文献速递乳腺MR

基于非脂肪抑制图像训练、脂肪抑制图像测试的Mask R-CNN在乳腺MRI上自动检测与分割乳腺癌

Automatic Detection and Segmentation of Breast Cancer on MRI Using Mask R-CNN Trained on Non-Fat-Sat Images and Tested on Fat-Sat Images.
PubMed 文献 · Acad Radiol · 2020-12-13

研究用241例非脂肪抑制序列DCE-MRI训练Mask R-CNN、98例脂肪抑制序列测试,以模糊C均值聚类分割肿瘤为参考标准。训练集10折交叉验证平均准确率0.86、DSC 0.82,测试集准确率0.75、DSC 0.79;逐切片结果合并后训练集241个病灶中240个(99.5%)、测试集98个病灶全部(100%)被检出。作者认为该方法可行,可能与其他人工智能算法整合构建全自动乳腺MRI诊断系统。

要点

  • 输入双乳增强前图像与减影图像可最大限度减少来自心脏及正常实质强化的假阳性。
  • 训练集逐切片准确率0.86、DSC 0.82;测试集准确率0.75、DSC 0.79。
  • 逐切片结果合并后病灶检出:训练集240/241(99.5%),测试集98/98(100%)。

研究设计与样本

  • 研究论文,采用两个DCE-MRI数据集:241例使用非脂肪抑制序列采集用于训练,98例使用脂肪抑制序列采集用于测试。
  • 全部患者均为经证实的单侧肿块型乳腺癌。
  • 以模糊C均值聚类算法分割的肿瘤作为参考标准(ground truth)。
  • Mask R-CNN以ResNet-101为主干网络实现,输出边界框与分割肿瘤,用Dice相似系数(DSC)评价。
  • 检测性能及敏感度与特异度之间的权衡用自由响应受试者工作特征(FROC)分析。

诊断标准与关键数值

  • 训练集含1469个阳性切片(含病灶)和9135个阴性切片,10折交叉验证平均准确率=0.86、DSC=0.82。
  • 测试集含1568个阳性切片和7264个阴性切片,准确率=0.75、DSC=0.79。
  • 逐切片结果合并后,训练集241个病灶中240个(99.5%)被识别,测试集98个病灶中98个(100%)被识别。
  • 使用双乳增强前图像与减影图像作为输入时,来自心脏和正常实质强化的假阳性可被最小化。

临床应用与阅片要点

  • 作者认为该方法可能与其他人工智能算法整合,以开发全自动乳腺MRI诊断系统。

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

RATIONALE AND OBJECTIVES: Computer-aided methods have been widely applied to diagnose lesions on breast magnetic resonance imaging (MRI). The first step was to identify abnormal areas. A deep learning Mask Regional Convolutional Neural Network (R-CNN) was implemented to search the entire set of images and detect suspicious lesions.

MATERIALS AND METHODS: Two DCE-MRI datasets were used, 241 patients acquired using non-fat-sat sequence for training, and 98 patients acquired using fat-sat sequence for testing. All patients have confirmed unilateral mass cancers. The tumor was segmented using fuzzy c-means clustering algorithm to serve as the ground truth. Mask R-CNN was implemented with ResNet-101 as the backbone. The neural network output the bounding boxes and the segmented tumor for evaluation using the Dice Similarity Coefficient (DSC). The detection performance, and the trade-off between sensitivity and specificity, was analyzed using free response receiver operating characteristic.

RESULTS: When the precontrast and subtraction image of both breasts were used as input, the false positive from the heart and normal parenchymal enhancements could be minimized. The training set had 1469 positive slices (containing lesion) and 9135 negative slices. In 10-fold cross-validation, the mean accuracy = 0.86 and DSC = 0.82. The testing dataset had 1568 positive and 7264 negative slices, with accuracy = 0.75 and DSC = 0.79. When the obtained per-slice results were combined, 240 of 241 (99.5%) lesions in the training and 98 of 98 (100%) lesions in the testing datasets were identified.

CONCLUSION: Deep learning using Mask R-CNN provided a feasible method to search breast MRI, localize, and segment lesions. This may be integrated with other artificial intelligence algorithms to develop a fully automatic breast MRI diagnostic system.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Zhang Y, Chan S, Park VY, et al. Automatic Detection and Segmentation of Breast Cancer on MRI Using Mask R-CNN Trained on Non-Fat-Sat Images and Tested on Fat-Sat Images. Acad Radiol. 2020. PMID: 33317911. doi:10.1016/j.acra.2020.12.001

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。