文献速递乳腺技术与安全US

基于超声的深度学习构建乳腺病灶风险分层系统:一项多中心研究

Ultrasound-based deep learning in the establishment of a breast lesion risk stratification system: a multicenter study.
PubMed 文献 · Eur Radiol · 2022-11-23

该多中心研究前瞻性收集32家医院5012例患者的超声图像,开发深度学习模型同时进行乳腺病灶良恶性二分类和BI-RADS六分类。外部测试集AUC分别为0.980和0.945,读者研究中模型与三位经验丰富放射科医生共识的AUC、敏感度、准确率相似,但特异度更高。结论认为模型性能良好,有望辅助减少BI-RADS 4a病灶的不必要活检。

要点

  • 深度学习模型可同时输出良恶性二分类和BI-RADS 2、3、4a、4b、4c、5六分类。
  • 外部测试集二分类AUC 0.980,六分类AUC 0.945。
  • 读者研究中模型特异度78.71%高于三位放射科医生共识的68.81%。

核心结论

  • 深度学习模型在区分乳腺良恶性病灶方面表现良好,结果与经验丰富的放射科医生相似,提示其临床诊断应用潜力。

研究设计与样本

  • 多中心前瞻性研究,2018年12月至2020年12月从32家医院收集5012例患者的超声图像。
  • 从测试集中随机选取324例患者进行读者研究,由三位经验丰富的放射科医生参与。

诊断标准与关键数值

  • 外部测试集中,深度学习模型二分类(良恶性)的AUC为0.980,六分类(BI-RADS 2、3、4a、4b、4c、5)的AUC为0.945。
  • 读者研究集中,深度学习模型的BI-RADS分类与三位放射科医生共识相比:AUC 0.901 vs. 0.933(p=0.0632),敏感度90.98% vs. 95.90%(p=0.1094),准确率83.33% vs. 79.01%(p=0.0541),特异度78.71% vs. 68.81%(p=0.0012)。

临床应用与阅片要点

  • 模型可同时输出良恶性二分类和BI-RADS六分类,有助于风险分层。
  • 模型特异度高于放射科医生共识,可能有助于减少BI-RADS 4a病灶的不必要活检。
  • 模型与放射科医生分类一致性可接受,可作为辅助诊断工具。

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

OBJECTIVES: To establish a breast lesion risk stratification system using ultrasound images to predict breast malignancy and assess Breast Imaging Reporting and Data System (BI-RADS) categories simultaneously.

METHODS: This multicenter study prospectively collected a dataset of ultrasound images for 5012 patients at thirty-two hospitals from December 2018 to December 2020. A deep learning (DL) model was developed to conduct binary categorization (benign and malignant) and BI-RADS categories (2, 3, 4a, 4b, 4c, and 5) simultaneously. The training set of 4212 patients and the internal test set of 416 patients were from thirty hospitals. The remaining two hospitals with 384 patients were used as an external test set. Three experienced radiologists performed a reader study on 324 patients randomly selected from the test sets. We compared the performance of the DL model with that of three radiologists and the consensus of the three radiologists.

RESULTS: In the external test set, the DL model achieved areas under the receiver operating characteristic curve (AUCs) of 0.980 and 0.945 for the binary categorization and six-way categorizations, respectively. In the reader study set, the DL BI-RADS categories achieved a similar AUC (0.901 vs. 0.933, p = 0.0632), sensitivity (90.98% vs. 95.90%, p = 0.1094), and accuracy (83.33% vs. 79.01%, p = 0.0541), but higher specificity (78.71% vs. 68.81%, p = 0.0012) than those of the consensus of the three radiologists.

CONCLUSIONS: The DL model performed well in distinguishing benign from malignant breast lesions and yielded outcomes similar to experienced radiologists. This indicates the potential applicability of the DL model in clinical diagnosis.

KEY POINTS: • The DL model can achieve binary categorization for benign and malignant breast lesions and six-way BI-RADS categorizations for categories 2, 3, 4a, 4b, 4c, and 5, simultaneously. • The DL model showed acceptable agreement with radiologists for the classification of breast lesions. • The DL model performed well in distinguishing benign from malignant breast lesions and had promise in helping reduce unnecessary biopsies of BI-RADS 4a lesions.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Gu, Xu, Liu, et al. Ultrasound-based deep learning in the establishment of a breast lesion risk stratification system: a multicenter study. Eur Radiol. 2022. PMID: 36418619. doi:10.1007/s00330-022-09263-8

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。