Department of Radiation Oncology, Emory University, Atlanta, GA 30322, United States of America. Department of Biomedical Informatics, Emory University, Atlanta, GA 30322, United States of America.
Phys Med Biol. 2020 Sep 18;65(18):185009. doi: 10.1088/1361-6560/aba6d4.
The segmentation of neoplasms is an important part of radiotherapy treatment planning, monitoring disease progression, and predicting patient outcome. In the brain, functional magnetic resonance imaging (MRI) like dynamic susceptibility contrast enhanced (DSCE) or T1-weighted dynamic contrast enhanced (DCE) perfusion MRI are important tools for diagnosis. They play a crucial role in providing pre-operative assessment of tumor histology, grading, and biopsy guidance. However, the manual contouring of these neoplasms is tedious, expensive, time-consuming, and vulnerable to inter-observer variability. In this work, we propose a 3D mask region-based convolutional neural network (R-CNN) method to automatically segment brain tumors in DSCE MRI perfusion images. As our goal is to simultaneously localize and segment the tumor, our training process contained both a region-of-interest (ROI) localization and regression with voxel-wise segmentation. The combination of classification loss, ROI location and size regression loss, and segmentation loss were used to supervise the proposed network. We retrospectively investigated 21 patients' perfusion images, with between 50 and 70 perfusion time point volumes, a total of 1260 3D volumes. Tumor contours were automatically segmented by our proposed method and compared against other state-of-the-art methods and those delineated by physicians as the ground truth. The results of our method demonstrated good agreement with the ground truth contours. The average DSC, precision, recall, Hausdorff distance, mean surface distance (MSD), root MSD, and center of mass distance were 0.90 ± 0.04, 0.91 ± 0.04, 0.90 ± 0.06, 7.16 ± 5.78 mm, 0.45 ± 0.34 mm, 1.03 ± 0.72 mm, and 0.86 ± 0.91 mm, respectively. These results support the feasibility of our method in accurately localizing and segmenting brain tumors in DSCE perfusion MRI. Our 3D Mask R-CNN segmentation method in DSCE perfusion imaging has great promise for future clinical use.
肿瘤的分割是放射治疗计划、监测疾病进展和预测患者预后的重要组成部分。在大脑中，功能磁共振成像（MRI），如动态磁敏感对比增强（DSCE）或 T1 加权动态对比增强（DCE）灌注 MRI，是诊断的重要工具。它们在提供肿瘤组织学、分级的术前评估和活检指导方面发挥着至关重要的作用。然而，这些肿瘤的手动勾画既繁琐、昂贵、耗时，且容易受到观察者间变异性的影响。在这项工作中，我们提出了一种基于三维掩模的区域卷积神经网络（R-CNN）方法，用于自动分割 DSCE MRI 灌注图像中的脑肿瘤。由于我们的目标是同时定位和分割肿瘤，因此我们的训练过程既包含了感兴趣区域（ROI）的定位，也包含了体素级别的分割回归。分类损失、ROI 位置和大小回归损失以及分割损失的组合用于监督所提出的网络。我们回顾性地研究了 21 名患者的灌注图像，每个患者的灌注时间点体积在 50 到 70 个之间，共 1260 个 3D 体积。我们的方法自动分割了肿瘤轮廓，并与其他最先进的方法和医生勾画的真实轮廓进行了比较。我们的方法的结果与真实轮廓有很好的一致性。该方法的平均 DSC、精度、召回率、Hausdorff 距离、平均表面距离（MSD）、根均方根距离（RMSD）和质心距离分别为 0.90 ± 0.04、0.91 ± 0.04、0.90 ± 0.06、7.16 ± 5.78mm、0.45 ± 0.34mm、1.03 ± 0.72mm 和 0.86 ± 0.91mm。这些结果支持了我们的方法在准确定位和分割 DSCE 灌注 MRI 中的脑肿瘤的可行性。我们在 DSCE 灌注成像中的 3D 掩模 R-CNN 分割方法具有很大的临床应用前景。
