A fully automatic multi-atlas based segmentation method for prostate MR images

Zhiqiang Tian, Lizhi Liu, Baowei Fei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Most of multi-atlas segmentation methods focus on the registration between the full-size volumes of the data set. Although the transformations obtained from these registrations may be accurate for the global field of view of the images, they may not be accurate for the local prostate region. This is because different magnetic resonance (MR) images have different fields of view and may have large anatomical variability around the prostate. To overcome this limitation, we proposed a two-stage prostate segmentation method based on a fully automatic multi-atlas framework, which includes the detection stage i.e. locating the prostate, and the segmentation stage i.e. extracting the prostate. The purpose of the first stage is to find a cuboid that contains the whole prostate as small cubage as possible. In this paper, the cuboid including the prostate is detected by registering atlas edge volumes to the target volume while an edge detection algorithm is applied to every slice in the volumes. At the second stage, the proposed method focuses on the registration in the region of the prostate vicinity, which can improve the accuracy of the prostate segmentation. We evaluated the proposed method on 12 patient MR volumes by performing a leave-one-out study. Dice similarity coefficient (DSC) and Hausdorff distance (HD) are used to quantify the difference between our method and the manual ground truth. The proposed method yielded a DSC of 83.4%±4.3%, and a HD of 9.3 mm±2.6 mm. The fully automated segmentation method can provide a useful tool in many prostate imaging applications.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2015
Subtitle of host publicationImage Processing
EditorsMartin A. Styner, Sebastien Ourselin
PublisherSPIE
ISBN (Electronic)9781628415032
DOIs
StatePublished - Jan 1 2015
Externally publishedYes
EventMedical Imaging 2015: Image Processing - Orlando, United States
Duration: Feb 24 2015Feb 26 2015

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume9413
ISSN (Print)1605-7422

Other

OtherMedical Imaging 2015: Image Processing
CountryUnited States
CityOrlando
Period2/24/152/26/15

Fingerprint

Atlases
Magnetic resonance
magnetic resonance
Prostate
Magnetic Resonance Spectroscopy
Edge detection
field of view
Imaging techniques
ground truth
edge detection
coefficients

Keywords

  • adaptive threshold
  • edge volume
  • Magnetic resonance imaging (MRI)
  • multi-atlas
  • prostate segmentation
  • registration

ASJC Scopus subject areas

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

Cite this

Tian, Z., Liu, L., & Fei, B. (2015). A fully automatic multi-atlas based segmentation method for prostate MR images. In M. A. Styner, & S. Ourselin (Eds.), Medical Imaging 2015: Image Processing [941340] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9413). SPIE. https://doi.org/10.1117/12.2082229

A fully automatic multi-atlas based segmentation method for prostate MR images. / Tian, Zhiqiang; Liu, Lizhi; Fei, Baowei.

Medical Imaging 2015: Image Processing. ed. / Martin A. Styner; Sebastien Ourselin. SPIE, 2015. 941340 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9413).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tian, Z, Liu, L & Fei, B 2015, A fully automatic multi-atlas based segmentation method for prostate MR images. in MA Styner & S Ourselin (eds), Medical Imaging 2015: Image Processing., 941340, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 9413, SPIE, Medical Imaging 2015: Image Processing, Orlando, United States, 2/24/15. https://doi.org/10.1117/12.2082229
Tian Z, Liu L, Fei B. A fully automatic multi-atlas based segmentation method for prostate MR images. In Styner MA, Ourselin S, editors, Medical Imaging 2015: Image Processing. SPIE. 2015. 941340. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.2082229
Tian, Zhiqiang ; Liu, Lizhi ; Fei, Baowei. / A fully automatic multi-atlas based segmentation method for prostate MR images. Medical Imaging 2015: Image Processing. editor / Martin A. Styner ; Sebastien Ourselin. SPIE, 2015. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
@inproceedings{d2e0518a66864237ac9a441358856782,
title = "A fully automatic multi-atlas based segmentation method for prostate MR images",
abstract = "Most of multi-atlas segmentation methods focus on the registration between the full-size volumes of the data set. Although the transformations obtained from these registrations may be accurate for the global field of view of the images, they may not be accurate for the local prostate region. This is because different magnetic resonance (MR) images have different fields of view and may have large anatomical variability around the prostate. To overcome this limitation, we proposed a two-stage prostate segmentation method based on a fully automatic multi-atlas framework, which includes the detection stage i.e. locating the prostate, and the segmentation stage i.e. extracting the prostate. The purpose of the first stage is to find a cuboid that contains the whole prostate as small cubage as possible. In this paper, the cuboid including the prostate is detected by registering atlas edge volumes to the target volume while an edge detection algorithm is applied to every slice in the volumes. At the second stage, the proposed method focuses on the registration in the region of the prostate vicinity, which can improve the accuracy of the prostate segmentation. We evaluated the proposed method on 12 patient MR volumes by performing a leave-one-out study. Dice similarity coefficient (DSC) and Hausdorff distance (HD) are used to quantify the difference between our method and the manual ground truth. The proposed method yielded a DSC of 83.4{\%}±4.3{\%}, and a HD of 9.3 mm±2.6 mm. The fully automated segmentation method can provide a useful tool in many prostate imaging applications.",
keywords = "adaptive threshold, edge volume, Magnetic resonance imaging (MRI), multi-atlas, prostate segmentation, registration",
author = "Zhiqiang Tian and Lizhi Liu and Baowei Fei",
year = "2015",
month = "1",
day = "1",
doi = "10.1117/12.2082229",
language = "English (US)",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",
editor = "Styner, {Martin A.} and Sebastien Ourselin",
booktitle = "Medical Imaging 2015",

}

TY - GEN

T1 - A fully automatic multi-atlas based segmentation method for prostate MR images

AU - Tian, Zhiqiang

AU - Liu, Lizhi

AU - Fei, Baowei

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Most of multi-atlas segmentation methods focus on the registration between the full-size volumes of the data set. Although the transformations obtained from these registrations may be accurate for the global field of view of the images, they may not be accurate for the local prostate region. This is because different magnetic resonance (MR) images have different fields of view and may have large anatomical variability around the prostate. To overcome this limitation, we proposed a two-stage prostate segmentation method based on a fully automatic multi-atlas framework, which includes the detection stage i.e. locating the prostate, and the segmentation stage i.e. extracting the prostate. The purpose of the first stage is to find a cuboid that contains the whole prostate as small cubage as possible. In this paper, the cuboid including the prostate is detected by registering atlas edge volumes to the target volume while an edge detection algorithm is applied to every slice in the volumes. At the second stage, the proposed method focuses on the registration in the region of the prostate vicinity, which can improve the accuracy of the prostate segmentation. We evaluated the proposed method on 12 patient MR volumes by performing a leave-one-out study. Dice similarity coefficient (DSC) and Hausdorff distance (HD) are used to quantify the difference between our method and the manual ground truth. The proposed method yielded a DSC of 83.4%±4.3%, and a HD of 9.3 mm±2.6 mm. The fully automated segmentation method can provide a useful tool in many prostate imaging applications.

AB - Most of multi-atlas segmentation methods focus on the registration between the full-size volumes of the data set. Although the transformations obtained from these registrations may be accurate for the global field of view of the images, they may not be accurate for the local prostate region. This is because different magnetic resonance (MR) images have different fields of view and may have large anatomical variability around the prostate. To overcome this limitation, we proposed a two-stage prostate segmentation method based on a fully automatic multi-atlas framework, which includes the detection stage i.e. locating the prostate, and the segmentation stage i.e. extracting the prostate. The purpose of the first stage is to find a cuboid that contains the whole prostate as small cubage as possible. In this paper, the cuboid including the prostate is detected by registering atlas edge volumes to the target volume while an edge detection algorithm is applied to every slice in the volumes. At the second stage, the proposed method focuses on the registration in the region of the prostate vicinity, which can improve the accuracy of the prostate segmentation. We evaluated the proposed method on 12 patient MR volumes by performing a leave-one-out study. Dice similarity coefficient (DSC) and Hausdorff distance (HD) are used to quantify the difference between our method and the manual ground truth. The proposed method yielded a DSC of 83.4%±4.3%, and a HD of 9.3 mm±2.6 mm. The fully automated segmentation method can provide a useful tool in many prostate imaging applications.

KW - adaptive threshold

KW - edge volume

KW - Magnetic resonance imaging (MRI)

KW - multi-atlas

KW - prostate segmentation

KW - registration

UR - http://www.scopus.com/inward/record.url?scp=84943413994&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943413994&partnerID=8YFLogxK

U2 - 10.1117/12.2082229

DO - 10.1117/12.2082229

M3 - Conference contribution

C2 - 26798187

AN - SCOPUS:84943413994

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

BT - Medical Imaging 2015

A2 - Styner, Martin A.

A2 - Ourselin, Sebastien

PB - SPIE

ER -