{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:30:24Z","timestamp":1773084624915,"version":"3.50.1"},"reference-count":24,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Broadcasting and Telecommunications Research and Development Fund for Public Interest","award":["A63-1-(2)-018"],"award-info":[{"award-number":["A63-1-(2)-018"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>A thyroid nodule, a common abnormal growth within the thyroid gland, is often identified through ultrasound imaging of the neck. These growths may be solid- or fluid-filled, and their treatment is influenced by factors such as size and location. The Thyroid Imaging Reporting and Data System (TI-RADS) is a classification method that categorizes thyroid nodules into risk levels based on features such as size, echogenicity, margin, shape, and calcification. It guides clinicians in deciding whether a biopsy or other further evaluation is needed. Machine learning (ML) can complement TI-RADS classification, thereby improving the detection of malignant tumors. When combined with expert rules (TI-RADS) and explanations, ML models may uncover elements that TI-RADS misses, especially when TI-RADS training data are scarce. In this paper, we present an automated system for classifying thyroid nodules according to TI-RADS and assessing malignancy effectively. We use ResNet-101 and DenseNet-201 models to classify thyroid nodules according to TI-RADS and malignancy. By analyzing the models\u2019 last layer using the Grad-CAM algorithm, we demonstrate that these models can identify risk areas and detect nodule features relevant to the TI-RADS score. By integrating Grad-CAM results with feature probability calculations, we provide a precise heat map, visualizing specific features within the nodule and potentially assisting doctors in their assessments. Our experiments show that the utilization of ResNet-101 and DenseNet-201 models, in conjunction with Grad-CAM visualization analysis, improves TI-RADS classification accuracy by up to 10%. This enhancement, achieved through iterative analysis and re-training, underscores the potential of machine learning in advancing thyroid nodule diagnosis, offering a promising direction for further exploration and clinical application.<\/jats:p>","DOI":"10.3390\/s23167289","type":"journal-article","created":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T01:49:34Z","timestamp":1692582574000},"page":"7289","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Explainable Automated TI-RADS Evaluation of Thyroid Nodules"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5804-6592","authenticated-orcid":false,"given":"Alisa","family":"Kunapinun","sequence":"first","affiliation":[{"name":"Harbor Branch Oceanographic Institute, Florida Atlantic University, Fort Pierce, FL 34946, USA"},{"name":"Department of Radiology, Faculty of Medicine, Siriraj Hospital, Mahidol University, Bangkok 10400, Thailand"}]},{"given":"Dittapong","family":"Songsaeng","sequence":"additional","affiliation":[{"name":"Department of Radiology, Faculty of Medicine, Siriraj Hospital, Mahidol University, Bangkok 10400, Thailand"}]},{"given":"Sittaya","family":"Buathong","sequence":"additional","affiliation":[{"name":"Department of Radiology, Faculty of Medicine, Siriraj Hospital, Mahidol University, Bangkok 10400, Thailand"}]},{"given":"Matthew N.","family":"Dailey","sequence":"additional","affiliation":[{"name":"Information and Communication Technologies, Asian Institute of Technology, Bangkok 12120, Thailand"}]},{"given":"Chadaporn","family":"Keatmanee","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Ramkhamhaeng University, Bangkok 10240, Thailand"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0192-6249","authenticated-orcid":false,"given":"Mongkol","family":"Ekpanyapong","sequence":"additional","affiliation":[{"name":"Industrial Systems Engineering, Asian Institute of Technology, Bangkok 12120, Thailand"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1016\/j.jacr.2017.01.046","article-title":"ACR Thyroid Imaging, Reporting and Data System (TI-RADS): White paper of the ACR TI-RADS Committee","volume":"14","author":"Tessler","year":"2017","journal-title":"J. Am. Coll. Radiol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1056\/NEJMp1604412","article-title":"World- wide thyroid-cancer epidemic? The increasing impact of overdiagnosis","volume":"375","author":"Vaccarella","year":"2016","journal-title":"N. Engl. J. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"570","DOI":"10.2214\/AJR.20.24608","article-title":"Update on ACR TI-RADS: Successes, Challenges, and Future Directions, From the AJR Special Series on Radiology Reporting and Data Systems","volume":"216","author":"Hoang","year":"2021","journal-title":"Am. J. Roentgenol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"471","DOI":"10.2214\/AJR.20.23123","article-title":"Analysis of malignant thyroid nodules that do not meet ACR TI-RADS criteria for fine needle aspiration","volume":"216","author":"Middleton","year":"2021","journal-title":"Am. J. Roentgenol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"905955","DOI":"10.3389\/fonc.2022.905955","article-title":"Ultrasound Image Classification of Thyroid Nodules Based on Deep Learning","volume":"12","author":"Yang","year":"2022","journal-title":"Front. Oncol."},{"key":"ref_6","unstructured":"Keatmanee, C., Namsena, P., Songsaeng, D., Soodcheun, S., Tanasoontrarat, W., Klabwong, S., Kunapinun, A., Ekpanyapong, M., Dailey, M., and Tarathipayakul, T. (2023). Diagnostic Performance of Artificial Intelligence in Interpreting Thyroid Cancer on Ultrasound Images in the Multi-center Study. Ultrasonic, in press."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Roest, C., Fransen, S.J., Kwee, T.C., and Yakar, D. (2022). Comparative Performance of Deep Learning and Radiologists for the Diagnosis and Localization of Clinically Significant Prostate Cancer at MRI: A Systematic Review. Life, 12.","DOI":"10.3390\/life12101490"},{"key":"ref_8","unstructured":"Chaiyasut, C.A.W. (2017). Ultrasound in Clinical Practice: Ultrasoun Diagnosis, Mahidol University."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1016\/j.otc.2010.01.002","article-title":"Evaluation of a thyroid nodule","volume":"43","author":"Bomeli","year":"2010","journal-title":"Otolaryngol. Clin. N. Am."},{"key":"ref_10","unstructured":"Morgan, M., Jones, J., and Knipe, H. (2023, August 08). Assessment of Thyroid Lesions (Ultrasound). Available online: https:\/\/radiopaedia.org."},{"key":"ref_11","first-page":"E85","article-title":"Clinical Management of Thyroid Disease","volume":"434","author":"Radovick","year":"2010","journal-title":"Mayo Clin. Proc."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1109\/JPROC.2021.3054390","article-title":"A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises","volume":"109","author":"Zhou","year":"2021","journal-title":"Proc. IEEE Inst. Electr. Electron. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1148\/radiol.2017171240","article-title":"Thyroid Imaging Reporting and Data System (TI-RADS): A User\u2019s Guide","volume":"287","author":"Tessler","year":"2018","journal-title":"Radiology"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1016\/j.media.2019.03.009","article-title":"Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis","volume":"54","author":"Pluim","year":"2019","journal-title":"Med. Image Anal."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1153","DOI":"10.1109\/TMI.2016.2553401","article-title":"Guest editorial deep learning in medical imaging: Overview and future promise of an exciting new technique","volume":"35","author":"Greenspan","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"9375","DOI":"10.1109\/ACCESS.2017.2788044","article-title":"Deep learning applications in medical image analysis","volume":"6","author":"Ker","year":"2018","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep residual learning for image recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2015). Rethinking the inception architecture for computer vision. arXiv.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Maaten, L.V.D., and Weinberger, K.Q. (2017, January 21\u201326). Densely Connected Convolutional Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1148\/radiol.2019182128","article-title":"Using Artificial Intelligence to Revise ACR TI-RADS Risk Stratification of Thyroid Nodules: Diagnostic Accuracy and Utility","volume":"292","author":"Buda","year":"2019","journal-title":"Radiology"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Xiao, M., Zhang, L., Shi, W., Liu, J., He, W., and Jiang, Z. (2021, January 23\u201326). A visualization method based on the Grad-CAM for medical image segmentation model. Proceedings of the 2021 International Conference on Electronic Information Engineering and Computer Science (EIECS), Changchun, China.","DOI":"10.1109\/EIECS53707.2021.9587953"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1016\/j.ultrasmedbio.2022.09.010","article-title":"Improving GAN Learning Dynamics for Thyroid Nodule Segmentation. Ultrasound in Medicine and Biology","volume":"49","author":"Kunapinun","year":"2023","journal-title":"Ultrasound Med. Biol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/16\/7289\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:38:12Z","timestamp":1760128692000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/16\/7289"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,21]]},"references-count":24,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2023,8]]}},"alternative-id":["s23167289"],"URL":"https:\/\/doi.org\/10.3390\/s23167289","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,21]]}}}