment involving 721 fissured tongue images, we discovered that TongueNet affords better feature extraction. The accuracy of TongueNet was 4% (p&lt; 0.05) and 3% (p&lt; 0.05) higher than that of InceptionV3 and ResNet18, respectively, for whole tongue images. Meanwhile, at local fissured regions, the accuracy of TongueNet was 3% (p&lt; 0.05) higher than that of InceptionV3 and equal to that of ResNet18. Finally, the fusion features outperformed the global and local features with a 78% accuracy. CONCLUSIONS: Our findings indicate that TongueNet designed with batch normalization and dropout is more suitable for uncomplicated images than InceptionV3 and ResNet18. In addition, compared with the global features, the fusion features supplement the detailed information of the fissures and improve classification accuracy.<\/jats:p>","DOI":"10.3233\/thc-228026","type":"journal-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T13:57:08Z","timestamp":1643723828000},"page":"271-283","source":"Crossref","is-referenced-by-count":12,"title":["Classification of fissured tongue images using deep neural networks"],"prefix":"10.1177","volume":"30","author":[{"given":"Junwei","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuangzhi","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiehui","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","reference":[{"key":"10.3233\/THC-228026_ref1","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1155\/2013\/264742","article-title":"Tongue color analysis for medical application","volume":"2013","author":"Zhang","year":"2013","journal-title":"Evidence-Based Complementray and Alternative Medicine."},{"issue":"8","key":"10.3233\/THC-228026_ref2","doi-asserted-by":"publisher","first-page":"153","DOI":"10.11113\/jt.v78.7129","article-title":"A fast and effective segmentation algorithm with automatic removal of ineffective features on tongue images","volume":"78","author":"Kamarudin","year":"2016","journal-title":"Jurnal Teknologi."},{"key":"10.3233\/THC-228026_ref3","doi-asserted-by":"publisher","first-page":"338","DOI":"10.4028\/www.scientific.net\/AMM.462-463.338","article-title":"A novel approach for color tongue image extraction based on random walk algorithm","volume":"462-463","author":"Zhu","year":"2013","journal-title":"Applied Mechanics & Materials."},{"issue":"8","key":"10.3233\/THC-228026_ref4","doi-asserted-by":"publisher","first-page":"1819","DOI":"10.1007\/s00521-010-0484-3","article-title":"Automatic tongue image segmentation based on gradient vector flow and region merging","volume":"21","author":"Ning","year":"2012","journal-title":"Neural Computing & Applications"},{"key":"10.3233\/THC-228026_ref5","first-page":"100110","article-title":"Tongue\u2019s substance and coating recognition analysis using HSV color threshold in tongue diagnosis","author":"Kamarudin","year":"2016","journal-title":"First International Workshop on Pattern Recognition."},{"key":"10.3233\/THC-228026_ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IPTA.2008.4743772"},{"key":"10.3233\/THC-228026_ref7","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":"Computational & Structural Biotechnology Journal."},{"issue":"2","key":"10.3233\/THC-228026_ref8","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1109\/TCYB.2017.2772289","article-title":"Tooth-marked tongue recognition using multiple instance learning and cnn features","volume":"49","author":"Li","year":"2019","journal-title":"IEEE Transactions on Cybernetics."},{"key":"10.3233\/THC-228026_ref9","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM.2016.7822686"},{"key":"10.3233\/THC-228026_ref10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2016\/3510807","article-title":"The classification of tongue colors with standardized acquisition and icc profile correction in traditional chinese medicine","volume":"2016","author":"Qi","year":"2016","journal-title":"BioMed Research International."},{"key":"10.3233\/THC-228026_ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICMB.2014.21"},{"key":"10.3233\/THC-228026_ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2284070"},{"key":"10.3233\/THC-228026_ref13","doi-asserted-by":"publisher","DOI":"10.1109\/BIBMW.2012.6470316"},{"key":"10.3233\/THC-228026_ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISDA.2006.253889"},{"key":"10.3233\/THC-228026_ref16","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM.2018.8621114"},{"issue":"1","key":"10.3233\/THC-228026_ref17","doi-asserted-by":"publisher","first-page":"420","DOI":"10.5370\/JEET.2017.12.1.420","article-title":"WLDF: effective statistical shape feature for cracked tongue recognition","volume":"12","author":"Li","year":"2017","journal-title":"Journal of Electrical Engineering & Technology."},{"key":"10.3233\/THC-228026_ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"10.3233\/THC-228026_ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.08.040","article-title":"A Dynamic Gradient Boosting Machine Using Genetic Optimizer for Practical Breast Cancer Prognosis","volume":"116","author":"Lu","journal-title":"Expert Systems with Applications"},{"key":"10.3233\/THC-228026_ref20","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv14091556."},{"key":"10.3233\/THC-228026_ref21","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"10.3233\/THC-228026_ref22","unstructured":"Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv150203167."},{"key":"10.3233\/THC-228026_ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"10.3233\/THC-228026_ref24","unstructured":"Nair V, Hinton G. Rectified linear units improve restricted boltzmann machines. in ICML: 2010."},{"key":"10.3233\/THC-228026_ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"10.3233\/THC-228026_ref26","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, Alemi A. Inception-v4, inception-resnet and the impact of residual connections on learning. Proceedings of the AAAI Conference on Artificial Intelligence: 2017. arXiv:1602.07261.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"10.3233\/THC-228026_ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.3233\/THC-228026_ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC.2010.5583303"},{"key":"10.3233\/THC-228026_ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICSGEA.2017.72"},{"issue":"10","key":"10.3233\/THC-228026_ref30","doi-asserted-by":"publisher","first-page":"2381","DOI":"10.3390\/s19102381","article-title":"A lighted deep convolutional neural network based fault diagnosis of rotating machinery","volume":"19","author":"Ma","journal-title":"Sensors"}],"container-title":["Technology and Health Care"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/THC-228026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:57:02Z","timestamp":1777615022000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/THC-228026"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,25]]},"references-count":29,"URL":"https:\/\/doi.org\/10.3233\/thc-228026","relation":{},"ISSN":["0928-7329","1878-7401"],"issn-type":[{"value":"0928-7329","type":"print"},{"value":"1878-7401","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,25]]}}}