{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:33:29Z","timestamp":1779384809309,"version":"3.53.1"},"reference-count":37,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T00:00:00Z","timestamp":1724284800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Objective: In clinical practice, thyroid nodules are typically visually evaluated by expert physicians using 2D ultrasound images. Based on their assessment, a fine needle aspiration (FNA) may be recommended. However, visually classifying thyroid nodules from ultrasound images may lead to unnecessary fine needle aspirations for patients. The aim of this study is to develop an automatic thyroid ultrasound image classification system to prevent unnecessary FNAs. Methods: An automatic computer-aided artificial intelligence system is proposed for classifying thyroid nodules using a fine-tuned deep learning model based on the DenseNet architecture, which incorporates an attention module. The dataset comprises 591 thyroid nodule images categorized based on the Bethesda score. Thyroid nodules are classified as either requiring FNA or not. The challenges encountered in this task include managing variability in image quality, addressing the presence of artifacts in ultrasound image datasets, tackling class imbalance, and ensuring model interpretability. We employed techniques such as data augmentation, class weighting, and gradient-weighted class activation maps (Grad-CAM) to enhance model performance and provide insights into decision making. Results: Our approach achieved excellent results with an average accuracy of 0.94, F1-score of 0.93, and sensitivity of 0.96. The use of Grad-CAM gives insights on the decision making and then reinforce the reliability of the binary classification for the end-user perspective. Conclusions: We propose a deep learning architecture that effectively classifies thyroid nodules as requiring FNA or not from ultrasound images. Despite challenges related to image variability, class imbalance, and interpretability, our method demonstrated a high classification accuracy with minimal false negatives, showing its potential to reduce unnecessary FNAs in clinical settings.<\/jats:p>","DOI":"10.3390\/jimaging10080203","type":"journal-article","created":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T11:14:41Z","timestamp":1724325281000},"page":"203","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Automatic Classification of Nodules from 2D Ultrasound Images Using Deep Learning Networks"],"prefix":"10.3390","volume":"10","author":[{"given":"Tewele W.","family":"Tareke","sequence":"first","affiliation":[{"name":"ICMUB Laboratory, UMR CNRS 6302, University of Burgundy, 7 Bld Jeanne d\u2019Arc, 21000 Dijon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah","family":"Leclerc","sequence":"additional","affiliation":[{"name":"ICMUB Laboratory, UMR CNRS 6302, University of Burgundy, 7 Bld Jeanne d\u2019Arc, 21000 Dijon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Catherine","family":"Vuillemin","sequence":"additional","affiliation":[{"name":"Medical Imaging Department, Hospital of Bastia, 20600 Bastia, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Perrine","family":"Buffier","sequence":"additional","affiliation":[{"name":"Department of Endocrinology-Diabetology, University Hospital, 21000 Dijon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elodie","family":"Crevisy","sequence":"additional","affiliation":[{"name":"Department of Endocrinology-Diabetology, University Hospital, 21000 Dijon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amandine","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Department of Endocrinology-Diabetology, University Hospital, 21000 Dijon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie-Paule","family":"Monnier Meteau","sequence":"additional","affiliation":[{"name":"Department of Endocrinology-Diabetology, University Hospital, 21000 Dijon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pauline","family":"Legris","sequence":"additional","affiliation":[{"name":"Department of Endocrinology-Diabetology, University Hospital, 21000 Dijon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Serge","family":"Angiolini","sequence":"additional","affiliation":[{"name":"Medical Imaging Department, Hospital of Bastia, 20600 Bastia, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7970-366X","authenticated-orcid":false,"given":"Alain","family":"Lalande","sequence":"additional","affiliation":[{"name":"ICMUB Laboratory, UMR CNRS 6302, University of Burgundy, 7 Bld Jeanne d\u2019Arc, 21000 Dijon, France"},{"name":"Department of Medical Imaging, University Hospital of Dijon, 21000 Dijon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"7","DOI":"10.3322\/caac.21551","article-title":"Cancer statistics, 2019","volume":"69","author":"Siegel","year":"2019","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1159\/000478927","article-title":"European Thyroid Association guidelines for ultrasound malignancy risk stratification of thyroid nodules in adults: The EU-TIRADS","volume":"6","author":"Russ","year":"2017","journal-title":"Eur. Thyroid. J."},{"key":"ref_3","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_4","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1089\/thy.2013.0317","article-title":"Malignancy rate in thyroid nodules classified as Bethesda category III (AUS\/FLUS)","volume":"24","author":"Ho","year":"2014","journal-title":"Thyroid"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1016\/j.ando.2022.11.001","article-title":"SFE-AFCE-SFMN 2022 consensus on the management of thyroid nodules: Synthesis and algorithms","volume":"83","author":"Buffet","year":"2022","journal-title":"Ann. d\u2019Endocrinol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Huh, S., Lee, H.S., Yoon, J., Kim, E.K., Moon, H.J., Yoon, J.H., Park, V.Y., and Kwak, J.Y. (2020). Diagnostic performances and unnecessary US-FNA rates of various TIRADS after application of equal size thresholds. Sci. Rep., 10.","DOI":"10.1038\/s41598-020-67543-z"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1148\/radiol.2019181343","article-title":"Management of thyroid nodules seen on US images: Deep learning may match performance of radiologists","volume":"292","author":"Buda","year":"2019","journal-title":"Radiology"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Mao, Y.J., Zha, L.W., Tam, A.Y.C., Lim, H.J., Cheung, A.K.Y., Zhang, Y.Q., Ni, M., Cheung, J.C.W., and Wong, D.W.C. (2023). Endocrine tumor classification via machine-learning-based elastography: A systematic scoping review. Cancers, 15.","DOI":"10.3390\/cancers15030837"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Peng, W., Liu, C., Xia, S., Shao, D., Chen, Y., Liu, R., and Zhang, Z. (2017). Thyroid nodule recognition in computed tomography using first order statistics. Biomed. Eng. Online, 16.","DOI":"10.1186\/s12938-017-0367-2"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1007\/s10278-017-9997-y","article-title":"Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network","volume":"30","author":"Chi","year":"2017","journal-title":"J. Digit. Imaging"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Alyas, T., Hamid, M., Alissa, K., Faiz, T., Tabassum, N., and Ahmad, A. (2022). Empirical method for thyroid disease classification using a machine learning approach. BioMed Res. Int., 2022.","DOI":"10.1155\/2022\/9809932"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Fu, Z., and Fei, J. (2017, January 13\u201316). An image augmentation method using convolutional network for thyroid nodule classification by transfer learning. Proceedings of the 2017 3rd IEEE International Conference on Computer and Communications (ICCC), Chengdu, China.","DOI":"10.1109\/CompComm.2017.8322853"},{"key":"ref_13","first-page":"30","article-title":"Diagnosis and treatment of patients with thyroid cancer","volume":"8","author":"Nguyen","year":"2015","journal-title":"Am. Health Drug Benefits"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"859","DOI":"10.2214\/AJR.15.15813","article-title":"Classifier model based on machine learning algorithms: Application to differential diagnosis of suspicious thyroid nodules via sonography","volume":"207","author":"Wu","year":"2016","journal-title":"Am. J. Roentgenol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1007\/s10278-020-00362-w","article-title":"Ultrasonographic thyroid nodule classification using a deep convolutional neural network with surgical pathology","volume":"33","author":"Kwon","year":"2020","journal-title":"J. Digit. Imaging"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"5540186","DOI":"10.1155\/2021\/5540186","article-title":"Automatic recognition and classification system of thyroid nodules in CT images based on CNN","volume":"2021","author":"Li","year":"2021","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., 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_18","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1089\/thy.2017.0500","article-title":"The 2017 Bethesda system for reporting thyroid cytopathology","volume":"27","author":"Cibas","year":"2017","journal-title":"Thyroid"},{"key":"ref_19","first-page":"6","article-title":"Use of histogram equalization in image processing for image enhancement","volume":"1","author":"Bagade","year":"2011","journal-title":"Int. J. Softw. Eng. Res. Pract."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Odusami, M., Maskeli\u016bnas, R., Dama\u0161evi\u010dius, R., and Krilavi\u010dius, T. (2021). Analysis of features of alzheimer\u2019s disease: Detection of early stage from functional brain changes in magnetic resonance images using a finetuned ResNet18 network. Diagnostics, 11.","DOI":"10.3390\/diagnostics11061071"},{"key":"ref_21","unstructured":"Tan, M., and Le, Q. (2019, January 10\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA."},{"key":"ref_22","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"287","DOI":"10.2174\/1381612827666211213143357","article-title":"Transfer Learning of the ResNet-18 and DenseNet-121 Model Used to Diagnose Intracranial Hemorrhage in CT Scanning","volume":"28","author":"Zhou","year":"2022","journal-title":"Curr. Pharm. Des."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8\u201314). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"23136","DOI":"10.1109\/TITS.2022.3198047","article-title":"Learning discriminative feature representation for estimating smoke density of smoky vehicle rear","volume":"23","author":"Tao","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"14168","DOI":"10.1109\/JIOT.2023.3339722","article-title":"A Spatial-Channel Feature-Enriched Module Based On Multi-Context Statistics Attention","volume":"11","author":"Tao","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1016\/j.neunet.2023.11.033","article-title":"Hierarchical attention network with progressive feature fusion for facial expression recognition","volume":"170","author":"Tao","year":"2024","journal-title":"Neural Netw."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 13\u201316). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref_31","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 IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_32","unstructured":"Vakili, M., Ghamsari, M., and Rezaei, M. (2020). Performance analysis and comparison of machine and deep learning algorithms for iot data classification. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Goutte, C., and Gaussier, E. (2005, January 21\u201323). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. Proceedings of the European Conference on Information Retrieval, Santiago de Compostela, Spain.","DOI":"10.1007\/978-3-540-31865-1_25"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Guo, T., Dong, J., Li, H., and Gao, Y. (2017, January 10\u201312). Simple convolutional neural network on image classification. Proceedings of the 2017 IEEE 2nd International Conference on Big Data Analysis (ICBDA), Beijing, China.","DOI":"10.1109\/ICBDA.2017.8078730"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Nguyen, D.T., Kang, J.K., Pham, T.D., Batchuluun, G., and Park, K.R. (2020). Ultrasound image-based diagnosis of malignant thyroid nodule using artificial intelligence. Sensors, 20.","DOI":"10.3390\/s20071822"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Koh, J., Lee, E., Han, K., Kim, E.K., Son, E.J., Sohn, Y.M., Seo, M., Kwon, M.r., Yoon, J.H., and Lee, J.H. (2020). Diagnosis of thyroid nodules on ultrasonography by a deep convolutional neural network. Sci. Rep., 10.","DOI":"10.1038\/s41598-020-72270-6"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Lin, Y.J., Chao, T.K., Khalil, M.A., Lee, Y.C., Hong, D.Z., Wu, J.J., and Wang, C.W. (2021). Deep learning fast screening approach on cytological whole slides for thyroid cancer diagnosis. Cancers, 13.","DOI":"10.3390\/cancers13153891"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/10\/8\/203\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:41:40Z","timestamp":1760110900000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/10\/8\/203"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,22]]},"references-count":37,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["jimaging10080203"],"URL":"https:\/\/doi.org\/10.3390\/jimaging10080203","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,22]]}}}