MS lesion segmentation in MRI with random forests

Oskar Maier; Heinz Handels

doi:https://pdfs.semanticscholar.org/d784/2bece5c890630a80e6c4a190cb491cfaf9a7.pdf

MS lesion segmentation in MRI with random forests

Institute of Medical Informatics

Abstract

Multiple sclerosis (MS) is a common autoimmune disorder,
whose diagnosis and study often relies on the extraction
of biomarkers from magnetic resonance imaging (MRI)
scans. Manual segmentation of MS lesions suffers from large
intra- and inter-rater differences, whereas automatic methods
promise reproducibility and enhanced consistency, especially
for tracking the disease progress over time. To test this claim,
the ISBI 2015 Longitudinal MS Lesion Segmentation Challenge
provides a platform to compare existing methods in a
fair and consistent manner to each other and the manual approach.
In this article, we present our challenge contribution,
which is based on random forests and local context intensity
features to segment MS lesions in multi-spectral MRI images.

Original language	English
Journal	Proc. 2015 Longitudinal Multiple Sclerosis Lesion Segmentation Challenge
Pages (from-to)	1-2
Number of pages	2
DOIs	https://doi.org/https://pdfs.semanticscholar.org/d784/2bece5c890630a80e6c4a190cb491cfaf9a7.pdf
Publication status	Published - 2015

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 9 Industry, Innovation, and Infrastructure

Access to Document

https://pdfs.semanticscholar.org/d784/2bece5c890630a80e6c4a190cb491cfaf9a7.pdf

Cite this

@article{9e4fcb6522c0496699e113dbc91a47a4,

title = "MS lesion segmentation in MRI with random forests",

abstract = "Multiple sclerosis (MS) is a common autoimmune disorder, whose diagnosis and study often relies on the extraction of biomarkers from magnetic resonance imaging (MRI) scans. Manual segmentation of MS lesions suffers from large intra- and inter-rater differences, whereas automatic methods promise reproducibility and enhanced consistency, especially for tracking the disease progress over time. To test this claim, the ISBI 2015 Longitudinal MS Lesion Segmentation Challenge provides a platform to compare existing methods in a fair and consistent manner to each other and the manual approach. In this article, we present our challenge contribution, which is based on random forests and local context intensity features to segment MS lesions in multi-spectral MRI images.",

author = "Oskar Maier and Heinz Handels",

year = "2015",

doi = "https://pdfs.semanticscholar.org/d784/2bece5c890630a80e6c4a190cb491cfaf9a7.pdf",

language = "English",

pages = "1--2",

journal = "Proc. 2015 Longitudinal Multiple Sclerosis Lesion Segmentation Challenge",

}

TY - JOUR

T1 - MS lesion segmentation in MRI with random forests

AU - Maier, Oskar

AU - Handels, Heinz

PY - 2015

Y1 - 2015

N2 - Multiple sclerosis (MS) is a common autoimmune disorder, whose diagnosis and study often relies on the extraction of biomarkers from magnetic resonance imaging (MRI) scans. Manual segmentation of MS lesions suffers from large intra- and inter-rater differences, whereas automatic methods promise reproducibility and enhanced consistency, especially for tracking the disease progress over time. To test this claim, the ISBI 2015 Longitudinal MS Lesion Segmentation Challenge provides a platform to compare existing methods in a fair and consistent manner to each other and the manual approach. In this article, we present our challenge contribution, which is based on random forests and local context intensity features to segment MS lesions in multi-spectral MRI images.

AB - Multiple sclerosis (MS) is a common autoimmune disorder, whose diagnosis and study often relies on the extraction of biomarkers from magnetic resonance imaging (MRI) scans. Manual segmentation of MS lesions suffers from large intra- and inter-rater differences, whereas automatic methods promise reproducibility and enhanced consistency, especially for tracking the disease progress over time. To test this claim, the ISBI 2015 Longitudinal MS Lesion Segmentation Challenge provides a platform to compare existing methods in a fair and consistent manner to each other and the manual approach. In this article, we present our challenge contribution, which is based on random forests and local context intensity features to segment MS lesions in multi-spectral MRI images.

UR - http://www.imi.uni-luebeck.de/en/content/ms-lesion-segmentation-mri-random-forests

U2 - https://pdfs.semanticscholar.org/d784/2bece5c890630a80e6c4a190cb491cfaf9a7.pdf

DO - https://pdfs.semanticscholar.org/d784/2bece5c890630a80e6c4a190cb491cfaf9a7.pdf

M3 - Journal articles

SP - 1

EP - 2

JO - Proc. 2015 Longitudinal Multiple Sclerosis Lesion Segmentation Challenge

JF - Proc. 2015 Longitudinal Multiple Sclerosis Lesion Segmentation Challenge

ER -

MS lesion segmentation in MRI with random forests

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this