Format

Send to

Choose Destination
J Med Imaging (Bellingham). 2017 Oct;4(4):041302. doi: 10.1117/1.JMI.4.4.041302. Epub 2017 Aug 21.

Automatic magnetic resonance prostate segmentation by deep learning with holistically nested networks.

Author information

1
Imaging Sciences Laboratory, Center of Information Technology, NIH, Bethesda, Maryland, United States.
2
Imaging Biomarkers and CAD Laboratory, Clinical Center, NIH, Bethesda, Maryland, United States.
3
Molecular Imaging Program, NCI, Bethesda, Maryland, United States.
4
Computational Bioscience and Engineering Laboratory, Center of Information Technology, NIH, Bethesda, Maryland, United States.
5
Center of Cancer Research, Urologic Oncology Branch, Bethesda, Maryland, United States.

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 [Formula: see text] and a mean Jaccard similarity coefficient (IoU) of [Formula: see text] are used to calculate without trimming any end slices. The proposed holistic model significantly ([Formula: see text]) 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.

KEYWORDS:

deep learning; holistically nested edge detection; holistically nested networks; magnetic resonance images; prostate; segmentation

Supplemental Content

Full text links

Icon for Society of Photo-Optical Instrumentation Engineers Icon for PubMed Central
Loading ...
Support Center