{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T23:08:53Z","timestamp":1787008133589,"version":"build-2736575974"},"reference-count":43,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T00:00:00Z","timestamp":1770768000000},"content-version":"vor","delay-in-days":10,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T00:00:00Z","timestamp":1770768000000},"content-version":"tdm","delay-in-days":10,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The incidence of thyroid nodules is relatively high. Doctors typically distinguish the benign and malignant nodules based on ultrasound images, but this method has the risk of misdiagnosis, causing serious consequences for patients. Therefore, improving diagnostic accuracy through Computer Aided Diagnosis (CAD) is crucial. In this study, we propose a novel feature fusion network ResNet-ViT, based on ResNet18 and ViT-l-16, to predict the benign and malignant nature of thyroid nodules. This model adopts the conv layer, layer1 and layer2 of ResNet18 to extract local features, and uses ViT-l-16 without the class token to extract global features. Finally, the convolutional block is used to fuse the local features and global features. We applied ResNet-ViT model to the DDTI and TN5000 dataset and compared it with eight other popular methods, namely, ResNet18, ResNet50, Densenet121, AlexNet, ViT-l-16, Cross-ViT, Hybrid and EfficientViT. The results showed that the predictive performance of ResNet-ViT after 5-fold cross-validation is superior to that of other models. In addition, we utilized the MCB algorithm to fuse image features extracted by ResNet-ViT with clinical features, constructing a ResNet-ViT multimodal model. Experimental results demonstrated that the predictive performance of the ResNet-ViT multimodal model was significantly improved and outperformed eight other models under the same conditions. Our study indicates that the ResNet-ViT multimodal model is capable of effectively capturing both image and clinical features while exhibiting a certain degree of stability. Furthermore, comparative experiments on datasets containing varying extents of surrounding tissue revealed that incorporating some surrounding tissue aids in distinguishing between benign and malignant nodules.<\/jats:p>","DOI":"10.1088\/2057-1976\/ae3e9b","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T22:48:28Z","timestamp":1769640508000},"page":"015074","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A ResNet-ViT classification model for thyroid nodules using ultrasound images and clinical information"],"prefix":"10.1088","volume":"12","author":[{"given":"Le","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7690-807X","authenticated-orcid":true,"given":"Cuicui","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7455-3458","authenticated-orcid":true,"given":"Lijuan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,2,11]]},"reference":[{"key":"bpexae3e9bbib1","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1186\/s40880-019-0368-6","type":"journal-article","article-title":"Current cancer situation in China: good or bad news from the 2018 global cancer statistics","volume":"39","author":"Feng","year":"2019","journal-title":"Cancer Commun (Lond)."},{"key":"bpexae3e9bbib2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1089\/thy.2015.0020","type":"journal-article","article-title":"2015American thyroid association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer: the American thyroid association guidelines task force on thyroid nodules and differentiated thyroid cancer","volume":"26","author":"Haugen","year":"2016","journal-title":"Review.Thyroid."},{"key":"bpexae3e9bbib3","doi-asserted-by":"publisher","DOI":"10.3389\/fcell.2021.619330","type":"journal-article","article-title":"Evaluating DNA methylation, gene expression, somatic mutation, and their combinations in inferring tumor tissue-of-origin","volume":"9","author":"Liu","year":"2021","journal-title":"Front Cell Dev Biol."},{"key":"bpexae3e9bbib4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0176103","type":"journal-article","article-title":"Ultrasound texture analysis: association with lymph node metastasis of papillary thyroid microcarcinoma","volume":"12","author":"Kim","year":"2017","journal-title":"PLoS One"},{"key":"bpexae3e9bbib5","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1002\/jum.14316","type":"journal-article","article-title":"Intraobserver and interobserver variability in ultrasound measurements of thyroid nodules","volume":"37","author":"Lee","year":"2018","journal-title":"J Ultrasound Med."},{"key":"bpexae3e9bbib6","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.cmpb.2009.04.001","type":"journal-article","article-title":"A computer-aided system for malignancy risk assessment of nodules in thyroid US images based on boundary features","volume":"96","author":"Savelonas","year":"2009","journal-title":"Comput. Methods Programs Biomed."},{"key":"bpexae3e9bbib7","doi-asserted-by":"publisher","first-page":"1259","DOI":"10.7863\/jum.2011.30.9.1259","type":"journal-article","article-title":"Quantitative measurement for thyroid cancer characterization based on elastography","volume":"30","author":"Ding","year":"2011","journal-title":"J Ultrasound Med."},{"key":"bpexae3e9bbib8","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/j.cmpb.2011.10.001","type":"journal-article","article-title":"ThyroScreen system: high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform","volume":"107","author":"Acharya","year":"2012","journal-title":"Comput. Methods Programs Biomed."},{"key":"bpexae3e9bbib9","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/978-3-642-31552-7_47","type":"journal-article","article-title":"Survey of computer-aided diagnosis of thyroid nodules in medical ultrasound images","volume":"177","author":"Koundal","year":"2013","journal-title":"Advances in Intelligent Systems and Computing."},{"key":"bpexae3e9bbib10","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/7632308","type":"journal-article","article-title":"A novel neutrosophic method for automatic seed point selection in thyroid nodule images","volume":"2019","author":"Haji","year":"2019","journal-title":"BioMed Res. Int."},{"key":"bpexae3e9bbib11","doi-asserted-by":"publisher","first-page":"2323","DOI":"10.1007\/s00330-023-10269-z","type":"journal-article","article-title":"Deep learning to assist composition classification and thyroid solid nodule diagnosis: a multicenter diagnostic study","volume":"34","author":"Chen","year":"2024","journal-title":"Multicenter Study.Eur Radiol."},{"key":"bpexae3e9bbib12","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1007\/s13246-023-01262-3","type":"journal-article","article-title":"An effective convolutional neural network for classification of benign and malignant breast and thyroid tumors from ultrasound images","volume":"46","author":"Tian","year":"2023","journal-title":"Phys Eng Sci Med."},{"key":"bpexae3e9bbib13","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.575166","type":"journal-article","article-title":"Deep learning based on ACR TI-RADS can improve the differential diagnosis of thyroid nodules","volume":"11","author":"Wu","year":"2021","journal-title":"Front Oncol."},{"key":"bpexae3e9bbib14","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","type":"journal-article","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"bpexae3e9bbib15","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1007\/s10278-017-9997-y","type":"journal-article","article-title":"Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network","volume":"30","author":"Chi","year":"2017","journal-title":"Journal of Digital Imaging."},{"key":"bpexae3e9bbib16","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/j.ultras.2016.09.011","type":"journal-article","article-title":"A pre-trained convolutional neural network based method for thyroid nodule diagnosis","volume":"73","author":"Ma","year":"2017","journal-title":"Ultrasonics"},{"key":"bpexae3e9bbib17","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1002\/ima.22363","type":"journal-article","article-title":"Thyroid nodules classification and diagnosis in ultrasound images using fine-tuning deep convolutional neural network","volume":"30","author":"Moussa","year":"2019","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"bpexae3e9bbib18","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/S1470-2045(18)30762-9","type":"journal-article","article-title":"Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study","volume":"20","author":"Li","year":"2019","journal-title":"Lancet Oncol."},{"key":"bpexae3e9bbib19","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","type":"journal-article","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"bpexae3e9bbib20","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106444","type":"journal-article","article-title":"Classification for thyroid nodule using ViT with contrastive learning in ultrasound images","volume":"152","author":"Sun","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"bpexae3e9bbib21","first-page":"420","type":"conference-proceedings","article-title":"Efficientvit: memory efficient vision transformer with cascaded group attention","volume":"14","author":"Liu","year":"2023"},{"key":"bpexae3e9bbib22","doi-asserted-by":"publisher","first-page":"3248","DOI":"10.1007\/s10278-024-01322-4","type":"journal-article","article-title":"Systematic review of hybrid vision transformer architectures for radiological image analysis","volume":"38","author":"Kim","year":"2025","journal-title":"J Imaging Inform Med."},{"key":"bpexae3e9bbib23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0318670","type":"journal-article","article-title":"Cross-ViT based benign and malignant classification of pulmonary nodules","volume":"20","author":"Zhu","year":"2025","journal-title":"PLoS One"},{"key":"bpexae3e9bbib24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929)","type":"conference-proceedings","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"bpexae3e9bbib25","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2020","type":"preprint"},{"key":"bpexae3e9bbib26","doi-asserted-by":"publisher","first-page":"127","DOI":"10.3322\/caac.21552","type":"journal-article","article-title":"Artificial intelligence in cancer imaging: clinical challenges and applications","volume":"69","author":"Bi","year":"2019","journal-title":"CA Cancer J Clin."},{"key":"bpexae3e9bbib27","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2025.102576","type":"journal-article","article-title":"Deep learning model for malignancy prediction of TI-RADS 4 thyroid nodules with high-risk characteristics using multimodal ultrasound: a multicentre study","volume":"124","author":"Chu","year":"2025","journal-title":"Multicenter Study.Comput Med Imaging Graph."},{"key":"bpexae3e9bbib28","doi-asserted-by":"publisher","first-page":"7052","DOI":"10.1038\/s41467-025-62042-z","type":"journal-article","article-title":"Explainable multimodal deep learning for predicting thyroid cancer lateral lymph node metastasis using ultrasound imaging","volume":"16","author":"Shen","year":"2025","journal-title":"Nat. Commun."},{"key":"bpexae3e9bbib29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1117\/12.2073532","type":"conference-proceedings","article-title":"An open access thyroid ultrasound image database","author":"Pedraza","year":"2015"},{"key":"bpexae3e9bbib30","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.3063","type":"journal-article","article-title":"Advancing thyroid diagnosis: integrating AI-driven CAD framework with numerical data and ultrasound images","volume":"11","author":"Ateeq Almutairi","year":"2025","journal-title":"PeerJ Comput Sci."},{"key":"bpexae3e9bbib31","doi-asserted-by":"publisher","DOI":"10.1007\/s12020-020-02441-y","type":"journal-article","article-title":"Chinese guidelines for ultrasound malignancy risk stratification of thyroid nodules: the C-TIRADS","volume":"70","author":"Zhou","year":"2020","journal-title":"Practice Guideline.Endocrine."},{"key":"bpexae3e9bbib32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0255838","type":"journal-article","article-title":"Optimal distribution-preserving downsampling of large biomedical data sets (opdisDownsampling)","volume":"16","author":"L\u00f6tsch","year":"2021","journal-title":"PLoS One"},{"key":"bpexae3e9bbib33","doi-asserted-by":"publisher","first-page":"186","DOI":"10.4258\/hir.2013.19.3.186","type":"journal-article","article-title":"Stratified sampling design based on data mining","volume":"19","author":"Kim","year":"2013","journal-title":"Healthc Inform Res."},{"key":"bpexae3e9bbib34","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D16-1044","type":"preprint","article-title":"Multimodal compact bilinear pooling for visual question answering and visual grounding","author":"Fukui","year":"2016"},{"key":"bpexae3e9bbib35","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/j.neucom.2019.05.104","type":"book","article-title":"Compact bilinear pooling via kernelized random projection for fine-grained image categorization on low computational power devices","volume":"398","author":"L\u00f3pez-S\u00e1nchez","year":"2020"},{"key":"bpexae3e9bbib36","doi-asserted-by":"publisher","first-page":"6207","DOI":"10.3390\/s21186207","type":"journal-article","article-title":"Human activity classification using multilayer perceptron","volume":"21","author":"Majidzadeh Gorjani","year":"2021","journal-title":"Sensors (Basel)."},{"key":"bpexae3e9bbib37","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021.582928","type":"journal-article","article-title":"A modified AUC for training convolutional neural networks: taking confidence into account","volume":"4","author":"Namdar","year":"2021","journal-title":"Front Artif Intell."},{"key":"bpexae3e9bbib38","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1137\/1.9781611974331.ch41","type":"journal-article","article-title":"Weighted SGD for \u2113p regression with randomized preconditioning","author":"Yang","year":"2016","journal-title":"Proc Annu Acm Siam Symp Discret Algorithms."},{"key":"bpexae3e9bbib39","doi-asserted-by":"publisher","first-page":"535","DOI":"10.3390\/e22050535","type":"journal-article","article-title":"A cross entropy based deep neural network model for road extraction from satellite images","volume":"22","author":"Shan","year":"2020","journal-title":"Entropy."},{"key":"bpexae3e9bbib40","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","type":"conference-proceedings","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"bpexae3e9bbib41","doi-asserted-by":"publisher","first-page":"2261","DOI":"10.1109\/CVPR.2017.243","type":"conference-proceedings","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"bpexae3e9bbib42","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","type":"journal-article","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"bpexae3e9bbib43","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.1038\/s41597-025-05757-4","type":"journal-article","article-title":"TN5000: an ultrasound image dataset for thyroid nodule detection and classification","volume":"12","author":"Zhang","year":"2025","journal-title":"Sci Data."}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3e9b","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3e9b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3e9b","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3e9b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3e9b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3e9b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3e9b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3e9b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T15:06:54Z","timestamp":1770822414000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae3e9b"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,1]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,2,11]]},"published-print":{"date-parts":[[2026,2,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae3e9b","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,1]]},"assertion":[{"value":"A ResNet-ViT classification model for thyroid nodules using ultrasound images and clinical information","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2025-10-20","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-01-28","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-02-11","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}