Scholarlink

Background <p>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.</p> Methods <p>This multicentre study retrospectively included 882&#xa0;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.</p> Results <p>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).</p> Conclusions <p>RKD-R3D when used with US videos becomes a potential supplementary tool to non-invasively assess breast cancer molecular subtypes.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Relation knowledge distillation 3D-ResNet-based deep learning for breast cancer molecular subtypes prediction on ultrasound videos: a multicenter study

  • 期刊论文

  • 发表日期：

    2025年8月26日

查看全文
  • Yingnan Wu,
  • Lei Zhou,
  • Jing Zhao,
  • Yanqing Peng,
  • Xiaoying Li,
  • Yaoting Wang,
  • Sutian Zhu,
  • Chunjie Hou,
  • Pei Du,
  • Lei Ling,
  • Ying Wang,
  • Jiawei Tian,
  • Litao Sun

摘要

Background

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.

Methods

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.

Results

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).

Conclusions

RKD-R3D when used with US videos becomes a potential supplementary tool to non-invasively assess breast cancer molecular subtypes.