{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T10:46:18Z","timestamp":1767091578406,"version":"3.48.0"},"reference-count":27,"publisher":"Medical Communications Sp. z.o.o.","issue":"102","license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Ultrason"],"abstract":"<jats:p>Introduction: T\ufeffhe aim of this study was to assess whether integrating selected ultrasound features into a convolutional neural network improves its ability to differentiate benign from malignant thyroid nodules. Material and methods: A total of 242 patients (196 women, 46 men) with thyroid lesions were included in the study. All patients underwent surgical treatment and histopathological analysis. Thyroid ultrasonography was also performed for all participants. Images were recorded in DICOM and AVI formats, and archived in a local database. Thyroid lesions were assessed according to the EU-TIRADS classification. Convolutional neural network models were developed using established architectures, including DenseNet and VGG16, as well as custom-designed models tailored to the dataset. Hybrid models were created by incorporating selected ultrasound features into these architectures as additional inputs. Performance was compared between the baseline convolutional neural network models and their feature-supported hybrid counterparts. Results: Model performance was evaluated using several metrics, including sensitivity and area under the ROC curve. Baseline convolutional neural network models served as the reference, while hybrid variants included structured ultrasound features. The VGG model showed a sensitivity of 0.78, and DenseNet achieved a sensitivity of 0.80 with an AUC of 0.84, demonstrating low variability. Inception models performed similarly, with balanced positive predictive value (PPV) (0.83) and negative predictive value (NPV) (0.74). Custom models also reached AUC values over 0.80. Selected ultrasonography features improved AUC by up to 7%, with additional gains in sensitivity and NPV. Conclusions: Eight baseline convolutional neural network models used to differentiate benign from malignant thyroid nodules were enhanced by incorporating five expert-assessed ultrasound features. This hybrid approach improved classification performance across all models, yielding an average AUC increase of approximately 7%.<\/jats:p>","DOI":"10.15557\/jou.2025.0022","type":"journal-article","created":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T10:40:51Z","timestamp":1767091251000},"source":"Crossref","is-referenced-by-count":0,"title":["Application of artificial intelligence in the ultrasonographic diagnosis of thyroid nodules"],"prefix":"10.15557","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5271-541X","authenticated-orcid":false,"given":"Agnieszka","family":"\u017by\u0142ka","sequence":"first","affiliation":[{"name":"Department of Endocrine Oncology and Nuclear Medicine, Maria Sklodowska-Curie National Research Institute of Oncology, Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4868-3571","authenticated-orcid":false,"given":"Mariusz","family":"Rafa\u0142o","sequence":"additional","affiliation":[{"name":"Institute of Information Systems and Digital Economy, Warsaw School of Economics, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3485-8219","authenticated-orcid":false,"given":"Marek","family":"Dedecjus","sequence":"additional","affiliation":[{"name":"Department of Endocrine Oncology and Nuclear Medicine, Maria Sklodowska-Curie National Research Institute of Oncology, Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1470-4140","authenticated-orcid":false,"given":"Katarzyna Sylwia","family":"Dobruch-Sobczak","sequence":"additional","affiliation":[{"name":"Radiology Department II, Maria Sklodowska-Curie National Research Institute of Oncology, Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"6250","published-online":{"date-parts":[[2025,9,30]]},"reference":[{"key":"ref0","unstructured":"1. Wojciechowska U, Didkowska J, Bara\u0144ska K, Miklewska M, Micha\u0142ek I, Olasek P, Jawo\u0142owska A: Nowotwory z\u0142o\u015bliwe w Polsce w 2022 roku. Krajowy Rejestr Nowotwor\u00f3w. Ministerstwo Zdrowia, Warszawa 2024: 50\u201351."},{"key":"ref1","doi-asserted-by":"crossref","unstructured":"2. Alexander EK, Cibas ES: Diagnosis of thyroid nodules. Lancet Diabetes Endocrinol 2022; 10: 533\u2013539. doi: 10.1016\/S2213-8587(22)00101-2.","DOI":"10.1016\/S2213-8587(22)00101-2"},{"key":"ref2","doi-asserted-by":"crossref","unstructured":"3. Tessler FN, Middleton WD, Grant EG, Hoang JK, Berland LL, Teefey SA et al.: ACR Thyroid Imaging, Reporting and Data System (TI-RADS): white paper of the ACR TI-RADS Committee. J Am Coll Radiol 2017; 14: 587\u2013595. doi: 10.1016\/j.jacr.2017.01.046.","DOI":"10.1016\/j.jacr.2017.01.046"},{"key":"ref3","doi-asserted-by":"crossref","unstructured":"4. Russ G, Bonnema SJ, Erdogan MF, Durante C, Ngu R, Leenhardt L: European Thyroid Association Guidelines for Ultrasound Malignancy Risk Stratification of Thyroid Nodules in Adults: The EU-TIRADS. Eur Thyroid J 2017; 6: 225\u2013237. doi: 10.1159\/000478927.","DOI":"10.1159\/000478927"},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"5. Ha EJ, Na DG, Baek JH: Korean Thyroid Imaging Reporting and Data System: current status, challenges, and future perspectives. Korean J Radiol 2021; 22: 1569\u20131578. doi: 10.3348\/kjr.2021.0106.","DOI":"10.3348\/kjr.2021.0106"},{"key":"ref5","doi-asserted-by":"crossref","unstructured":"6. Friedrich-Rust M, Meyer G, Dauth N, Berner C, Bogdanou D, Herrmann E et al.: Interobserver agreement of Thyroid Imaging Reporting and Data System (TI-RADS) and strain elastography for the assessment of thyroid nodules. PLoS One 2013; 8: e77927. doi: 10.1371\/journal.pone.0077927.","DOI":"10.1371\/journal.pone.0077927"},{"key":"ref6","doi-asserted-by":"crossref","unstructured":"7. Yang L, Li C, Chen Z, He S, Wang Z, Liu J: Diagnostic efficiency among Eu-\/C-\/ACR-TIRADS and S-Detect for thyroid nodules: a systematic review and network meta-analysis. Front Endocrinol (Lausanne) 2023; 14: 1227339. doi: 10.3389\/fendo.2023.1227339.","DOI":"10.3389\/fendo.2023.1227339"},{"key":"ref7","doi-asserted-by":"crossref","unstructured":"8. Toro-Tobon D, Loor-Torres R, Duran M, Fan JW, Singh Ospina N, Wu Y et al.: artificial intelligence in thyroidology: a narrative review of the current applications, associated challenges, and future directions. Thyroid 2023; 33: 903\u2013917. doi: 10.1089\/thy.2023.0132.","DOI":"10.1089\/thy.2023.0132"},{"key":"ref8","doi-asserted-by":"crossref","unstructured":"9. Shen L, Margolies LR, Rothstein JH, Fluder E, McBride R, Sieh W: Deep learning to improve breast cancer detection on screening mammography. Sci Rep 2019; 9: 12495. doi: 10.1038\/s41598-019-48995-4.","DOI":"10.1038\/s41598-019-48995-4"},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"10. Zhou H, Liu B, Liu Y, Huang Q, Yan W: Ultrasonic intelligent diagnosis of papillary thyroid carcinoma based on machine learning. J Healthc Eng 2022; 2022: 6428796. doi: 10.1155\/2022\/6428796. Retraction in: J Healthc Eng 2023; 2023: 9854690. doi: 10.1155\/2023\/9854690.","DOI":"10.1155\/2023\/9854690"},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"11. Brinker TJ, Hekler A, Enk AH, Klode J, Hauschild A, Berking C et al.; Collaborators. Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task. Eur J Cancer 2019; 113: 47\u201354. doi: 10.1016\/j.ejca.2019.04.001.","DOI":"10.1016\/j.ejca.2019.04.001"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"12. Todoroki Y, Iwamoto Y, Lin L, Hu H, Chen YW: Automatic Detection of Focal Liver Lesions in Multi-phase CT Images Using A Multi-channel & Multi-scale CNN. Annu Int Conf IEEE Eng Med Biol Soc 2019; 2019: 872\u2013875. doi: 10.1109\/EMBC.2019.8857292.","DOI":"10.1109\/EMBC.2019.8857292"},{"key":"ref12","doi-asserted-by":"crossref","unstructured":"13. Bradshaw TJ, Huemann Z, Hu J, Rahmim A: A guide to cross-validation for artificial intelligence in medical imaging. Radiol Artif Intell 2023; 5: e220232. doi: 10.1148\/ryai.220232.","DOI":"10.1148\/ryai.220232"},{"key":"ref13","doi-asserted-by":"crossref","unstructured":"14. Lee JH, Kim YG, Ahn Y, Park S, Kong HJ, Choi JY et al.: Investigation of optimal convolutional neural network conditions for thyroid ultrasound image analysis. Sci Rep. 2023;13: 1360. doi: 10.1038\/s41598-023-28001-8.","DOI":"10.1038\/s41598-023-28001-8"},{"key":"ref14","doi-asserted-by":"crossref","unstructured":"15. Li X, Zhang S, Zhang Q, Wei X, Pan Y, Zhao J et al.: Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study. Lancet Oncol 2019; 20: 193\u2013201. doi: 10.1016\/S1470-2045(18)30762-9. Erratum in: Lancet Oncol 2020; 21: e462. doi: 10.1016\/S1470-2045(20)30546-5.","DOI":"10.1016\/S1470-2045(18)30762-9"},{"key":"ref15","doi-asserted-by":"crossref","unstructured":"16. Lai M, Feng B, Yao J, Wang Y, Pan Q, Chen Y et al.: Value of artificial intelligence in improving the accuracy of diagnosing TI-RADS category 4 nodules. Ultrasound Med Biol 2023; 49: 2413\u20132421. doi: 10.1016\/j.ultrasmedbio.2023.08.008.","DOI":"10.1016\/j.ultrasmedbio.2023.08.008"},{"key":"ref16","doi-asserted-by":"crossref","unstructured":"17. Peng S, Liu Y, Lv W, Liu L, Zhou Q, Yang H et al.: Deep learning-based artificial intelligence model to assist thyroid nodule diagnosis and management: a multicentre diagnostic study. Lancet Digit Health 2021; 3: e250\u2013e259. doi: 10.1016\/S2589-7500(21)00041-8. Erratum in: Lancet Digit Health 2021; 3: e413. doi: 10.1016\/S2589-7500(21)00110-2.","DOI":"10.1016\/S2589-7500(21)00110-2"},{"key":"ref17","doi-asserted-by":"crossref","unstructured":"18. Namsena P, Songsaeng D, Keatmanee C, Klabwong S, Kunapinun A, Soodchuen S et al.: Diagnostic performance of artificial intelligence in interpreting thyroid nodules on ultrasound images: a multicenter retrospective study. Quant Imaging Med Surg 2024; 14: 3676\u20133694. doi: 10.21037\/qims-23-1650.","DOI":"10.21037\/qims-23-1650"},{"key":"ref18","doi-asserted-by":"crossref","unstructured":"19. Tong WJ, Wu SH, Cheng MQ, Huang H, Liang JY, Li CQ et al.: Integration of artificial intelligence decision aids to reduce workload and enhance efficiency in thyroid nodule management. JAMA Netw Open 2023; 6: e2313674. doi: 10.1001\/jamanetworkopen.2023.13674.","DOI":"10.1001\/jamanetworkopen.2023.13674"},{"key":"ref19","doi-asserted-by":"crossref","unstructured":"20. Zhou T, Xu L, Shi J, Zhang Y, Lin X, Wang Y et al.: US of thyroid nodules: can AIassisted diagnostic system compete with fine needle aspiration? Eur Radiol 2024; 34: 1324\u20131333. doi: 10.1007\/s00330-023-10132-1.","DOI":"10.1007\/s00330-023-10132-1"},{"key":"ref20","doi-asserted-by":"crossref","unstructured":"21. Wu GG, Lv WZ, Yin R, Xu JW, Yan YJ, Chen RX et al.: Deep learning based on ACR TI-RADS can improve the differential diagnosis of thyroid nodules. Front Oncol 2021; 11: 575166. doi: 10.3389\/fonc.2021.575166.","DOI":"10.3389\/fonc.2021.575166"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"22. Wang J, Jiang J, Zhang D, Zhang YZ, Guo L, Jiang Y et al.: An integrated AI model to improve diagnostic accuracy of ultrasound and output known risk features in suspicious thyroid nodules. Eur Radiol 2022; 32: 2120\u20132129. doi: 10.1007\/s00330-021-08298-7.","DOI":"10.1007\/s00330-021-08298-7"},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"23. Li X, Peng C, Liu Y, Hu Y, Yang L, Yu Y et al.: Modified American College of Radiology Thyroid Imaging Reporting and Data System and Modified Artificial Intelligence Thyroid Imaging Reporting and Data System for Thyroid Nodules: a multicenter retrospective study. Thyroid 2024; 34: 88\u2013100. doi: 0.1089\/thy.2023.0429.","DOI":"10.1089\/thy.2023.0429"},{"key":"ref23","doi-asserted-by":"crossref","unstructured":"24. Cui Y, Fu C, Si C, Li J, Kang Y, Huang Y, Cui K: Analysis and comparison of the malignant thyroid nodules not recommended for biopsy in ACR TIRADS and AI TIRADS with a large sample of surgical series. J Ultrasound Med 2023; 42: 1225\u20131233. doi: 10.1002\/jum.16132.","DOI":"10.1002\/jum.16132"},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"25. Li J, Guo Q, Tan X: Multi-modal feature integration for thyroid nodule prediction: Combining clinical data with ultrasound-based deep features. J Radiat Res Appl Sci 2025; 18: 101217. doi:10.1016\/j.jrras.2024.101217.","DOI":"10.1016\/j.jrras.2024.101217"},{"key":"ref25","doi-asserted-by":"crossref","unstructured":"26. Yao S, Shen P, Dai T, Dai F, Wang Y, Zhang W, Lu H: Human understandable thyroid ultrasound imaging AI report system \u2013 A bridge between AI and clinicians. iScience. 2023; 26: 106530. doi: 10.1016\/j.isci.2023.106530.","DOI":"10.1016\/j.isci.2023.106530"},{"key":"ref26","doi-asserted-by":"crossref","unstructured":"27. Gomes Ataide EJ, Ponugoti N, Illanes A, Schenke S, Kreissl M, Friebe M: Thyroid nodule classification for physician decision support using machine learning-evaluated geometric and morphological features. Sensors (Basel) 2020; 20: 6110. doi: 10.3390\/s2021611.","DOI":"10.3390\/s20216110"}],"container-title":["Journal of Ultrasonography"],"original-title":[],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T10:40:59Z","timestamp":1767091259000},"score":1,"resource":{"primary":{"URL":"https:\/\/jultrason.pl\/index.php\/issues\/volume-25-no-102\/application-of-artificial-intelligence-in-the-ultrasonographic-diagnosis-of-thyroid-nodules"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":27,"journal-issue":{"issue":"102","published-online":{"date-parts":[[2025,9,30]]}},"URL":"https:\/\/doi.org\/10.15557\/jou.2025.0022","relation":{},"ISSN":["2084-8404","2451-070X"],"issn-type":[{"value":"2084-8404","type":"print"},{"value":"2451-070X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,30]]}}}