PSNet: Prostate segmentation on MRI based on a convolutional neural network

Zhiqiang Tian, Lizhi Liu, Zhenfeng Zhang, Baowei Fei

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Automatic segmentation of the prostate on magnetic resonance images (MRI) has many applications in prostate cancer diagnosis and therapy. We proposed 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, which uses prostate MRI and the corresponding ground truths as inputs. The learned CNN model can be used to make an inference for pixel-wise segmentation. Experiments were performed on three data sets, which contain prostate MRI of 140 patients. The proposed CNN model of prostate segmentation (PSNet) obtained a mean Dice similarity coefficient of 85.0 ± 3.8% as compared to the manually labeled ground truth. Experimental results show that the proposed model could yield satisfactory segmentation of the prostate on MRI.

Original languageEnglish (US)
Article number021208
JournalJournal of Medical Imaging
Volume5
Issue number2
DOIs
StatePublished - Apr 1 2018
Externally publishedYes

Fingerprint

Prostate
Magnetic Resonance Spectroscopy
Neural Networks (Computer)
Prostatic Neoplasms
Learning
Therapeutics

Keywords

  • convolutional neural network
  • deep learning
  • magnetic resonance imaging
  • prostate segmentation

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

PSNet : Prostate segmentation on MRI based on a convolutional neural network. / Tian, Zhiqiang; Liu, Lizhi; Zhang, Zhenfeng; Fei, Baowei.

In: Journal of Medical Imaging, Vol. 5, No. 2, 021208, 01.04.2018.

Research output: Contribution to journalArticle

Tian, Zhiqiang ; Liu, Lizhi ; Zhang, Zhenfeng ; Fei, Baowei. / PSNet : Prostate segmentation on MRI based on a convolutional neural network. In: Journal of Medical Imaging. 2018 ; Vol. 5, No. 2.
@article{d582fe1500f949469ddc586926d22934,
title = "PSNet: Prostate segmentation on MRI based on a convolutional neural network",
abstract = "Automatic segmentation of the prostate on magnetic resonance images (MRI) has many applications in prostate cancer diagnosis and therapy. We proposed 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, which uses prostate MRI and the corresponding ground truths as inputs. The learned CNN model can be used to make an inference for pixel-wise segmentation. Experiments were performed on three data sets, which contain prostate MRI of 140 patients. The proposed CNN model of prostate segmentation (PSNet) obtained a mean Dice similarity coefficient of 85.0 ± 3.8{\%} as compared to the manually labeled ground truth. Experimental results show that the proposed model could yield satisfactory segmentation of the prostate on MRI.",
keywords = "convolutional neural network, deep learning, magnetic resonance imaging, prostate segmentation",
author = "Zhiqiang Tian and Lizhi Liu and Zhenfeng Zhang and Baowei Fei",
year = "2018",
month = "4",
day = "1",
doi = "10.1117/1.JMI.5.2.021208",
language = "English (US)",
volume = "5",
journal = "Journal of Medical Imaging",
issn = "0720-048X",
publisher = "Elsevier Ireland Ltd",
number = "2",

}

TY - JOUR

T1 - PSNet

T2 - Prostate segmentation on MRI based on a convolutional neural network

AU - Tian, Zhiqiang

AU - Liu, Lizhi

AU - Zhang, Zhenfeng

AU - Fei, Baowei

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Automatic segmentation of the prostate on magnetic resonance images (MRI) has many applications in prostate cancer diagnosis and therapy. We proposed 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, which uses prostate MRI and the corresponding ground truths as inputs. The learned CNN model can be used to make an inference for pixel-wise segmentation. Experiments were performed on three data sets, which contain prostate MRI of 140 patients. The proposed CNN model of prostate segmentation (PSNet) obtained a mean Dice similarity coefficient of 85.0 ± 3.8% as compared to the manually labeled ground truth. Experimental results show that the proposed model could yield satisfactory segmentation of the prostate on MRI.

AB - Automatic segmentation of the prostate on magnetic resonance images (MRI) has many applications in prostate cancer diagnosis and therapy. We proposed 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, which uses prostate MRI and the corresponding ground truths as inputs. The learned CNN model can be used to make an inference for pixel-wise segmentation. Experiments were performed on three data sets, which contain prostate MRI of 140 patients. The proposed CNN model of prostate segmentation (PSNet) obtained a mean Dice similarity coefficient of 85.0 ± 3.8% as compared to the manually labeled ground truth. Experimental results show that the proposed model could yield satisfactory segmentation of the prostate on MRI.

KW - convolutional neural network

KW - deep learning

KW - magnetic resonance imaging

KW - prostate segmentation

UR - http://www.scopus.com/inward/record.url?scp=85040843405&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040843405&partnerID=8YFLogxK

U2 - 10.1117/1.JMI.5.2.021208

DO - 10.1117/1.JMI.5.2.021208

M3 - Article

C2 - 29376105

AN - SCOPUS:85040843405

VL - 5

JO - Journal of Medical Imaging

JF - Journal of Medical Imaging

SN - 0720-048X

IS - 2

M1 - 021208

ER -