Automated fibroglandular tissue segmentation in breast MRI using generative adversarial networks
Automated fibroglandular tissue segmentation in breast MRI using generative adversarial networks
复制标题
使用生成对抗网络在乳腺 MRI 中自动进行纤维腺体组织分割
DOI：
10.1088/1361-6560/ab7e7f
复制
发表时间：
2020-05-21
影响因子：
3.5
通讯作者：
Lu, Yao
中科院分区：
文献类型：
--
作者：
Ma, Xiangyuan;Wang, Jinlong;Lu, Yao
纤维腺体组织（Fibroglandular tissue，FGT）分割是磁共振成像（magnetic resonance imaging，MRI）中背景实质增强（background parenchymal enhancement，BPE）定量分析的关键步骤，对乳腺癌风险评估具有重要意义。在这项研究中，我们开发了一种基于生成对抗网络（GAN）的自动深度学习方法，以识别MRI体积中的FGT区域，并评估其对特定临床应用的影响。GAN由改进的U-Net作为生成器来生成FGT候选区域，以及补丁深度卷积神经网络（DCNN）作为评估合成FGT区域真实性的工具。与经典的U-Net相比，该方法有两个改进：（1）改进的U-Net能够提取更多的FGT区域特征，对FGT区域进行更准确的描述;（2）设计了一个补丁DCNN来判别改进的U-Net生成的FGT区域的真实性，使得分割结果更加稳定和准确。本研究使用了100例患者（年龄22-78岁）的100次三维（3D）双侧乳腺MRI扫描数据集，并获得了机构审查委员会（IRB）的批准。提供所有乳房的3D手动分割FGT区域作为参考标准。在模型的训练和测试中使用了五重交叉验证。采用Dice相似系数（DSC）和Jaccard指数（JI）来衡量分割的准确性。在这项研究中，以前的方法使用经典的U-Net作为基线。在交叉验证集的五个分区中，GAN分别获得87.0 ± 7.0%和77.6 ± 10.1%的DSC和JI值，而通过基线方法获得的相应值分别为81.1 ± 8.7%和69.0 ± 11.3%。所提出的方法是显着的上级优于以前的方法，使用U-网。FGT分割以以下方式影响BPE量化应用：量化BPE值与放射科医师提供的BI-RADS BPE类别之间的相关系数为0.46 ± 0.15（最佳：0.63），而相应的相关系数为0.41 ± 0.16（最佳：0.60）基于基线U-Net分割FGT区域。使用GAN模型分割的FGT区域比使用基线U-Net分割的FGT区域可以更好地量化BPE。
Fibroglandular tissue (FGT) segmentation is a crucial step for quantitative analysis of background parenchymal enhancement (BPE) in magnetic resonance imaging (MRI), which is useful for breast cancer risk assessment. In this study, we develop an automated deep learning method based on a generative adversarial network (GAN) to identify the FGT region in MRI volumes and evaluate its impact on a specific clinical application. The GAN consists of an improved U-Net as a generator to generate FGT candidate areas and a patch deep convolutional neural network (DCNN) as a discriminator to evaluate the authenticity of the synthetic FGT region. The proposed method has two improvements compared to the classical U-Net: (1) the improved U-Net is designed to extract more features of the FGT region for a more accurate description of the FGT region; (2) a patch DCNN is designed for discriminating the authenticity of the FGT region generated by the improved U-Net, which makes the segmentation result more stable and accurate. A dataset of 100 three-dimensional (3D) bilateral breast MRI scans from 100 patients (aged 22–78 years) was used in this study with Institutional Review Board (IRB) approval. 3D hand-segmented FGT areas for all breasts were provided as a reference standard. Five-fold cross-validation was used in training and testing of the models. The Dice similarity coefficient (DSC) and Jaccard index (JI) values were evaluated to measure the segmentation accuracy. The previous method using classical U-Net was used as a baseline in this study. In the five partitions of the cross-validation set, the GAN achieved DSC and JI values of 87.0 ± 7.0% and 77.6 ± 10.1%, respectively, while the corresponding values obtained through by the baseline method were 81.1 ± 8.7% and 69.0 ± 11.3%, respectively. The proposed method is significantly superior to the previous method using U-Net. The FGT segmentation impacted the BPE quantification application in the following manner: the correlation coefficients between the quantified BPE value and BI-RADS BPE categories provided by the radiologist were 0.46 ± 0.15 (best: 0.63) based on GAN segmented FGT areas, while the corresponding correlation coefficients were 0.41 ± 0.16 (best: 0.60) based on baseline U-Net segmented FGT areas. BPE can be quantified better using the FGT areas segmented by the proposed GAN model than using the FGT areas segmented by the baseline U-Net.