Share Email Print

Journal of Medical Imaging

Automatic magnetic resonance prostate segmentation by deep learning with holistically nested networks
Author(s): Ruida Cheng; Holger R. Roth; Nathan S. Lay; Le Lu; Baris Turkbey; William Gandler; Evan S. McCreedy; Thomas J. Pohida; Peter A. Pinto; Peter L. Choyke; Matthew J. McAuliffe; Ronald M. Summers
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Accurate automatic segmentation of the prostate in magnetic resonance images (MRI) is a challenging task due to the high variability of prostate anatomic structure. Artifacts such as noise and similar signal intensity of tissues around the prostate boundary inhibit traditional segmentation methods from achieving high accuracy. We investigate both patch-based and holistic (image-to-image) deep-learning methods for segmentation of the prostate. First, we introduce a patch-based convolutional network that aims to refine the prostate contour which provides an initialization. Second, we propose a method for end-to-end prostate segmentation by integrating holistically nested edge detection with fully convolutional networks. Holistically nested networks (HNN) automatically learn a hierarchical representation that can improve prostate boundary detection. Quantitative evaluation is performed on the MRI scans of 250 patients in fivefold cross-validation. The proposed enhanced HNN model achieves a mean ± standard deviation. A Dice similarity coefficient (DSC) of 89.77%±3.29% and a mean Jaccard similarity coefficient (IoU) of 81.59%±5.18% are used to calculate without trimming any end slices. The proposed holistic model significantly (p<0.001) outperforms a patch-based AlexNet model by 9% in DSC and 13% in IoU. Overall, the method achieves state-of-the-art performance as compared with other MRI prostate segmentation methods in the literature.

Paper Details

Date Published: 21 August 2017
PDF: 12 pages
J. Med. Imag. 4(4) 041302 doi: 10.1117/1.JMI.4.4.041302
Published in: Journal of Medical Imaging Volume 4, Issue 4
Show Author Affiliations
Ruida Cheng, National Institutes of Health (United States)
Holger R. Roth, National Institutes of Health (United States)
Nathan S. Lay, National Institutes of Health (United States)
Le Lu, National Institutes of Health (United States)
Baris Turkbey, National Cancer Institute (United States)
William Gandler, National Institutes of Health (United States)
Evan S. McCreedy, National Institutes of Health (United States)
Thomas J. Pohida, National Institutes of Health (United States)
Peter A. Pinto, National Cancer Institute (United States)
Peter L. Choyke, National Cancer Institute (United States)
Matthew J. McAuliffe, National Institutes of Health (United States)
Ronald M. Summers, National Institutes of Health (United States)

© SPIE. Terms of Use
Back to Top