Deep convolutional neural network for prostate MR segmentation

Zhiqiang Tian; Lizhi Liu; Baowei Fei

doi:10.1117/12.2254621

Deep convolutional neural network for prostate MR segmentation

Zhiqiang Tian, Lizhi Liu, Baowei Fei

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

18 Scopus citations

Abstract

Automatic segmentation of the prostate in magnetic resonance imaging (MRI) has many applications in prostate cancer diagnosis and therapy. We propose a deep fully convolutional neural network (CNN) to segment the prostate automatically. Our deep CNN model is trained end-to-end in a single learning stage based on prostate MR images and the corresponding ground truths, and learns to make inference for pixel-wise segmentation. Experiments were performed on our in-house data set, which contains prostate MR images of 20 patients. The proposed CNN model obtained a mean Dice similarity coefficient of 85.3%±3.2% as compared to the manual segmentation. Experimental results show that our deep CNN model could yield satisfactory segmentation of the prostate.

Original language	English (US)
Title of host publication	Medical Imaging 2017
Subtitle of host publication	Image-Guided Procedures, Robotic Interventions, and Modeling
Editors	Robert J. Webster, Baowei Fei
Publisher	SPIE
ISBN (Electronic)	9781510607156
DOIs	https://doi.org/10.1117/12.2254621
State	Published - 2017
Externally published	Yes
Event	Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling - Orlando, United States Duration: Feb 14 2017 → Feb 16 2017

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	10135
ISSN (Print)	1605-7422

Other

Other	Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling
Country/Territory	United States
City	Orlando
Period	2/14/17 → 2/16/17

Keywords

Convolutional neural network
Deep learning
Magnetic resonance imaging (MRI)
Prostate segmentation

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Biomaterials
Atomic and Molecular Physics, and Optics
Radiology Nuclear Medicine and imaging

Access to Document

10.1117/12.2254621

Cite this

Deep convolutional neural network for prostate MR segmentation. / Tian, Zhiqiang; Liu, Lizhi; Fei, Baowei.
Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling. ed. / Robert J. Webster; Baowei Fei. SPIE, 2017. 101351L (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10135).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Tian, Z, Liu, L & Fei, B 2017, Deep convolutional neural network for prostate MR segmentation. in RJ Webster & B Fei (eds), Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling., 101351L, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 10135, SPIE, Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling, Orlando, United States, 2/14/17. https://doi.org/10.1117/12.2254621

@inproceedings{e39714e9ce59462193ebd81e0f748e80,

title = "Deep convolutional neural network for prostate MR segmentation",

abstract = "Automatic segmentation of the prostate in magnetic resonance imaging (MRI) has many applications in prostate cancer diagnosis and therapy. We propose a deep fully convolutional neural network (CNN) to segment the prostate automatically. Our deep CNN model is trained end-to-end in a single learning stage based on prostate MR images and the corresponding ground truths, and learns to make inference for pixel-wise segmentation. Experiments were performed on our in-house data set, which contains prostate MR images of 20 patients. The proposed CNN model obtained a mean Dice similarity coefficient of 85.3%±3.2% as compared to the manual segmentation. Experimental results show that our deep CNN model could yield satisfactory segmentation of the prostate.",

keywords = "Convolutional neural network, Deep learning, Magnetic resonance imaging (MRI), Prostate segmentation",

author = "Zhiqiang Tian and Lizhi Liu and Baowei Fei",

note = "Funding Information: This research is supported in part by NIH grants (CA176684, R01CA156775 and CA204254). Publisher Copyright: {\textcopyright} 2017 SPIE.; Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling ; Conference date: 14-02-2017 Through 16-02-2017",

year = "2017",

doi = "10.1117/12.2254621",

language = "English (US)",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Webster, {Robert J.} and Baowei Fei",

booktitle = "Medical Imaging 2017",

}

TY - GEN

T1 - Deep convolutional neural network for prostate MR segmentation

AU - Tian, Zhiqiang

AU - Liu, Lizhi

AU - Fei, Baowei

PY - 2017

Y1 - 2017

N2 - Automatic segmentation of the prostate in magnetic resonance imaging (MRI) has many applications in prostate cancer diagnosis and therapy. We propose a deep fully convolutional neural network (CNN) to segment the prostate automatically. Our deep CNN model is trained end-to-end in a single learning stage based on prostate MR images and the corresponding ground truths, and learns to make inference for pixel-wise segmentation. Experiments were performed on our in-house data set, which contains prostate MR images of 20 patients. The proposed CNN model obtained a mean Dice similarity coefficient of 85.3%±3.2% as compared to the manual segmentation. Experimental results show that our deep CNN model could yield satisfactory segmentation of the prostate.

AB - Automatic segmentation of the prostate in magnetic resonance imaging (MRI) has many applications in prostate cancer diagnosis and therapy. We propose a deep fully convolutional neural network (CNN) to segment the prostate automatically. Our deep CNN model is trained end-to-end in a single learning stage based on prostate MR images and the corresponding ground truths, and learns to make inference for pixel-wise segmentation. Experiments were performed on our in-house data set, which contains prostate MR images of 20 patients. The proposed CNN model obtained a mean Dice similarity coefficient of 85.3%±3.2% as compared to the manual segmentation. Experimental results show that our deep CNN model could yield satisfactory segmentation of the prostate.

KW - Convolutional neural network

KW - Deep learning

KW - Magnetic resonance imaging (MRI)

KW - Prostate segmentation

UR - http://www.scopus.com/inward/record.url?scp=85020421134&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020421134&partnerID=8YFLogxK

U2 - 10.1117/12.2254621

DO - 10.1117/12.2254621

M3 - Conference contribution

AN - SCOPUS:85020421134

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2017

A2 - Webster, Robert J.

A2 - Fei, Baowei

PB - SPIE

T2 - Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling

Y2 - 14 February 2017 through 16 February 2017

ER -

Deep convolutional neural network for prostate MR segmentation

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this