EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Deep learning model for diagnosis of thyroid nodules with size less than 1 cm: A multicenter, retrospective study

Na Feng, Shanshan Zhao, Kai Wang, Peizhe Chen, Yunpeng Wang, Yuan Gao, Zhengping Wang, Yidan Lu, Chen Chen, Jincao Yao, Zhikai Lei, Dong Xu

European Journal of Radiology Open · 2024-12 · 13 · 100609

DOI: 10.1016/j.ejro.2024.100609 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Radiology Open, 2024-12. Verfasst von Na Feng und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ultrasound, Zhejiang Cancer Hospital, Hangzhou 310022, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To develop a ultrasound images based dual-channel deep learning model to achieve accurate early diagnosis of thyroid nodules less than 1 cm.

Methods

A dual-channel deep learning model called thyroid nodule transformer network (TNT-Net) was proposed. The model has two input channels for transverse and longitudinal ultrasound images of thyroid nodules, respectively. A total of 9649 nodules from 8455 patients across five hospitals were retrospectively collected. The data were divided into a training set (8453 nodules, 7369 patients), an internal test set (565 nodules, 512 patients), and an external test set (631 nodules, 574 patients).

Results

TNT-Net achieved an area under the curve (AUC) of 0.953 (95 % confidence interval (CI): 0.934, 0.969) on the internal test set and 0.941 (95 % CI: 0.921, 0.957) on the external test set, significantly outperforming traditional deep convolutional neural network models and single-channel swin transformer model, whose AUCs ranged from 0.800 (95 % CI: 0.759, 0.837) to 0.856 (95 % CI: 0.819, 0.881). Furthermore, feature heatmap visualization showed that TNT-Net could extract richer and more energetic malignant nodule patterns.

Conclusion

The proposed TNT-Net model significantly improved the recognition capability for thyroid nodules with size less than 1 cm. This model has the potential to reduce overdiagnosis and overtreatment of such nodules, providing essential support for precise management of thyroid nodules while complementing fine-needle aspiration biopsy.

Schlagwörter

Stichwörter der Autor:innen

Deep LearningEarly diagnosisThyroid nodulesTransformerUltrasound image

Autor:innen und Institutionen

  • Department of Ultrasound, Zhejiang Cancer Hospital, Hangzhou 310022, China.
  • Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou 310000, China.
  • Department of Ultrasound, Shaoxing People's Hospital (Zhejiang University Shaoxing Hospital), Shaoxing 312300, China.
  • Department of Ultrasound, The Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang 322100, China.
  • College of Optical Science and Engineering, Zhejiang University, Hangzhou, Zhejiang Province, China.
  • Wenling Medical Big Data and Artificial Intelligence Research Institute, Taizhou 310061, China.

Zitieren

APA

Feng, N., Zhao, S., Wang, K., Chen, P., Wang, Y., Gao, Y., Wang, Z., Lu, Y., Chen, C., Yao, J., Lei, Z., & Xu, D. (2024). Deep learning model for diagnosis of thyroid nodules with size less than 1 cm: A multicenter, retrospective study. European Journal of Radiology Open, 13, 100609. https://doi.org/10.1016/j.ejro.2024.100609

Vancouver

Feng N, Zhao S, Wang K, Chen P, Wang Y, Gao Y, et al. Deep learning model for diagnosis of thyroid nodules with size less than 1 cm: A multicenter, retrospective study. European Journal of Radiology Open. 2024;13:100609. doi:10.1016/j.ejro.2024.100609

BibTeX
@article{Feng2024,
  author = {Feng, Na and Zhao, Shanshan and Wang, Kai and Chen, Peizhe and Wang, Yunpeng and Gao, Yuan and Wang, Zhengping and Lu, Yidan and Chen, Chen and Yao, Jincao and Lei, Zhikai and Xu, Dong},
  title = {Deep learning model for diagnosis of thyroid nodules with size less than 1 cm: A multicenter, retrospective study},
  journal = {European Journal of Radiology Open},
  year = {2024},
  volume = {13},
  pages = {100609},
  doi = {10.1016/j.ejro.2024.100609}
}
Kostenlos starten →