Wu Yingnan, Zhou Lei, Zhao Jing, Peng Yanqing, Li Xiaoying, Wang Yaoting, Zhu Sutian, Hou Chunjie, Du Pei, Ling Lei, Wang Ying, Tian Jiawei, Sun Litao
Cancer Center, Department of Ultrasound Medicine, Zhejiang Provincial People's Hospital (Affiliated People's Hospital), Hangzhou Medical College, Hangzhou, Zhejiang, China.
Key Discipline of Zhejiang Province in Public Health and Preventive Medicine (First Class, Category A), Hangzhou Medical College, Hangzhou, Zhejiang, China.
Br J Cancer. 2025 Aug 26. doi: 10.1038/s41416-025-03146-7.
To develop and test a relation knowledge distillation three-dimensional residual network (RKD-R3D) model for predicting breast cancer molecular subtypes using ultrasound (US) videos to aid clinical personalized management.
This multicentre study retrospectively included 882 breast cancer patients (2375 US videos and 9499 images) between January 2017 and December 2021, which was divided into training, validation, and internal test cohorts. Additionally, 86 patients was collected between May 2023 and November 2023 as the external test cohort. St. Gallen molecular subtypes (luminal A, luminal B, HER2-positive, and triple-negative) were confirmed via postoperative immunohistochemistry. The RKD-R3D based on US videos was developed and validated to predict four-classification molecular subtypes of breast cancer. The predictive performance of RKD-R3D was compared with RKD-R2D, traditional R3D, and preoperative core needle biopsy (CNB). The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, balanced accuracy, precision, recall, and F1-score were analyzed.
RKD-R3D (AUC: 0.88, 0.95) outperformed RKD-R2D (AUC: 0.72, 0.85) and traditional R3D (AUC: 0.65, 0.79) in predicting four-classification breast cancer molecular subtypes in the internal and external test cohorts. RKD-R3D outperformed CNB (Accuracy: 0.87 vs. 0.79) in the external test cohort, achieved good performance in predicting triple negative from non-triple negative breast cancers (AUC: 0.98), and obtained satisfactory prediction performance for both T1 and non-T1 lesions (AUC: 0.96, 0.90).
RKD-R3D when used with US videos becomes a potential supplementary tool to non-invasively assess breast cancer molecular subtypes.
开发并测试一种关系知识蒸馏三维残差网络（RKD-R3D）模型，用于利用超声（US）视频预测乳腺癌分子亚型，以辅助临床个性化管理。
这项多中心研究回顾性纳入了2017年1月至2021年12月期间的882例乳腺癌患者（2375个US视频和9499张图像），并将其分为训练、验证和内部测试队列。此外，收集了2023年5月至2023年11月期间的86例患者作为外部测试队列。通过术后免疫组织化学确定圣加仑分子亚型（腔面A型、腔面B型、HER2阳性型和三阴性）。基于US视频开发并验证了RKD-R3D，以预测乳腺癌的四类分子亚型。将RKD-R3D的预测性能与RKD-R2D、传统R3D和术前粗针穿刺活检（CNB）进行比较。分析了受试者操作特征曲线下面积（AUC）、敏感性、特异性、准确性、平衡准确性、精确性、召回率和F1分数。
在内部和外部测试队列中，RKD-R3D（AUC：0.88，0.95）在预测四类乳腺癌分子亚型方面优于RKD-R2D（AUC：0.72，0.85）和传统R3D（AUC：0.65，0.79）。在外部测试队列中，RKD-R3D的表现优于CNB（准确性：0.87对0.79），在预测非三阴性乳腺癌中的三阴性方面表现良好（AUC：0.98），并且对T1和非T1病变均获得了令人满意的预测性能（AUC：0.96，0.90）。
RKD-R3D与US视频一起使用时，成为一种潜在的非侵入性评估乳腺癌分子亚型的辅助工具。
