Simultaneous Whole-Brain Segmentation and White Matter Lesion Detection Using Contrast-Adaptive Probabilistic Models

Oula Puonti; Koen Van Leemput

doi:10.1007/978-3-319-30858-6_2

Simultaneous Whole-Brain Segmentation and White Matter Lesion Detection Using Contrast-Adaptive Probabilistic Models

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

Abstract

In this paper we propose a new generative model for simultaneous brain parcellation and white matter lesion segmentation from multi-contrast magnetic resonance images. The method combines an existing whole-brain segmentation technique with a novel spatial lesion model based on a convolutional restricted Boltzmann machine. Unlike current state-of-the-art lesion detection techniques based on discriminative modeling, the proposed method is not tuned to one specific scanner or imaging protocol, and simultaneously segments dozens of neuroanatomical structures. Experiments on a public benchmark dataset in multiple sclerosis indicate that the method’s lesion segmentation accuracy compares well to that of the current state-of-the-art in the field, while additionally providing robust whole-brain segmentations.

Original language	English
Title of host publication	1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015) : Revised Selected Papers
Publisher	Springer
Publication date	2016
Pages	9-20
ISBN (Print)	978-3-319-30857-9
ISBN (Electronic)	978-3-319-30858-6
DOIs	https://doi.org/10.1007/978-3-319-30858-6_2
Publication status	Published - 2016
Event	1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015) - Munich, Germany Duration: 5 Oct 2015 → 5 Oct 2015 Conference number: 1

Workshop

Workshop	1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015)
Number	1
Country	Germany
City	Munich
Period	05/10/2015 → 05/10/2015
Other	Held in Conjunction with MICCAI 2015

Series	Lecture Notes in Computer Science
Volume	9556
ISSN	0302-9743

Access to Document

10.1007/978-3-319-30858-6_2

Fingerprint Dive into the research topics of 'Simultaneous Whole-Brain Segmentation and White Matter Lesion Detection Using Contrast-Adaptive Probabilistic Models'. Together they form a unique fingerprint.

Cite this

Puonti, O., & Van Leemput, K. (2016). Simultaneous Whole-Brain Segmentation and White Matter Lesion Detection Using Contrast-Adaptive Probabilistic Models. In 1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015): Revised Selected Papers (pp. 9-20). Springer. Lecture Notes in Computer Science Vol. 9556 https://doi.org/10.1007/978-3-319-30858-6_2

Puonti, Oula ; Van Leemput, Koen. / Simultaneous Whole-Brain Segmentation and White Matter Lesion Detection Using Contrast-Adaptive Probabilistic Models. 1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015): Revised Selected Papers. Springer, 2016. pp. 9-20 (Lecture Notes in Computer Science, Vol. 9556).

@inproceedings{9cb080e531a740d4a4e3f1c08ad35298,

title = "Simultaneous Whole-Brain Segmentation and White Matter Lesion Detection Using Contrast-Adaptive Probabilistic Models",

abstract = "In this paper we propose a new generative model for simultaneous brain parcellation and white matter lesion segmentation from multi-contrast magnetic resonance images. The method combines an existing whole-brain segmentation technique with a novel spatial lesion model based on a convolutional restricted Boltzmann machine. Unlike current state-of-the-art lesion detection techniques based on discriminative modeling, the proposed method is not tuned to one specific scanner or imaging protocol, and simultaneously segments dozens of neuroanatomical structures. Experiments on a public benchmark dataset in multiple sclerosis indicate that the method{\textquoteright}s lesion segmentation accuracy compares well to that of the current state-of-the-art in the field, while additionally providing robust whole-brain segmentations.",

author = "Oula Puonti and {Van Leemput}, Koen",

year = "2016",

doi = "10.1007/978-3-319-30858-6_2",

language = "English",

isbn = "978-3-319-30857-9",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "9--20",

booktitle = "1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015)",

note = "1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015) ; Conference date: 05-10-2015 Through 05-10-2015",

}

Puonti, O & Van Leemput, K 2016, Simultaneous Whole-Brain Segmentation and White Matter Lesion Detection Using Contrast-Adaptive Probabilistic Models. in 1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015): Revised Selected Papers. Springer, Lecture Notes in Computer Science, vol. 9556, pp. 9-20, 1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015), Munich, Germany, 05/10/2015. https://doi.org/10.1007/978-3-319-30858-6_2

Simultaneous Whole-Brain Segmentation and White Matter Lesion Detection Using Contrast-Adaptive Probabilistic Models. / Puonti, Oula; Van Leemput, Koen.

1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015): Revised Selected Papers. Springer, 2016. p. 9-20 (Lecture Notes in Computer Science, Vol. 9556).

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

TY - GEN

T1 - Simultaneous Whole-Brain Segmentation and White Matter Lesion Detection Using Contrast-Adaptive Probabilistic Models

AU - Puonti, Oula

AU - Van Leemput, Koen

N1 - Conference code: 1

PY - 2016

Y1 - 2016

N2 - In this paper we propose a new generative model for simultaneous brain parcellation and white matter lesion segmentation from multi-contrast magnetic resonance images. The method combines an existing whole-brain segmentation technique with a novel spatial lesion model based on a convolutional restricted Boltzmann machine. Unlike current state-of-the-art lesion detection techniques based on discriminative modeling, the proposed method is not tuned to one specific scanner or imaging protocol, and simultaneously segments dozens of neuroanatomical structures. Experiments on a public benchmark dataset in multiple sclerosis indicate that the method’s lesion segmentation accuracy compares well to that of the current state-of-the-art in the field, while additionally providing robust whole-brain segmentations.

AB - In this paper we propose a new generative model for simultaneous brain parcellation and white matter lesion segmentation from multi-contrast magnetic resonance images. The method combines an existing whole-brain segmentation technique with a novel spatial lesion model based on a convolutional restricted Boltzmann machine. Unlike current state-of-the-art lesion detection techniques based on discriminative modeling, the proposed method is not tuned to one specific scanner or imaging protocol, and simultaneously segments dozens of neuroanatomical structures. Experiments on a public benchmark dataset in multiple sclerosis indicate that the method’s lesion segmentation accuracy compares well to that of the current state-of-the-art in the field, while additionally providing robust whole-brain segmentations.

U2 - 10.1007/978-3-319-30858-6_2

DO - 10.1007/978-3-319-30858-6_2

M3 - Article in proceedings

SN - 978-3-319-30857-9

T3 - Lecture Notes in Computer Science

SP - 9

EP - 20

BT - 1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015)

PB - Springer

T2 - 1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015)

Y2 - 5 October 2015 through 5 October 2015

ER -

Puonti O, Van Leemput K. Simultaneous Whole-Brain Segmentation and White Matter Lesion Detection Using Contrast-Adaptive Probabilistic Models. In 1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015): Revised Selected Papers. Springer. 2016. p. 9-20. (Lecture Notes in Computer Science, Vol. 9556). https://doi.org/10.1007/978-3-319-30858-6_2