期刊
MEDICAL PHYSICS
卷 46, 期 4, 页码 1707-1718出版社
WILEY
DOI: 10.1002/mp.13416
关键词
3D prostate segmentation; deeply supervised mechanism; fully convolutional networks (FCN); group dilated convolution
资金
- National Cancer Institute of the National Institutes of Health [R01CA215718]
- Department of Defense (DoD) Prostate Cancer Research Program (PCRP) Award [W81XWH-13-1-0269, W81XWH-17-1-0438, W81XWH-17-1-0439]
- Dunwoody Golf Club Prostate Cancer Research Award
- Winship Cancer Institute of Emory University
- NVIDIA Corporation
PurposeReliable automated segmentation of the prostate is indispensable for image-guided prostate interventions. However, the segmentation task is challenging due to inhomogeneous intensity distributions, variation in prostate anatomy, among other problems. Manual segmentation can be time-consuming and is subject to inter- and intraobserver variation. We developed an automated deep learning-based method to address this technical challenge. MethodsWe propose a three-dimensional (3D) fully convolutional networks (FCN) with deep supervision and group dilated convolution to segment the prostate on magnetic resonance imaging (MRI). In this method, a deeply supervised mechanism was introduced into a 3D FCN to effectively alleviate the common exploding or vanishing gradients problems in training deep models, which forces the update process of the hidden layer filters to favor highly discriminative features. A group dilated convolution which aggregates multiscale contextual information for dense prediction was proposed to enlarge the effective receptive field of convolutional neural networks, which improve the prediction accuracy of prostate boundary. In addition, we introduced a combined loss function including cosine and cross entropy, which measures similarity and dissimilarity between segmented and manual contours, to further improve the segmentation accuracy. Prostate volumes manually segmented by experienced physicians were used as a gold standard against which our segmentation accuracy was measured. ResultsThe proposed method was evaluated on an internal dataset comprising 40 T2-weighted prostate MR volumes. Our method achieved a Dice similarity coefficient (DSC) of 0.860.04, a mean surface distance (MSD) of 1.79 +/- 0.46mm, 95% Hausdorff distance (95%HD) of 7.98 +/- 2.91mm, and absolute relative volume difference (aRVD) of 15.65 +/- 10.82. A public dataset (PROMISE12) including 50 T2-weighted prostate MR volumes was also employed to evaluate our approach. Our method yielded a DSC of 0.88 +/- 0.05, MSD of 1.02 +/- 0.35mm, 95% HD of 9.50 +/- 5.11mm, and aRVD of 8.93 +/- 7.56. ConclusionWe developed a novel deeply supervised deep learning-based approach with a group dilated convolution to automatically segment the MRI prostate, demonstrated its clinical feasibility, and validated its accuracy against manual segmentation. The proposed technique could be a useful tool for image-guided interventions in prostate cancer.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据