EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

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

Endocrinology and Metabolism · 30.04.2025 · 40 (2) · 216-224

DOI: 10.3803/enm.2024.2058 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Endocrinology and Metabolism, erschienen am 30.04.2025. Verfasst von Jinyoung Kim und 11 weiteren Autor:innen. Beteiligte Einrichtung: Division of Endocrinology and Metabolism, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Korea. Hauptthemen laut MEDLINE: Thyroid Nodule, Deep Learning, Thyroid Neoplasms. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Research Foundation of Korea, Ministry of Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Thyroid NoduleDeep LearningThyroid NeoplasmsHumansRetrospective StudiesFemaleUltrasonographyMaleMiddle AgedAdultAgedNeural Networks, ComputerBiopsy, Fine-NeedleAlgorithmsFollow-Up Studies

Stichwörter der Autor:innen

Artificial intelligenceDeep learningThyroid neoplasmsThyroid noduleUltrasonography

Autor:innen und Institutionen

  • Division of Endocrinology and Metabolism, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Korea.
  • Department of Computer Engineering, Hongik University, Seoul, Korea.
  • Department of Industrial and Data Engineering, Hongik University, Seoul, Korea.
  • Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul, Korea.
  • Department of Radiology, College of Medicine, The Catholic University of Korea, Seoul, Korea.

Förderung

  • National Research Foundation of Korea
  • Ministry of Education

Zitieren

APA

Kim, J., Kim, M. H., Lim, D. J., Lee, H., Lee, J. J., Kwon, H. S., Kim, M. K., Song, K. H., Kim, T. J., Jung, S. L., Lee, Y. O., & Baek, K. H. (2025). Deep Learning Technology for Classification of Thyroid Nodules Using Multi-View Ultrasound Images: Potential Benefits and Challenges in Clinical Application. Endocrinology and Metabolism, 40(2), 216-224. https://doi.org/10.3803/enm.2024.2058

Vancouver

Kim J, Kim MH, Lim DJ, Lee H, Lee JJ, Kwon HS, et al. Deep Learning Technology for Classification of Thyroid Nodules Using Multi-View Ultrasound Images: Potential Benefits and Challenges in Clinical Application. Endocrinology and Metabolism. 2025;40(2):216-224. doi:10.3803/enm.2024.2058

BibTeX
@article{Kim2025,
  author = {Kim, Jinyoung and Kim, Min-Hee and Lim, Dong-Jun and Lee, Hankyeol and Lee, Jae Jun and Kwon, Hyuk-Sang and Kim, Mee Kyoung and Song, Ki-Ho and Kim, Tae-Jung and Jung, So Lyung and Lee, Yong Oh and Baek, Ki-Hyun},
  title = {Deep Learning Technology for Classification of Thyroid Nodules Using Multi-View Ultrasound Images: Potential Benefits and Challenges in Clinical Application},
  journal = {Endocrinology and Metabolism},
  year = {2025},
  volume = {40},
  number = {2},
  pages = {216--224},
  doi = {10.3803/enm.2024.2058}
}
Kostenlos starten →