Task-based assessment of a convolutional neural network for segmenting breast lesions for radiomic analysis
Task-based assessment of a convolutional neural network for segmenting breast lesions for radiomic analysis
复制标题
DOI：
10.1002/mrm.27758
复制
发表时间：
2019-08-01
影响因子：
3.3
通讯作者：
Huang, Chuan
中科院分区：
文献类型：
--
作者：
Spuhler, Karl D.;Ding, Jie;Huang, Chuan
放射组学允许强大的数据挖掘和特征提取技术来指导临床决策。在这样的管道中，图像分割是必要的一步，不同的技术会显著影响结果。在已建立的放射组学流水线中，卷积神经网络(CNN)分割方法的性能与专家手动分割相当。方法使用专家放射科医生(R1)的手动感兴趣区域(ROI)，训练CNN从动态对比增强MRI(DCE-MRI)中分割乳腺病变。在网络训练之后，我们为先前建立的用于预测乳腺癌DCE-MRI淋巴转移的放射组学流水线的测试集分割病变。从原始研究、一位住院医师(R2)和另一位放射科专家(R3)确定CNN分割相对于手动分割的准确性。然后，我们使用R3‘S人工分割对CNN和放射组学模型进行重新训练，以确定不同专家观察员对端到端预测的影响。结果使用R1’S感兴趣区，CNN在测试集中的平均骰子系数为0.71~0.16。当输入到我们之前发表的放射组学流水线时，这些CNN分段获得了与R1‘S手动ROI相当的预测性能，并优于其他放射科医生的预测性能。在使用R3‘S感兴趣区训练细胞神经网络和放射组学模型时，也看到了类似的结果。结论细胞神经网络结构能够提供适合于输入到我们的放射组学模型的DCE-MRI乳腺病变分割。此外，以前建立的放射组学模型和CNN可以使用不同专家提供的地面事实数据进行端到端的准确培训。
PurposeRadiomics allows for powerful data-mining and feature extraction techniques to guide clinical decision making. Image segmentation is a necessary step in such pipelines and different techniques can significantly affect results. We demonstrate that a convolutional neural network (CNN) segmentation method performs comparably to expert manual segmentations in an established radiomics pipeline.MethodsUsing the manual regions of interest (ROIs) of an expert radiologist (R1), a CNN was trained to segment breast lesions from dynamic contrast-enhanced MRI (DCE-MRI). Following network training, we segmented lesions for the testing set of a previously established radiomics pipeline for predicting lymph node metastases using DCE-MRI of breast cancer. Prediction accuracy of CNN segmentations relative to manual segmentations by R1 from the original study, a resident (R2), and another expert radiologist (R3) were determined. We then retrained the CNN and radiomics model using R3's manual segmentations to determine the effects of different expert observers on end-to-end prediction.ResultsUsing R1's ROIs, the CNN achieved a mean Dice coefficient of 0.71 0.16 in the testing set. When input to our previously published radiomics pipeline, these CNN segmentations achieved comparable prediction performance to R1's manual ROIs, and superior performance to those of the other radiologists. Similar results were seen when training the CNN and radiomics model using R3's ROIs.ConclusionA CNN architecture is able to provide DCE-MRI breast lesion segmentations which are suitable for input to our radiomics model. Moreover, the previously established radiomics model and CNN can be accurately trained end-to-end using ground truth data provided by distinct experts.