文献速递乳腺技术与安全US

基于超声的深度学习列线图预测乳腺癌患者新辅助化疗后腋窝淋巴结状态的多中心队列研究

A Multicenter Cohort Study on Ultrasound-based Deep Learning Nomogram for Predicting Post-Neoadjuvant Chemotherapy Axillary Lymph Node Status in Breast Cancer Patients.
PubMed 文献 · Acad Radiol · 2024-10-15

本研究在两个医疗中心回顾性纳入535例接受新辅助化疗的淋巴结阳性乳腺癌患者,基于超声图像训练五种深度学习模型并构建列线图,ResNet 50表现最佳,列线图在内外部验证队列的AUC分别为0.890和0.870,且能显著提高放射科医生的诊断能力。

要点

  • 基于超声的深度学习列线图预测新辅助化疗后腋窝淋巴结状态,外部验证AUC为0.870。
  • ResNet 50在五种深度学习模型中表现最佳,内外部验证AUC分别为0.837和0.850。
  • 列线图辅助可显著提高放射科医生的诊断能力。

核心结论

  • 基于超声的深度学习列线图在新辅助化疗后腋窝淋巴结状态预测方面具有前景,可辅助放射科医生获得更好的诊断表现。

研究设计与样本

  • 两中心回顾性队列研究,共纳入535例接受新辅助化疗的淋巴结阳性乳腺癌患者;中心1的288例为训练队列、123例为内部验证队列,中心2的124例为外部验证队列;基于新辅助化疗前后超声图像训练ResNet 34、ResNet 50、VGG19、GoogLeNet和DenseNet 121五种深度学习模型并选择最佳模型,结合深度学习预测概率与临床病理特征构建超声深度学习列线图。

诊断标准与关键数值

  • ResNet 50在内部验证队列和外部验证队列的AUC分别为0.837和0.850;超声深度学习列线图在内部验证队列和外部验证队列的AUC分别为0.890和0.870,均优于临床模型和深度学习模型(p均<0.05,但外部验证队列中与深度学习模型比较p=0.19)。

临床应用与阅片要点

  • 列线图可辅助放射科医生提高对新辅助化疗后腋窝淋巴结状态的诊断能力。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVES: The aim of this study was to evaluate the capability of an ultrasound (US)-based deep learning (DL) nomogram for predicting axillary lymph node (ALN) status after neoadjuvant chemotherapy (NAC) in breast cancer patients and its potential to assist radiologists in diagnosis.

METHODS: Two medical centers retrospectively recruited 535 node-positive breast cancer patients who had undergone NAC. Center 1 included 288 patients in the training cohort and 123 patients in the internal validation cohort, while center 2 enrolled 124 patients for the external validation cohort. Five DL models (ResNet 34, ResNet 50, VGG19, GoogLeNet, and DenseNet 121) were trained on pre- and post-NAC US images, and the best model was chosen. A US-based DL nomogram was constructed using DL predictive probabilities and clinicopathological characteristics. Furthermore, the performances of radiologists were compared with and without the assistance of the nomogram.

RESULT: ResNet 50 performed best among all DL models, achieving areas under the curve (AUCs) of 0.837 and 0.850 in the internal and external validation cohorts, respectively. The US-based DL nomogram demonstrated strong predictive ability for ALN status post-NAC, with AUCs of 0.890 and 0.870 in the internal and external validation cohorts, respectively, outperforming both the clinical model and the DL model (p all < 0.05, except p = 0.19 for DL model in external validation cohort). Moreover, the nomogram significantly improved radiologists' diagnostic ability.

CONCLUSION: The US-based DL nomogram is promising for predicting ALN status post-NAC and could assist radiologists for better diagnostic performance.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Sun S, Chen Y, Liu Y, et al. A Multicenter Cohort Study on Ultrasound-based Deep Learning Nomogram for Predicting Post-Neoadjuvant Chemotherapy Axillary Lymph Node Status in Breast Cancer Patients. Acad Radiol. 2024. PMID: 39406583. doi:10.1016/j.acra.2024.09.065

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。