文献速递乳腺MR

弱监督深度学习方法用于乳腺MRI评估

Weakly Supervised Deep Learning Approach to Breast MRI Assessment.
PubMed 文献 · Acad Radiol · 2021-06-06

本研究评估了一种无需像素级分割的弱监督深度学习方法用于乳腺MRI病变分类,数据集包含438例患者的278685个图像切片,弱监督网络基于Resnet-101架构,在区分恶性与良性图像中AUC为0.92(SD ± 0.03),准确率94.2%(SD ± 3.4),敏感度74.4%(SD ± 8.5),特异度95.3%(SD ± 3.3)。作者结论为无需像素级分割的弱监督深度学习方法评估乳腺MRI图像是可行的,并在病变分类中获得了高度特异度。

要点

  • 弱监督网络区分乳腺MRI恶性与良性图像的AUC为0.92(SD ± 0.03)。
  • 模型准确率94.2%(SD ± 3.4),敏感度74.4%(SD ± 8.5),特异度95.3%(SD ± 3.3)。
  • 无需像素级分割即可获得高特异度的病变分类。

核心结论

  • 使用弱监督深度学习方法评估乳腺MRI图像而无需像素级分割是可行的,并在病变分类中获得了高度特异度。

研究设计与样本

  • 经IRB批准的研究,数据集由438例患者的278685个图像切片组成,弱监督网络基于Resnet-101架构,使用Adam优化器训练,最终SoftMax分数阈值0.5用于二分类(恶性或良性),278685个图像切片合并为92895个三通道图像,79871个(85%)图像用于训练和验证,13024个(15%)图像用于测试,测试集中11498个(88%)为良性、1531个(12%)为恶性。

诊断标准与关键数值

  • 弱监督网络区分恶性与良性图像的AUC为0.92(SD ± 0.03);模型准确率94.2%(SD ± 3.4),敏感度74.4%(SD ± 8.5),特异度95.3%(SD ± 3.3);二分类最终SoftMax分数阈值为0.5。

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: To evaluate a weakly supervised deep learning approach to breast Magnetic Resonance Imaging (MRI) assessment without pixel level segmentation in order to improve the specificity of breast MRI lesion classification.

MATERIALS AND METHODS: In this IRB approved study, the dataset consisted of 278,685 image slices from 438 patients. The weakly supervised network was based on the Resnet-101 architecture. Training was implemented using the Adam optimizer and a final SoftMax score threshold of 0.5 was used for two class classification (malignant or benign). 278,685 image slices were combined into 92,895 3-channel images. 79,871 (85%) images were used for training and validation while 13,024 (15%) images were separated for testing. Of the testing dataset, 11,498 (88%) were benign and 1531 (12%) were malignant. Model performance was assessed.

RESULTS: The weakly supervised network achieved an AUC of 0.92 (SD ± 0.03) in distinguishing malignant from benign images. The model had an accuracy of 94.2% (SD ± 3.4) with a sensitivity and specificity of 74.4% (SD ± 8.5) and 95.3% (SD ± 3.3) respectively.

CONCLUSION: It is feasible to use a weakly supervised deep learning approach to assess breast MRI images without the need for pixel-by-pixel segmentation yielding a high degree of specificity in lesion classification.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Liu MZ, Swintelski C, Sun S, et al. Weakly Supervised Deep Learning Approach to Breast MRI Assessment. Acad Radiol. 2021. PMID: 34108114. doi:10.1016/j.acra.2021.03.032

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。