MS lesion segmentation using a multi-channel patch-based approach with spatial consistency

Roey Mechrez; Jacob Goldberger; Hayit Greenspan

doi:10.1117/12.2082558

MS lesion segmentation using a multi-channel patch-based approach with spatial consistency

Roey Mechrez, Jacob Goldberger, Hayit Greenspan

Tel Aviv University

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

1 Scopus citations

Abstract

This paper presents an automatic method for segmentation of Multiple Sclerosis (MS) in Magnetic Resonance Images (MRI) of the brain. The approach is based on similarities between multi-channel patches (T1, T2 and FLAIR). An MS lesion patch database is built using training images for which the label maps are known. For each patch in the testing image, k similar patches are retrieved from the database. The matching labels for these k patches are then combined to produce an initial segmentation map for the test case. Finally a novel iterative patch-based label refinement process based on the initial segmentation map is performed to ensure spatial consistency of the detected lesions. A leave-one-out evaluation is done for each testing image in the MS lesion segmentation challenge of MICCAI 2008. Results are shown to compete with the state-of-the-art methods on the MICCAI 2008 challenge.

Original language	English
Title of host publication	Medical Imaging 2015
Subtitle of host publication	Image Processing
Editors	Martin A. Styner, Sebastien Ourselin
Publisher	SPIE
ISBN (Electronic)	9781628415032
DOIs	https://doi.org/10.1117/12.2082558
State	Published - 2015
Event	Medical Imaging 2015: Image Processing - Orlando, United States Duration: 24 Feb 2015 → 26 Feb 2015

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	9413
ISSN (Print)	1605-7422

Conference

Conference	Medical Imaging 2015: Image Processing
Country/Territory	United States
City	Orlando
Period	24/02/15 → 26/02/15

Bibliographical note

Publisher Copyright:
© 2015 SPIE.

Access to Document

10.1117/12.2082558

Cite this

@inproceedings{4af065e5f09e4b928c66b37caf74cd3b,

title = "MS lesion segmentation using a multi-channel patch-based approach with spatial consistency",

abstract = "This paper presents an automatic method for segmentation of Multiple Sclerosis (MS) in Magnetic Resonance Images (MRI) of the brain. The approach is based on similarities between multi-channel patches (T1, T2 and FLAIR). An MS lesion patch database is built using training images for which the label maps are known. For each patch in the testing image, k similar patches are retrieved from the database. The matching labels for these k patches are then combined to produce an initial segmentation map for the test case. Finally a novel iterative patch-based label refinement process based on the initial segmentation map is performed to ensure spatial consistency of the detected lesions. A leave-one-out evaluation is done for each testing image in the MS lesion segmentation challenge of MICCAI 2008. Results are shown to compete with the state-of-the-art methods on the MICCAI 2008 challenge.",

author = "Roey Mechrez and Jacob Goldberger and Hayit Greenspan",

note = "Publisher Copyright: {\textcopyright} 2015 SPIE.; Medical Imaging 2015: Image Processing ; Conference date: 24-02-2015 Through 26-02-2015",

year = "2015",

doi = "10.1117/12.2082558",

language = "אנגלית",

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

publisher = "SPIE",

editor = "Styner, {Martin A.} and Sebastien Ourselin",

booktitle = "Medical Imaging 2015",

address = "ארצות הברית",

}

Mechrez, R, Goldberger, J & Greenspan, H 2015, MS lesion segmentation using a multi-channel patch-based approach with spatial consistency. in MA Styner & S Ourselin (eds), Medical Imaging 2015: Image Processing., 94130O, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 9413, SPIE, Medical Imaging 2015: Image Processing, Orlando, United States, 24/02/15. https://doi.org/10.1117/12.2082558

MS lesion segmentation using a multi-channel patch-based approach with spatial consistency. / Mechrez, Roey; Goldberger, Jacob; Greenspan, Hayit.
Medical Imaging 2015: Image Processing. ed. / Martin A. Styner; Sebastien Ourselin. SPIE, 2015. 94130O (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9413).

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

TY - GEN

T1 - MS lesion segmentation using a multi-channel patch-based approach with spatial consistency

AU - Mechrez, Roey

AU - Goldberger, Jacob

AU - Greenspan, Hayit

PY - 2015

Y1 - 2015

N2 - This paper presents an automatic method for segmentation of Multiple Sclerosis (MS) in Magnetic Resonance Images (MRI) of the brain. The approach is based on similarities between multi-channel patches (T1, T2 and FLAIR). An MS lesion patch database is built using training images for which the label maps are known. For each patch in the testing image, k similar patches are retrieved from the database. The matching labels for these k patches are then combined to produce an initial segmentation map for the test case. Finally a novel iterative patch-based label refinement process based on the initial segmentation map is performed to ensure spatial consistency of the detected lesions. A leave-one-out evaluation is done for each testing image in the MS lesion segmentation challenge of MICCAI 2008. Results are shown to compete with the state-of-the-art methods on the MICCAI 2008 challenge.

AB - This paper presents an automatic method for segmentation of Multiple Sclerosis (MS) in Magnetic Resonance Images (MRI) of the brain. The approach is based on similarities between multi-channel patches (T1, T2 and FLAIR). An MS lesion patch database is built using training images for which the label maps are known. For each patch in the testing image, k similar patches are retrieved from the database. The matching labels for these k patches are then combined to produce an initial segmentation map for the test case. Finally a novel iterative patch-based label refinement process based on the initial segmentation map is performed to ensure spatial consistency of the detected lesions. A leave-one-out evaluation is done for each testing image in the MS lesion segmentation challenge of MICCAI 2008. Results are shown to compete with the state-of-the-art methods on the MICCAI 2008 challenge.

UR - http://www.scopus.com/inward/record.url?scp=84943377697&partnerID=8YFLogxK

U2 - 10.1117/12.2082558

DO - 10.1117/12.2082558

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84943377697

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

BT - Medical Imaging 2015

A2 - Styner, Martin A.

A2 - Ourselin, Sebastien

PB - SPIE

T2 - Medical Imaging 2015: Image Processing

Y2 - 24 February 2015 through 26 February 2015

ER -

MS lesion segmentation using a multi-channel patch-based approach with spatial consistency

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this