Endocrinol Metab.
2025 Apr;40(2):216-224. 10.3803/EnM.2024.2058.
Deep Learning Technology for Classification of Thyroid Nodules Using Multi-View Ultrasound Images: Potential Benefits and Challenges in Clinical Application
- Affiliations
-
- 1Division of Endocrinology and Metabolism, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Korea
- 2Department of Computer Engineering, Hongik University, Seoul, Korea
- 3Department of Industrial and Data Engineering, Hongik University, Seoul, Korea
- 4Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul, Korea
- 5Department of Radiology, College of Medicine, The Catholic University of Korea, Seoul, Korea
- KMID: 2567176
- DOI: http://doi.org/10.3803/EnM.2024.2058
Abstract
- 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.
- Full Text Links
-
- Actions
-
Cited
- CITED
-
- Close
- Share
-
- Similar articles
-
- Clinical Implementation of Deep Learning in ThoracicRadiology: Potential Applications and Challenges
- Current status of deep learning applications in abdominal ultrasonography
- Elastography of the Thyroid Glands
- Unsupervised speckle noise reduction technique for clinical ultrasound imaging
- Korean Thyroid Imaging Reporting and Data System: Current Status, Challenges, and Future Perspectives
