Ultrasound Video-Based Deep Learning Model for Predicting Axillary Lymph Node Status and Nodal Burden in Breast Cancer
Academic Radiology · 2026-06 · 33 (6) · 2507-2520
DOI: 10.1016/j.acra.2026.02.014 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Academic Radiology, 2026-06. Verfasst von Jiaheng Huang und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, China (J.H., Y.Y., Z.C., Q.L., Y.…. Hauptthemen laut MEDLINE: Breast Neoplasms, Deep Learning, Lymphatic Metastasis, Lymph Nodes. Die Arbeit nennt 44 Literaturangaben. Gefördert von: Medical Science and Technology Project of Zhejiang Province, Science and Technology Department of Zhejiang Province.
Abstract (Originalsprache)
RATIONALE AND OBJECTIVES Accurate preoperative assessment of axillary lymph node (ALN) status and nodal burden is crucial for individualized management of patients with breast cancer. This study aimed to develop and validate a two-stage deep learning (DL) framework that leverages preoperative breast ultrasound videos to predict ALN status and nodal burden. MATERIALS AND METHODS In this multicenter retrospective study, 864 patients with pathologically confirmed breast cancer (July 2019-December 2024) were analyzed and divided into a training set (n=495), an internal test set (n=213), and two external test sets (n=120 and 36). A two-stage framework, based on a Temporal Shift Module (TSM) video model, was proposed to first predict ALN status (negative vs positive) and subsequently classify ALN-positive patients via nodal burden (1-2 vs ≥3 nodes). Model performance was evaluated using AUC, sensitivity, and specificity, along with subgroup analyses and comparisons with other DL and clinical models. RESULTS For ALN status prediction, the TSM-ResNet50 yielded AUCs of 0.851 (95% CI, 0.803-0.894), 0.886, and 0.772 across the internal and two external test sets. Performance was consistent across key subgroups, including tumors >2 cm (0.870) and BI-RADS 4 C lesions (>0.875). For nodal burden prediction, the TSM-ResNet18 achieved AUCs of 0.937, 0.797, and 0.667 for internal and two external test sets, respectively. CONCLUSION A two-stage video-based DL model showed promising performance in predicting ALN status and moderate yet clinically meaningful performance in predicting nodal burden, supporting its potential value for preoperative axillary assessment and individualized management.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, China (J.H., Y.Y., Z.C., Q.L., Y.Z., C.C., X.Z.); Wenzhou Medical University, Wenzhou, Zhejiang 325035,…
- Center of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Taizhou 317502, China (Q.X., Z.J., V.Y.W., Y.Z., D.X.); Wenling Institute of Big Data and Artific…
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, China (J.H., Y.Y., Z.C., Q.L., Y.Z., C.C., X.Z.). Electronic address: yanyuqi17@163.com.
- Wenzhou Medical University, Wenzhou, Zhejiang 325035, China (J.H., Z.J., X.Z., D.X.); Center of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Taizhou 317…
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, China (J.H., Y.Y., Z.C., Q.L., Y.Z., C.C., X.Z.). Electronic address: 3029526753@qq.com.
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, China (J.H., Y.Y., Z.C., Q.L., Y.Z., C.C., X.Z.). Electronic address: 18758816919@163.com.
Förderung
- Medical Science and Technology Project of Zhejiang Province
- Science and Technology Department of Zhejiang Province
Zitieren
APA
Huang, J., Xia, Q., Yan, Y., Jin, Z., Chen, Z., Li, Q., Zheng, Y., Chen, C., Zhu, X., Wu, J., Cai, J., Wang, V. Y., Zhang, Y., & Xu, D. (2026). Ultrasound Video-Based Deep Learning Model for Predicting Axillary Lymph Node Status and Nodal Burden in Breast Cancer. Academic Radiology, 33(6), 2507-2520. https://doi.org/10.1016/j.acra.2026.02.014
Vancouver
Huang J, Xia Q, Yan Y, Jin Z, Chen Z, Li Q, et al. Ultrasound Video-Based Deep Learning Model for Predicting Axillary Lymph Node Status and Nodal Burden in Breast Cancer. Academic Radiology. 2026;33(6):2507-2520. doi:10.1016/j.acra.2026.02.014
BibTeX
@article{Huang2026,
author = {Huang, Jiaheng and Xia, Qing and Yan, Yuqi and Jin, Zhiyan and Chen, Zhiyuan and Li, Qian and Zheng, Yin and Chen, Chen and Zhu, Xinying and Wu, Jiangfeng and Cai, Jing and Wang, Vicky Yang and Zhang, Yang and Xu, Dong},
title = {Ultrasound Video-Based Deep Learning Model for Predicting Axillary Lymph Node Status and Nodal Burden in Breast Cancer},
journal = {Academic Radiology},
year = {2026},
volume = {33},
number = {6},
pages = {2507--2520},
doi = {10.1016/j.acra.2026.02.014}
}
EUVIMED