Format

Send to

Choose Destination
J Med Imaging (Bellingham). 2019 Apr;6(2):024007. doi: 10.1117/1.JMI.6.2.024007. Epub 2019 Jun 5.

Fully automated prostate whole gland and central gland segmentation on MRI using holistically nested networks with short connections.

Author information

1
National Institutes of Health, Center for Information Technology, Image Sciences Laboratory, Bethesda, Maryland, United States.
2
National Institutes of Health Clinical Center, Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, Bethesda, Maryland, United States.
3
National Cancer Institute, Molecular Imaging Program, Bethesda, Maryland, United States.
4
National Institutes of Health, Center for Information Technology, Computational Bioscience and Engineering Laboratory, Bethesda, Maryland, United States.
5
National Cancer Institute, Center for Cancer Research, Urologic Oncology Branch, Bethesda, Maryland, United States.

Abstract

Accurate and automated prostate whole gland and central gland segmentations on MR images are essential for aiding any prostate cancer diagnosis system. Our work presents a 2-D orthogonal deep learning method to automatically segment the whole prostate and central gland from T2-weighted axial-only MR images. The proposed method can generate high-density 3-D surfaces from low-resolution ( z axis) MR images. In the past, most methods have focused on axial images alone, e.g., 2-D based segmentation of the prostate from each 2-D slice. Those methods suffer the problems of over-segmenting or under-segmenting the prostate at apex and base, which adds a major contribution for errors. The proposed method leverages the orthogonal context to effectively reduce the apex and base segmentation ambiguities. It also overcomes jittering or stair-step surface artifacts when constructing a 3-D surface from 2-D segmentation or direct 3-D segmentation approaches, such as 3-D U-Net. The experimental results demonstrate that the proposed method achieves 92.4 % ± 3 % Dice similarity coefficient (DSC) for prostate and DSC of 90.1 % ± 4.6 % for central gland without trimming any ending contours at apex and base. The experiments illustrate the feasibility and robustness of the 2-D-based holistically nested networks with short connections method for MR prostate and central gland segmentation. The proposed method achieves segmentation results on par with the current literature.

KEYWORDS:

MRI; deep learning; holistically nested networks; prostate; segmentation

PMID:
31205977
PMCID:
PMC6551111
[Available on 2020-06-05]
DOI:
10.1117/1.JMI.6.2.024007

Supplemental Content

Loading ...
Support Center