Endocrinology and Metabolism

Original Article

Thyroid
Deep Learning Technology for Classification of Thyroid Nodules Using Multi-View Ultrasound Images: Potential Benefits and Challenges in Clinical Application: Jinyoung Kim, Min-Hee Kim, Dong-Jun Lim, Hankyeol Lee, Jae Jun Lee, Hyuk-Sang Kwon, Mee Kyoung Kim, Ki-Ho Song, Tae-Jung Kim, So Lyung Jung, Yong Oh Lee, Ki-Hyun Baek; Endocrinol Metab. 2025;40(2):216-224. Published online January 13, 2025; DOI: https://doi.org/10.3803/EnM.2024.2058

12,154 View
308 Download
15 Web of Science
16 Crossref

Abstract PDF Supplementary Material PubReader ePub

Background
This study aimed to evaluate the applicability of deep learning technology to thyroid ultrasound images for classification of thyroid nodules.
Methods
This retrospective analysis included ultrasound images of patients with thyroid nodules investigated by fine-needle aspiration at the thyroid clinic of a single center from April 2010 to September 2012. Thyroid nodules with cytopathologic results of Bethesda category V (suspicious for malignancy) or VI (malignant) were defined as thyroid cancer. Multiple deep learning algorithms based on convolutional neural networks (CNNs) —ResNet, DenseNet, and EfficientNet—were utilized, and Siamese neural networks facilitated multi-view analysis of paired transverse and longitudinal ultrasound images.
Results
Among 1,048 analyzed thyroid nodules from 943 patients, 306 (29%) were identified as thyroid cancer. In a subgroup analysis of transverse and longitudinal images, longitudinal images showed superior prediction ability. Multi-view modeling, based on paired transverse and longitudinal images, significantly improved the model performance; with an accuracy of 0.82 (95% confidence intervals [CI], 0.80 to 0.86) with ResNet50, 0.83 (95% CI, 0.83 to 0.88) with DenseNet201, and 0.81 (95% CI, 0.79 to 0.84) with EfficientNetv2_ s. Training with high-resolution images obtained using the latest equipment tended to improve model performance in association with increased sensitivity.
Conclusion
CNN algorithms applied to ultrasound images demonstrated substantial accuracy in thyroid nodule classification, indicating their potential as valuable tools for diagnosing thyroid cancer. However, in real-world clinical settings, it is important to aware that model performance may vary depending on the quality of images acquired by different physicians and imaging devices.

Citations

Citations to this article as recorded by

Molecular intelligence and immune reconnaissance in thyroid cancer: a new paradigm for diagnosis, risk stratification, and therapeutic precision
Marcio J. Concepción-Zavaleta, Jenyfer M. Fuentes-Mendoza, Alfredo Cruz-Quintá, Argelia V. Cadena-Guerrero, Ximena Barrón, Luis Concepción-Urteaga, Cristian D. Armas, José Paz-Ibarra, Juan Eduardo Quiroz-Aldave
Expert Review of Anticancer Therapy.2026; 26(5): 585. CrossRef
Deep Learning for Ultrasound Classification to Identify Noninvasive Follicular Thyroid Neoplasms with Papillary–Like Nuclear Features
I-Hung Chien, Yi-Chiung Hsu, Shih-Ping Cheng
Journal of Imaging Informatics in Medicine.2026;[Epub] CrossRef
Knowledge-Prompted Trustworthy Disentangled Learning for Thyroid Ultrasound Segmentation With Limited Annotations
Wenxu Wang, Weizhen Wang, Qianjin Feng, Yu Zhang, Zhenyuan Ning
IEEE Transactions on Image Processing.2026; 35: 983. CrossRef
Integrating Robotic Bilateral Axillo-Breast Approach Thyroidectomy with Molecular Diagnostics and Artificial Intelligence in Thyroid Cancer Care
Qiang Deng, Xiaoping Men, Duo Jin, Yuzhuo Bai
Biomolecules & Therapeutics.2026; 34(1): 45. CrossRef
Improving Non-Invasive Prediction of Thyroid Nodule Malignancy: A Machine Learning-Based Clinical Approach
Maja Reiner, Hanna Drobińska, Michał Miciak, Michał Kisiel, Szymon Biernat, Krzysztof Kaliszewski
Cancer Management and Research.2026; Volume 18: 1. CrossRef
An early evaluation of MedSigLIP in thyroid cytology: a comparative frozen-encoder benchmark against ImageNet-pretrained encoders
Mehmet Poyrazer, Rıdvan Erten
Frontiers in Endocrinology.2026;[Epub] CrossRef
The Role of Cytology, Histology and Molecular Pathology in the Diagnostic Process of Thyroid Nodules
Mathilde Ribeiro, Sule Canberk, Massimo Bongiovanni
Cancers.2026; 18(11): 1814. CrossRef
Classification of Thyroid Nodules from Ultrasound Images Using Deep Learning Methods
Mehmet Emre Özbey, Mehmet Kaplan, Sercan Yalçın, Muhammed Yıldırım
Muş Alparslan Üniversitesi Fen Bilimleri Dergisi.2026; 14(1): 95. CrossRef
Explainable AI for accurate diagnosis of papillary thyroid carcinoma via fine-needle aspiration cytopathology
Ahmet Kilicarslan, Canan Tastimur, Gokhan Gundogdu, Erhan Akin
The Visual Computer.2026;[Epub] CrossRef
Artificial intelligence-assisted risk stratification of thyroid nodules with atypia of undetermined significance
Jinyoung Kim, Jeongmin Lee, Jeonghoon Ha, Ohjoon Kwon, Ki-Hyun Baek, Chang Myeon Song, Hyeon A Lee, Hyemi Kwon, Inyoung Youn, Mi-ri Kwon, Dong-Jun Lim
European Thyroid Journal.2026;[Epub] CrossRef
Artificial intelligence in otorhinolaryngology: a scoping review of diagnostic, surgical, and rehabilitative applications
Wan-Ling Lin, Sheng-Han Chen, Shih-Shuan Fang
The Egyptian Journal of Otolaryngology.2026;[Epub] CrossRef
Diagnostic performance of multimodal ultrasound-based deep learning models in differentiating benign and malignant thyroid nodules
Huajie Ding, Lei Na, Meiling Hao, Wanlou Chen, Zhen Zhang
Frontiers in Oncology.2026;[Epub] CrossRef
Development and clinical application of an ultrasound-based deep learning model for preoperative staging of colorectal cancer
Jing Zhao, Li-Juan Du, Ying Liu, Dan-Dan Zhu, Hui-Qing Wang, Ming-Kui Shen, Ling-Yue Wang, Hai-Yan Wang
World Journal of Gastrointestinal Oncology.2026;[Epub] CrossRef
Automated segmentation of thyroid tissue and carotid artery in ultrasound videos using expert-in-the-loop deep learning: a foundational step toward AI-assisted thyroid diagnostics
Maria Bolomiti, Joel Burman, Keyur Radiya, Olav Inge Håskjold, Karl Øyvind Mikalsen, Vegard Heimly Brun
Updates in Surgery.2026;[Epub] CrossRef
Deep Learning for the Diagnosis and Treatment of Thyroid Cancer: A Review
Rili Gao, Shangqing Mai, Song Wang, Wuqiang Hu, Zhangqi Chang, Guozhi Wu, Haixia Guan
Endocrine Practice.2025; 31(12): 1608. CrossRef
Artificial Intelligence for Thyroid Ultrasound: Clinical Performance, Pitfalls, and Practice Integration
Junseok Kang, Jihyun Ahn, Jeong Hun Hah
Clinical Ultrasound.2025; 10(2): 59. CrossRef

First
Prev
Page of 1
Next
Last

Search