{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T05:07:48Z","timestamp":1784092068568,"version":"3.55.0"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Thyroid nodules refer to discrete lesions within the thyroid gland, caused by abnormal proliferation of thyroid cells and local growth. Thyroid ultrasound imaging is a non-invasive, widely used technique primarily employed to assess the benign or malignant nature of nodules, the extent of invasion into adjacent tissues, and lymph node metastasis. Early ultrasound diagnosis can help reduce the incidence of thyroid cancer. However, the diagnostic results from ultrasound examinations are often subjective, labor-intensive, and highly dependent on the clinical experience of the ultrasound physician.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a C-TIRADS-guided computer-aided diagnostic framework consisting of a nodule detection module, a C-TIRADS feature classification module, and a rule-based risk scoring module. Thyroid nodules were first localized using the detection network and then classified according to key C-TIRADS ultrasound features, including composition, echogenicity, margin, shape, and echogenic foci. The predicted feature scores were aggregated to determine the benign or malignant risk category. The model was trained using task-specific datasets and clinically validated on an independent cohort of 303 thyroid nodules\/images from 284 patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In the independent clinical validation set, the AI model achieved an overall accuracy of 0.862 [95% CI, 0.822\u20130.901]. Physician accuracy was 0.705 [95% CI, 0.657\u20130.756] without AI assistance and increased to 0.845 [95% CI, 0.802\u20130.884] with AI assistance. These findings suggest the potential value of the proposed system as a C-TIRADS-guided decision-support tool.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed C-TIRADS-guided framework can localize thyroid nodules, classify guideline-defined ultrasound features, and provide standardized malignancy risk stratification. The model may assist physicians in thyroid ultrasound interpretation; however, larger blinded multicenter studies are required before routine clinical application.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1877809","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T04:39:58Z","timestamp":1784090398000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and clinical validation of an artificial intelligence based model for thyroid nodule malignancy risk assessment using C-TIRADS guidelines"],"prefix":"10.3389","volume":"13","author":[{"given":"Rongzhou","family":"Ye","sequence":"first","affiliation":[{"name":"Department of General Practice, Quanzhou First Hospital Affiliated to Fujian Medical University","place":["Quanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Engineering, Huaqiao University","place":["Quanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuming","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Medicine, Quanzhou First Hospital Affiliated to Fujian Medical University","place":["Quanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kangjian","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Medicine, Zhangzhou Affiliated Hospital of Fujian Medical University","place":["Zhangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"e250","DOI":"10.1016\/S2589-7500(21)00041-8","article-title":"Deep learning-based artificial intelligence model to assist thyroid nodule diagnosis and management: a multicentre diagnostic study","volume":"3","author":"Peng","year":"2021","journal-title":"Lancet Digit Health"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1016\/S2213-8587(22)00101-2","article-title":"Diagnosis of thyroid nodules","volume":"10","author":"Alexander","year":"2022","journal-title":"Lancet Diabetes Endocrinol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"2869","DOI":"10.1210\/clinem\/dgaa322","article-title":"Contemporary thyroid nodule evaluation and manage- ment","volume":"105","author":"Grani","year":"2020","journal-title":"J Clin Endocrinol Metab"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1531","DOI":"10.1016\/S0140-6736(23)00020-X","article-title":"Thyroid cancer","volume":"401","author":"Chen","year":"2023","journal-title":"Lancet"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.7507\/1001-5515.202302049","article-title":"Review on ultrasonographic diagnosis of thyroid diseases based on deep learning","volume":"40","author":"Qi","year":"2023","journal-title":"Sheng Wu Yi Xue Gong Cheng Xue Za Zhi"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"729","DOI":"10.3390\/healthcare10040729","article-title":"Busis: a benchmark for breast ultrasound image segmentation","volume":"10","author":"Zhang","year":"2022","journal-title":"Healthcare"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1016\/j.chest.2020.06.068","article-title":"Feasibility of a 5G-based robot-assisted remote ultrasound system for car- diopulmonary assessment of patients with coronavirus disease 2019","volume":"159","author":"Ye","year":"2019","journal-title":"Chest"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"22662","DOI":"10.1109\/ACCESS.2024.3359367","article-title":"Automatic thyroid nodule detection in ultrasound imaging with improved yolov 5 neural network","volume":"12","author":"Yang","year":"2024","journal-title":"IEEE Access"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"2611","DOI":"10.1109\/TUFFC.2022.3190012","article-title":"Multi- attribute attention network for interpretable diagnosis of thyroid nodules in ultrasound images","volume":"69","author":"Manh","year":"2022","journal-title":"IEEE Trans Ultrason Ferroelectr Freq Control"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1007\/s12020-020-02441-y","article-title":"Chinese guidelines for ultrasound malignancy risk stratification of thyroid nodules: the C-TIRADS","volume":"70","author":"Zhou","year":"2020","journal-title":"Endocr Res"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"109872","DOI":"10.1016\/j.compbiomed.2025.109872","article-title":"Comparative analysis for accurate multi-classification of brain tumor based on significant deep learning models","volume":"188","author":"Elhadidy","year":"2025","journal-title":"Comput Biol Med"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/s11227-025-08145-2","article-title":"Early predictive modeling of uterine adhesions severity: a comparative study of ANN and ANFIS techniques","volume":"82","author":"Elgohr","year":"2026","journal-title":"J Supercomput"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"32924","DOI":"10.1038\/s41598-025-12216-y","article-title":"Attention-enhanced CNNs and transformers for accurate monkeypox and skin disease detection","volume":"15","author":"Mousa","year":"2025","journal-title":"Sci Rep"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1215","DOI":"10.1109\/JBHI.2018.2852718","article-title":"Multitask cascade convolution neural networks for automatic thyroid nodule detection and recognition","volume":"23","author":"Song","year":"2018","journal-title":"IEEE J Biomed Health Inform"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"104064","DOI":"10.1016\/j.engappai.2020.104064","article-title":"Integrate domain knowledge in training multi-task cascade deep learning model for benign\u2013malignant thyroid nodule classification on ultrasound images","volume":"98","author":"Yang","year":"2021","journal-title":"Eng Appl Artif Intell"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"740","DOI":"10.3390\/diagnostics13040740","article-title":"Differentiation of benign and malignant thyroid nodules with anfis by using genetic algorithm and proposing a novel CAD-based risk stratification system of thyroid nodules","volume":"13","author":"Ozturk","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"e848","DOI":"10.1016\/j.ijrobp.2020.07.401","article-title":"Classification of TI-RADS class-4 thyroid nodules via ultrasound-based radiomics and multi-kernel learning","volume":"108","author":"Lu","year":"2020","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"e918452","DOI":"10.12659\/MSM.918452","article-title":"Ultrasound computer-aided diagnosis (CAD) based on the thyroid imaging reporting and data system (TI-RADS) to distinguish benign from malignant thyroid nodules and the diagnostic performance of radiologists with different diagnostic experience","volume":"26","author":"Jin","year":"2020","journal-title":"Med Sci Monit"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"10934","DOI":"10.48550\/arXiv.2004.10934","article-title":"Yolov 4: optimal speed and accuracy of object detection","volume":"2020","author":"Bochkovskiy","year":"2020","journal-title":"arXiv"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"05941","DOI":"10.48550\/arXiv.1710.05941","article-title":"Searching for activa- tion functions","volume":"2017","author":"Ramachandran","year":"2017","journal-title":"arXiv"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"02907","DOI":"10.48550\/arXiv.2103.02907","article-title":"Coordinate attention for efficient mobile network design (2021)","volume":"2021","author":"Hou","year":"2021","journal-title":"arXiv"},{"key":"ref22","author":"He","year":"2016"},{"key":"ref23","author":"Liu","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1790","DOI":"10.3390\/s22051790","article-title":"Detection of farmland obstacles based on an improved yolov 5s algorithm by using ciou and anchor box scale clustering","volume":"22","author":"Xue","year":"2022","journal-title":"Sensors (Basel)"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"938961","DOI":"10.3389\/fendo.2022.938961","article-title":"Diagnostic performance of c- tirads in malignancy risk stratification of thyroid nodules: a systematic review and meta-analysis","volume":"13","author":"Hu","year":"2022","journal-title":"Front Endocrinol (Lausanne)"},{"key":"ref26","author":"Liu","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J Big Data"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"4747","DOI":"10.48550\/arXiv.1609.04747","article-title":"An overview of gradient descent optimization algorithms","volume":"2016","author":"Ruder","year":"2016","journal-title":"arXiv"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1469","DOI":"10.1001\/jama.1983.03340110071044","article-title":"Clinical epidemiology: the essentials","volume":"250","author":"Levy","year":"1983","journal-title":"JAMA"},{"key":"ref30","author":"Ren","year":"2015"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"9972","DOI":"10.48550\/arXiv.2305.09972","article-title":"Real- time flying object detection with yolov 8","volume":"2023","author":"Reis","year":"2023","journal-title":"arXiv"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1109\/CVPR52729.2023.00721","article-title":"Yolov 7: trainable bag-of-freebies sets new state-of-the-art for real-time object de- tectors","volume":"2022","author":"Wang","year":"2022","journal-title":"arXiv"},{"key":"ref33","first-page":"2976","article-title":"Yolov 6: A single-stage object detection framework for industrial applications","author":"Li","year":"2022"},{"key":"ref34","author":"Redmon","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"04861","DOI":"10.48550\/arXiv.1704.04861","article-title":"Mobilenets: efficient convolutional neural networks for mobile vision applications","volume":"2017","author":"Howard","year":"2017","journal-title":"arXiv"},{"key":"ref36","author":"Zhang","year":"2018"},{"key":"ref37","author":"Tan","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"11929","DOI":"10.48550\/arXiv.2010.11929","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","volume":"2020","author":"Dosovitskiy","year":"2020","journal-title":"arXiv"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1877809\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T04:40:04Z","timestamp":1784090404000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1877809\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":38,"alternative-id":["10.3389\/fmed.2026.1877809"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1877809","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"article-number":"1877809"}}