Deep learning based on ultrasound images predicting cervical lymph node metastasis in postoperative patients with differentiated thyroid carcinoma
British Journal of Radiology · 2025
DOI: 10.1093/bjr/tqaf047 ↗Kurz gefasst
Fachartikel in der Zeitschrift British Journal of Radiology, 2025. Verfasst von Fengjing Fan und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Ultrasound, Shandong Medicine and Health Key Laboratory of Abdominal Medical Imaging, The First Affiliated Hospital of Shandong…. Hauptthemen laut MEDLINE: Thyroid Neoplasms, Lymphatic Metastasis, Deep Learning, Lymph Nodes. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 22 Literaturangaben.
Abstract (Originalsprache)
Objectives
To develop a deep learning (DL) model based on ultrasound (US) images of lymph nodes for predicting cervical lymph node metastasis (CLNM) in postoperative patients with differentiated thyroid carcinoma (DTC).
Methods
Retrospective collection of 352 lymph nodes from 330 patients with cytopathology findings between June 2021 and December 2023 at our institution. The database was randomly divided into the training and test cohort at an 8:2 ratio. The DL basic model of longitudinal and cross-sectional of lymph nodes was constructed based on ResNet50 respectively, and the results of the 2 basic models were fused (1:1) to construct a longitudinal + cross-sectional DL model. Univariate and multivariate analyses were used to assess US features and construct a conventional US model. Subsequently, a combined model was constructed by integrating DL and US.
Results
The diagnostic accuracy of the longitudinal + cross-sectional DL model was higher than that of longitudinal or cross-sectional alone. The area under the curve (AUC) of the combined model (US + DL) was 0.855 (95% CI, 0.767-0.942) and the accuracy, sensitivity, and specificity were 0.786 (95% CI, 0.671-0.875), 0.972 (95% CI, 0.855-0.999), and 0.588 (95% CI, 0.407-0.754), respectively. Compared with US and DL models, the integrated discrimination improvement and net reclassification improvement of the combined models are both positive.
Conclusions
This preliminary study shows that the DL model based on US images of lymph nodes has a high diagnostic efficacy for predicting CLNM in postoperative patients with DTC, and the combined model of US+DL is superior to single conventional US and DL for predicting CLNM in this population. Advances in knowledge We innovatively used DL of lymph node US images to predict the status of cervical lymph nodes in postoperative patients with DTC.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medical Ultrasound, Shandong Medicine and Health Key Laboratory of Abdominal Medical Imaging, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, J…
- Ultrasound Medicine, Jining Medical University, Jining, 272000, China.
- School of Computer Science and Technology, Shandong Jianzhu University, Jinan, 250100, China.
ORCID-Profile: Bei Wang
Zitieren
APA
Fan, F., Li, F., Wang, Y., Liu, T., Wang, K., Xi, X., & Wang, B. (2025). Deep learning based on ultrasound images predicting cervical lymph node metastasis in postoperative patients with differentiated thyroid carcinoma. British Journal of Radiology. https://doi.org/10.1093/bjr/tqaf047
Vancouver
Fan F, Li F, Wang Y, Liu T, Wang K, Xi X, et al. Deep learning based on ultrasound images predicting cervical lymph node metastasis in postoperative patients with differentiated thyroid carcinoma. British Journal of Radiology. 2025. doi:10.1093/bjr/tqaf047
BibTeX
@article{Fan2025,
author = {Fan, Fengjing and Li, Fei and Wang, Yixuan and Liu, Tong and Wang, Kesong and Xi, Xiaoming and Wang, Bei},
title = {Deep learning based on ultrasound images predicting cervical lymph node metastasis in postoperative patients with differentiated thyroid carcinoma},
journal = {British Journal of Radiology},
year = {2025},
doi = {10.1093/bjr/tqaf047}
}
EUVIMED