{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T20:47:47Z","timestamp":1793998067461,"version":"4.8.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100009367","name":"Mansoura University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100009367","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The thyroid gland is prone to various diseases, including thyroid nodules. Ultrasound is the primary diagnostic tool, but classification accuracy is often limited by radiologist expertise. Integrating Artificial Intelligence, particularly Deep Learning, offers the potential to enhance diagnostic reliability. This study investigates whether transfer-learning Convolutional Neural Networks (CNNs) can reliably classify TNs using a publicly available, biopsy-verified ultrasound dataset of 483 images (197 benign, 286 malignant). Nine pre-trained CNNs (ResNet50, ResNet101, VGG16, VGG19, DenseNet121, EfficientNetB0, InceptionV3, InceptionResNetV2, and Xception) were evaluated with transfer learning, data augmentation, class balancing, and tenfold cross-validation. ResNet50 achieved the best performance (accuracy 96.90%, Area Under the Receiver Operating Characteristic Curve (AUC) 0.97, precision 96.93%, recall 96.90%, F1-score 96.90%), followed by ResNet101 (94.75% accuracy, AUC 0.95) and EfficientNetB0 (93.09% accuracy, AUC 0.94). Other models achieved accuracies between 87\u201390% with AUC values of 0.89\u20130.93. Augmentation and balancing strategies effectively reduced class bias and improved generalization across all models. These findings highlight the superiority of ResNet50 while underscoring the broader potential of CNN-based transfer learning as a reliable decision-support approach for thyroid nodule classification.<\/jats:p>","DOI":"10.1038\/s41598-025-25780-0","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T10:53:23Z","timestamp":1763463203000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Enhancing automatic diagnosis of thyroid nodules from ultrasound scans leveraging deep learning models"],"prefix":"10.1038","volume":"15","author":[{"given":"Aya","family":"Rashed","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T.","family":"Medhat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Elgarayhi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,18]]},"reference":[{"key":"25780_CR1","unstructured":"Cedars Sinai. Thyroid nodules. (n.d.) https:\/\/www.cedars-sinai.org\/health-library\/diseasesandconditions\/t\/thyroidnodules.html#:~:text=Thyroid%20nodules%20are%20detected%20in,but%20are%20usually%20not%20diagnosed"},{"key":"25780_CR2","unstructured":"Yale medicine. Thyroid Nodule. Yale Medicine (n.d.) https:\/\/www.yalemedicine.org\/conditions\/thyroid-nodule"},{"key":"25780_CR3","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1089\/thy.2012.0392","volume":"23","author":"N Li","year":"2013","unstructured":"Li, N., Du, X., Reitzel, L., Xu, L. & Sturgis, E. Impact of enhanced detection on the increase in thyroid cancer incidence in the United States: Review of incidence trends by socioeconomic status within the surveillance, epidemiology, and end results registry, 1980\u20132008. Thyroid 23, 103\u2013110 (2013).","journal-title":"Thyroid"},{"key":"25780_CR4","doi-asserted-by":"publisher","first-page":"1029926","DOI":"10.3389\/fonc.2022.1029926","volume":"12","author":"C Mu","year":"2022","unstructured":"Mu, C. et al. Mapping global epidemiology of thyroid nodules among general population: A systematic review and meta-analysis. Front. Oncol. 12, 1029926 (2022).","journal-title":"Front. Oncol."},{"key":"25780_CR5","doi-asserted-by":"publisher","DOI":"10.7537\/marsnsj14081615","author":"Y Ahmed","year":"2016","unstructured":"Ahmed, Y. et al. Prevalence of thyroid nodule among kafrelsheikh population. Nat. Sci. https:\/\/doi.org\/10.7537\/marsnsj14081615 (2016).","journal-title":"Nat. Sci."},{"issue":"7","key":"25780_CR6","doi-asserted-by":"publisher","first-page":"708","DOI":"10.1089\/thy.2005.15.708","volume":"15","author":"J Lin","year":"2005","unstructured":"Lin, J. et al. Thyroid cancer in the thyroid nodules evaluated by ultrasonography and fine-needle aspiration cytology. Thyroid 15(7), 708\u2013717 (2005).","journal-title":"Thyroid"},{"key":"25780_CR7","doi-asserted-by":"publisher","first-page":"5052435","DOI":"10.1155\/2022\/5052435","volume":"2022","author":"S Anari","year":"2022","unstructured":"Anari, S., Sarshar, N., Mahjoori, N., Dorosti, S. & Rezaie, A. Review of deep learning approaches for thyroid cancer diagnosis. Hindawi, Math. Problems Eng. 2022, 5052435. https:\/\/doi.org\/10.1155\/2022\/5052435 (2022).","journal-title":"Hindawi, Math. Problems Eng."},{"key":"25780_CR8","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2018.0380","author":"B Zhang","year":"2019","unstructured":"Zhang, B. et al. Machine learning-assisted system for thyroid nodule diagnosis. Thyroid https:\/\/doi.org\/10.1089\/thy.2018.0380 (2019).","journal-title":"Thyroid"},{"key":"25780_CR9","doi-asserted-by":"publisher","first-page":"14350","DOI":"10.1038\/s41598-017-14432-7","volume":"7","author":"F Baig","year":"2017","unstructured":"Baig, F. et al. Computer-aided assessment of regional vascularity of thyroid nodules for prediction of malignancy. Sci. Rep. 7, 14350 (2017).","journal-title":"Sci. Rep."},{"key":"25780_CR10","doi-asserted-by":"crossref","unstructured":"Keramidas E, Maroulis D and Iakovidis D. TND: A thyroid nodule detection system for analysis of ultrasound images and videos. J. Med. Syst. (2010)","DOI":"10.1007\/s10916-010-9588-7"},{"issue":"2","key":"25780_CR11","first-page":"34","volume":"17","author":"P Porkar","year":"2025","unstructured":"Porkar, P. et al. Enhancing cancer zone diagnosis in MRI images: A novel SOM neural network approach with block processing in the presence of noise. Iran J. Blood Cancer 17(2), 34\u201345 (2025).","journal-title":"Iran J. Blood Cancer"},{"issue":"4","key":"25780_CR12","doi-asserted-by":"publisher","first-page":"9","DOI":"10.61186\/ijbc.16.4.9","volume":"16","author":"R Tajvidi Asr","year":"2024","unstructured":"Tajvidi Asr, R. et al. Hematology and hematopathology insights powered by machine learning: Shaping the future of blood disorder management. Iran J. Blood Cancer 16(4), 9\u201319 (2024).","journal-title":"Iran J. Blood Cancer"},{"issue":"3","key":"25780_CR13","doi-asserted-by":"publisher","first-page":"653","DOI":"10.21037\/gs.2020.04.03","volume":"9","author":"S Miao","year":"2020","unstructured":"Miao, S. et al. The analysis of differential diagnosis of benign and malignant thyroid nodules based on ultrasound reports. Gland Surg. 9(3), 653\u2013660 (2020).","journal-title":"Gland Surg."},{"issue":"7","key":"25780_CR14","doi-asserted-by":"publisher","first-page":"137","DOI":"10.21037\/atm.2019.04.34","volume":"7","author":"Q Guan","year":"2019","unstructured":"Guan, Q. et al. Deep learning based classification of ultrasound images for thyroid nodules: A large scale of pilot study. Ann. Transl. Med. 7(7), 137 (2019).","journal-title":"Ann. Transl. Med."},{"key":"25780_CR15","doi-asserted-by":"publisher","first-page":"101665","DOI":"10.1016\/j.media.2020.101665","volume":"61","author":"L Wang","year":"2020","unstructured":"Wang, L., Zhang, L., Zhu, M., Qi, X. & Yi, Z. Automatic diagnosis for thyroid nodules in ultrasound images by deep neural networks. Med. Image Anal. 61, 101665 (2020).","journal-title":"Med. Image Anal."},{"key":"25780_CR16","doi-asserted-by":"publisher","first-page":"15245","DOI":"10.1038\/s41598-020-72270-6","volume":"10","author":"J Koh","year":"2020","unstructured":"Koh, J. et al. Diagnosis of thyroid nodules on ultrasonography by a deep convolutional neural network. Sci. Rep. 10, 15245 (2020).","journal-title":"Sci. Rep."},{"key":"25780_CR17","doi-asserted-by":"crossref","unstructured":"Zhu Y et al. A generic deep learning framework to classify thyroid and breast lesions in ultrasound images. Ultrasonics (2020)","DOI":"10.1016\/j.ultras.2020.106300"},{"issue":"9","key":"25780_CR18","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1002\/mp.14301","volume":"47","author":"C Sun","year":"2020","unstructured":"Sun, C. et al. Evaluation of a deep learning-based computer-aided diagnosis system for distinguishing benign from malignant thyroid nodules in ultrasound images. Med. Phys. 47(9), 3952\u20133960 (2020).","journal-title":"Med. Phys."},{"issue":"12","key":"25780_CR19","doi-asserted-by":"publisher","first-page":"6355","DOI":"10.1002\/mp.14543","volume":"47","author":"Z Bai","year":"2020","unstructured":"Bai, Z. et al. Thyroid nodules risk stratification through deep learning based on ultrasound images. Med. Phys. 47(12), 6355\u20136365 (2020).","journal-title":"Med. Phys."},{"issue":"2","key":"25780_CR20","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1016\/j.bbe.2021.02.008","volume":"41","author":"Y Sharifi","year":"2023","unstructured":"Sharifi, Y. et al. Deep learning on ultrasound images of thyroid nodules. Biocybern. Biomed. Eng. 41(2), 636\u2013655 (2023).","journal-title":"Biocybern. Biomed. Eng."},{"key":"25780_CR21","doi-asserted-by":"publisher","first-page":"575166","DOI":"10.3389\/fonc.2021.575166","volume":"11","author":"G Wu","year":"2021","unstructured":"Wu, G. et al. Deep learning based on ACR TI-RADS can improve the differential diagnosis of thyroid nodules. Front. Oncol. 11, 575166 (2021).","journal-title":"Front. Oncol."},{"key":"#cr-split#-25780_CR22.1","doi-asserted-by":"crossref","unstructured":"Choudhury A, Mihail R and Chiriac S. Prediction of thyroid malignancy using contextual semantic interpretability from sonograms. In Proc. of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - Volume 2: BIOIMAGING, pages 94-101 ISBN: 978-989-758-631-6","DOI":"10.5220\/0011670900003414"},{"key":"#cr-split#-25780_CR22.2","unstructured":"ISSN: 2184-4305 Copyright c 2023 by SCITEPRESS - Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0) (2023)."},{"key":"25780_CR23","doi-asserted-by":"publisher","first-page":"1360","DOI":"10.1038\/s41598-023-28001-8","volume":"13","author":"J Lee","year":"2023","unstructured":"Lee, J. et al. Investigation of optimal convolutional neural network conditions for thyroid ultrasound image analysis. Sci. Rep. 13, 1360 (2023).","journal-title":"Sci. Rep."},{"key":"25780_CR24","doi-asserted-by":"crossref","unstructured":"Peddakama R. Developing a deep learning ultrasonography model to classify thyroid nodules as benign. medRxiv preprint (2023)","DOI":"10.1101\/2022.12.31.22284087"},{"key":"25780_CR25","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.clinimag.2023.04.010","volume":"99","author":"J Weng","year":"2023","unstructured":"Weng, J. et al. Deep learning for classification of thyroid nodules on ultrasound: Validation on an independent dataset. Clin. Imaging 99, 60\u201366 (2023).","journal-title":"Clin. Imaging"},{"key":"25780_CR26","doi-asserted-by":"publisher","first-page":"1654","DOI":"10.1038\/s41598-023-28932-2","volume":"13","author":"Z Zheng","year":"2023","unstructured":"Zheng, Z. et al. A novel ultrasound image diagnostic method for thyroid nodules. Sci. Rep. 13, 1654 (2023).","journal-title":"Sci. Rep."},{"key":"25780_CR27","doi-asserted-by":"publisher","first-page":"89","DOI":"10.3390\/diagnostics13010089","volume":"13","author":"A Al-Hejri","year":"2023","unstructured":"Al-Hejri, A. et al. Ensemble self-attention transformer encoder for breast cancer diagnosis using full-field digital X-ray breast images. Diagnostics 13, 89. https:\/\/doi.org\/10.3390\/diagnostics13010089 (2023).","journal-title":"Diagnostics"},{"key":"25780_CR28","doi-asserted-by":"publisher","first-page":"19598","DOI":"10.1038\/s41598-023-46865-8","volume":"13","author":"R Sharma","year":"2023","unstructured":"Sharma, R. et al. Comparative performance analysis of binary variants of FOX optimization algorithm with half quadratic ensemble ranking method for thyroid cancer detection. Sci. Rep. 13, 19598. https:\/\/doi.org\/10.1038\/s41598-023-46865-8 (2023).","journal-title":"Sci. Rep."},{"key":"25780_CR29","doi-asserted-by":"publisher","unstructured":"sharma R, Mahanti G, Chakraborty C, Panda G and Rath A. An IoT and Deep Learning-Based Smart Healthcare Framework for Thyroid Cancer Detection. ACM1533\u20135399\/12-ART (2023) https:\/\/doi.org\/10.1145\/3637062","DOI":"10.1145\/3637062"},{"key":"25780_CR30","doi-asserted-by":"publisher","unstructured":"Sharma R, Mahanti G and Panda G. Performance Evaluation and Ranking of Deep Learning Feature Extraction Models for Thyroid Cancer Diagnosis using D-CRITIC TOPSIS. 2023 7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), Kirtipur, Nepal, pp. 702\u2013708, (2023) https:\/\/doi.org\/10.1109\/I-SMAC58438.2023.10290455.","DOI":"10.1109\/I-SMAC58438.2023.10290455"},{"key":"25780_CR31","doi-asserted-by":"publisher","DOI":"10.2174\/1573405620666230405085358","author":"R Sharma","year":"2024","unstructured":"Sharma, R., Mahanti, G., Panda, G. & Singh, A. Thyroid nodules classification using weighted average ensemble and D CRITIC based TOPSIS methods for ultrasound images. Curr. Med. Imaging https:\/\/doi.org\/10.2174\/1573405620666230405085358 (2024).","journal-title":"Curr. Med. Imaging"},{"issue":"1","key":"25780_CR32","doi-asserted-by":"publisher","first-page":"361","DOI":"10.32604\/cmes.2023.031229","volume":"139","author":"L Chen","year":"2024","unstructured":"Chen, L. et al. ThyroidNet: A deep learning network for localization and classification of thyroid nodules. CMES 139(1), 361 (2024).","journal-title":"CMES"},{"key":"25780_CR33","doi-asserted-by":"publisher","unstructured":"Sharma R, Mahanti G, Panda G and Rath A. Evaluation of dimensionality reduction techniques for thyroid cancer diagnosis using ultrasound and histopathological images. Proc. of International Joint Conference on Advances in Computational Intelligence, Springer, (2024) https:\/\/doi.org\/10.1007\/978-981-97-0180-3_43","DOI":"10.1007\/978-981-97-0180-3_43"},{"key":"25780_CR34","doi-asserted-by":"publisher","first-page":"18453","DOI":"10.1038\/s41598-025-96527-0","volume":"15","author":"A Al-Hejri","year":"2025","unstructured":"Al-Hejri, A. et al. A hybrid explainable federated based vision transformer framework for breast cancer prediction via risk factors. Sci. Rep. 15, 18453. https:\/\/doi.org\/10.1038\/s41598-025-96527-0 (2025).","journal-title":"Sci. Rep."},{"key":"25780_CR35","unstructured":"Khachnaoui H, Guetari R and Khlifa N. A review on deep learning in thyroid ultrasound Computer-assisted diagnosis systems. IEEE International Conference on Image Processing, Applications and Systems (IPAS) 978\u20131\u20137281\u20130247\u20134\/18\/$31.00 (2018)."},{"key":"25780_CR36","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/s10462-023-10635-9","volume":"57","author":"D Das","year":"2024","unstructured":"Das, D., Iyengar, M., Majdi, M., Rodriguez, J. & Alsayed, M. Deep learning for thyroid nodule examination: A technical review. Artif. Intell. Rev. 57, 47. https:\/\/doi.org\/10.1007\/s10462-023-10635-9 (2024).","journal-title":"Artif. Intell. Rev."},{"key":"25780_CR37","unstructured":"Geertsma T. UltrasoundCases.info: Cases. Head and Neck. Thyroid gland. Available at: https:\/\/www.ultrasoundcases.info\/cases\/head-and-neck\/thyroid-gland\/"},{"key":"25780_CR38","unstructured":"Oracle. Do you know what deep learning is? Oracle cloud infrastructure (n.d.) https:\/\/www.oracle.com\/data-science\/machine-learning\/what-is-deep-learning\/"},{"key":"25780_CR39","unstructured":"Jeevanandam N. Why does deep learning have the name \"deep\u201d? Ask INDIAai (2022) https:\/\/indiaai.gov.in\/article\/why-does-deep-learning-have-the-name-deep"},{"key":"25780_CR40","unstructured":"Biswal A. Convolutional Neural Network Tutorial. Simplilearn, online certification training course provider, Lesson 13 of 26 (2024) https:\/\/www.simplilearn.com\/tutorials\/deep-learning-tutorial\/convolutional-neural-network"},{"key":"25780_CR41","doi-asserted-by":"publisher","unstructured":"Albawi S, Mohammed T and Al-zawi S. Understanding of a convolutional neural network. ICET, Antalya, Turkey (2017) https:\/\/doi.org\/10.1109\/ICEngTechnol.2017.8308186","DOI":"10.1109\/ICEngTechnol.2017.8308186"},{"issue":"10","key":"25780_CR42","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"S Pan","year":"2009","unstructured":"Pan, S. & Yang, Q. A survey on transfer learning. IEEE Transac. Knowl. Data Eng. 22(10), 1345\u20131359. https:\/\/doi.org\/10.1109\/TKDE.2009.191 (2009).","journal-title":"IEEE Transac. Knowl. Data Eng."},{"key":"25780_CR43","doi-asserted-by":"crossref","unstructured":"Prathibha S , Dahiya D, Robin C , Nishkala C and Swedha S. A Novel Technique for Detecting Various Thyroid Diseases Using Deep Learning. Intelligent Automation & Soft Computing IASC, vol.35, no.1 (2023).","DOI":"10.32604\/iasc.2023.025819"},{"key":"25780_CR44","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1002\/ima.22363","volume":"30","author":"O Moussa","year":"2020","unstructured":"Moussa, O., Khachnaoui, H., Guetari, R. & Khlifa, N. Thyroid nodules classification and diagnosis in ultrasound images using fine-tuning deep convolutional neural network. Int. J. Imaging Syst. Technol. 30, 185\u2013195 (2020).","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"25780_CR45","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S and Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770\u2013778) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"25780_CR46","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1136\/emermed-2017-206735","volume":"34","author":"Z Hoo","year":"2017","unstructured":"Hoo, Z., Candlish, J. & Teare, D. What is an ROC curve?. Emergency Med. J. 34, 357\u2013359 (2017).","journal-title":"Emergency Med. J."},{"key":"25780_CR47","first-page":"52014","volume":"8","author":"Y Wang","year":"2020","unstructured":"Wang, Y. et al. Comparison study of radiomics and deep learning-based methods for thyroid nodules classification using ultrasound images. IEEE Access 8, 52014 (2020).","journal-title":"IEEE Access"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-25780-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-25780-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-25780-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T23:04:29Z","timestamp":1763507069000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-25780-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":48,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["25780"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-25780-0","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,18]]},"assertion":[{"value":"20 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"40364"}}