文献速递乳腺技术与安全US

模拟人类决策的深度卷积神经网络用于乳腺超声病变自动分类

Automatic classification of ultrasound breast lesions using a deep convolutional neural network mimicking human decision-making.
PubMed 文献 · Eur Radiol · 2019-03-29

dCNN在内部测试集区分BI-RADS 2与3-5的准确率为87.1%(外部93.0%),人类阅片者为79.2±1.9%(外部95.3±2.3%);区分BI-RADS 2-3与4-5的准确率dCNN为93.1%(外部95.3%),人类为91.6±5.4%(外部94.1±1.2%);内部AUC dCNN为83.8(外部96.7),人类为84.6±2.3(外部90.9±2.9)。dCNN可能用于模拟人类决策并有助于标准化高度依赖观察者的超声评估。

要点

  • dCNN可按BI-RADS对乳腺超声病变分类,内部测试集区分BI-RADS 2与3-5准确率87.1%,外部93.0%。
  • 区分BI-RADS 2-3与4-5时,dCNN内部准确率93.1%、外部95.3%,与人类阅片者相近。
  • dCNN内部AUC 83.8、外部96.7,人类内部84.6±2.3、外部90.9±2.9,可能有助于标准化BI-RADS分类。

核心结论

  • dCNN可能用于模拟人类按BI-RADS标准对单张乳腺超声图像进行决策,达到较高准确率,并可能有助于标准化高度依赖观察者的超声评估。

诊断标准与关键数值

  • dCNN区分BI-RADS 2与BI-RADS 3-5病变的分类准确率:内部测试集87.1%,外部测试集93.0%;人类阅片者内部79.2±1.9%,外部95.3±2.3%。
  • dCNN区分BI-RADS 2-3与BI-RADS 4-5病变的分类准确率:内部测试集93.1%,外部测试集95.3%;人类阅片者内部91.6±5.4%,外部94.1±1.2%。
  • dCNN的AUC:内部数据集83.8,外部数据集96.7;人类阅片者AUC:内部84.6±2.3,外部90.9±2.9。

临床应用与阅片要点

  • dCNN可能用于模拟人类决策,对单张乳腺超声图像按BI-RADS目录进行分类。
  • 该技术达到较高准确率,可能有助于标准化高度依赖观察者的超声评估。

局限性

  • 原文未报告局限性。

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 evaluate a deep convolutional neural network (dCNN) for detection, highlighting, and classification of ultrasound (US) breast lesions mimicking human decision-making according to the Breast Imaging Reporting and Data System (BI-RADS).

METHODS AND MATERIALS: One thousand nineteen breast ultrasound images from 582 patients (age 56.3 ± 11.5 years) were linked to the corresponding radiological report. Lesions were categorized into the following classes: no tissue, normal breast tissue, BI-RADS 2 (cysts, lymph nodes), BI-RADS 3 (non-cystic mass), and BI-RADS 4-5 (suspicious). To test the accuracy of the dCNN, one internal dataset (101 images) and one external test dataset (43 images) were evaluated by the dCNN and two independent readers. Radiological reports, histopathological results, and follow-up examinations served as reference. The performances of the dCNN and the humans were quantified in terms of classification accuracies and receiver operating characteristic (ROC) curves.

RESULTS: In the internal test dataset, the classification accuracy of the dCNN differentiating BI-RADS 2 from BI-RADS 3-5 lesions was 87.1% (external 93.0%) compared with that of human readers with 79.2 ± 1.9% (external 95.3 ± 2.3%). For the classification of BI-RADS 2-3 versus BI-RADS 4-5, the dCNN reached a classification accuracy of 93.1% (external 95.3%), whereas the classification accuracy of humans yielded 91.6 ± 5.4% (external 94.1 ± 1.2%). The AUC on the internal dataset was 83.8 (external 96.7) for the dCNN and 84.6 ± 2.3 (external 90.9 ± 2.9) for the humans.

CONCLUSION: dCNNs may be used to mimic human decision-making in the evaluation of single US images of breast lesion according to the BI-RADS catalog. The technique reaches high accuracies and may serve for standardization of highly observer-dependent US assessment.

KEY POINTS: • Deep convolutional neural networks could be used to classify US breast lesions. • The implemented dCNN with its sliding window approach reaches high accuracies in the classification of US breast lesions. • Deep convolutional neural networks may serve for standardization in US BI-RADS classification.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Ciritsis A, Rossi C, Eberhard M, et al. Automatic classification of ultrasound breast lesions using a deep convolutional neural network mimicking human decision-making. Eur Radiol. 2019. PMID: 30927100. doi:10.1007/s00330-019-06118-7

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。