The Relevance Voxel Machine (RVoxM): A Bayesian Method for Image-Based Prediction

Mert R. Sabuncu; Koen Van Leemput

doi:10.1007/978-3-642-23626-6_13

The Relevance Voxel Machine (RVoxM): A Bayesian Method for Image-Based Prediction

Mert R. Sabuncu, Koen Van Leemput

Massachusetts General Hospital/Harvard Medical School

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

Abstract

This paper presents the Relevance VoxelMachine (RVoxM), a Bayesian multivariate pattern analysis (MVPA) algorithm that is specifically designed for making predictions based on image data. In contrast to generic MVPA algorithms that have often been used for this purpose, the method is designed to utilize a small number of spatially clustered sets of voxels that are particularly suited for clinical interpretation. RVoxM automatically tunes all its free parameters during the training phase, and offers the additional advantage of producing probabilistic prediction outcomes. Experiments on age prediction from structural brain MRI indicate that RVoxM yields biologically meaningful models that provide excellent predictive accuracy.

Original language	English
Title of host publication	Medical Image Computing and Computer-Assisted Intervention –MICCAI2011 : 14th International Conference Toronto, Canada, September 18-22, 2011 Proceedings
Volume	3
Publisher	Springer
Publication date	2011
Pages	99-106
ISBN (Print)	978-3-642-23625-9
ISBN (Electronic)	978-3-642-23626-6
DOIs	https://doi.org/10.1007/978-3-642-23626-6_13
Publication status	Published - 2011
Event	14th International Conference on Medical Image Computing and Computer-Assisted Intervention - Toronto, Canada Duration: 18 Sept 2011 → 22 Sept 2011 Conference number: 14

Conference

Conference	14th International Conference on Medical Image Computing and Computer-Assisted Intervention
Number	14
Country/Territory	Canada
City	Toronto
Period	18/09/2011 → 22/09/2011

Series	Lecture Notes in Computer Science
Number	6893
ISSN	0302-9743

Keywords

MRI
Multivariate Pattern Analysis

Access to Document

10.1007/978-3-642-23626-6_13

http://www.miccai2011.org/

OpenUrl availability

Full text

Cite this

@inproceedings{12a7eba93d38477b83297200b77d8a95,

title = "The Relevance Voxel Machine (RVoxM): A Bayesian Method for Image-Based Prediction",

abstract = "This paper presents the Relevance VoxelMachine (RVoxM), a Bayesian multivariate pattern analysis (MVPA) algorithm that is specifically designed for making predictions based on image data. In contrast to generic MVPA algorithms that have often been used for this purpose, the method is designed to utilize a small number of spatially clustered sets of voxels that are particularly suited for clinical interpretation. RVoxM automatically tunes all its free parameters during the training phase, and offers the additional advantage of producing probabilistic prediction outcomes. Experiments on age prediction from structural brain MRI indicate that RVoxM yields biologically meaningful models that provide excellent predictive accuracy.",

keywords = "MRI, Multivariate Pattern Analysis",

author = "Sabuncu, {Mert R.} and {Van Leemput}, Koen",

year = "2011",

doi = "10.1007/978-3-642-23626-6_13",

language = "English",

isbn = "978-3-642-23625-9",

volume = "3",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

number = "6893",

pages = "99--106",

booktitle = "Medical Image Computing and Computer-Assisted Intervention –MICCAI2011",

note = "14th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2011 ; Conference date: 18-09-2011 Through 22-09-2011",

}

Sabuncu, MR & Van Leemput, K 2011, The Relevance Voxel Machine (RVoxM): A Bayesian Method for Image-Based Prediction. in Medical Image Computing and Computer-Assisted Intervention –MICCAI2011: 14th International Conference Toronto, Canada, September 18-22, 2011 Proceedings. vol. 3, Springer, Lecture Notes in Computer Science, no. 6893, pp. 99-106, 14th International Conference on Medical Image Computing and Computer-Assisted Intervention, Toronto, Canada, 18/09/2011. https://doi.org/10.1007/978-3-642-23626-6_13

The Relevance Voxel Machine (RVoxM): A Bayesian Method for Image-Based Prediction. / Sabuncu, Mert R.; Van Leemput, Koen.
Medical Image Computing and Computer-Assisted Intervention –MICCAI2011: 14th International Conference Toronto, Canada, September 18-22, 2011 Proceedings. Vol. 3 Springer, 2011. p. 99-106 (Lecture Notes in Computer Science; No. 6893).

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

TY - GEN

T1 - The Relevance Voxel Machine (RVoxM): A Bayesian Method for Image-Based Prediction

AU - Sabuncu, Mert R.

AU - Van Leemput, Koen

N1 - Conference code: 14

PY - 2011

Y1 - 2011

N2 - This paper presents the Relevance VoxelMachine (RVoxM), a Bayesian multivariate pattern analysis (MVPA) algorithm that is specifically designed for making predictions based on image data. In contrast to generic MVPA algorithms that have often been used for this purpose, the method is designed to utilize a small number of spatially clustered sets of voxels that are particularly suited for clinical interpretation. RVoxM automatically tunes all its free parameters during the training phase, and offers the additional advantage of producing probabilistic prediction outcomes. Experiments on age prediction from structural brain MRI indicate that RVoxM yields biologically meaningful models that provide excellent predictive accuracy.

AB - This paper presents the Relevance VoxelMachine (RVoxM), a Bayesian multivariate pattern analysis (MVPA) algorithm that is specifically designed for making predictions based on image data. In contrast to generic MVPA algorithms that have often been used for this purpose, the method is designed to utilize a small number of spatially clustered sets of voxels that are particularly suited for clinical interpretation. RVoxM automatically tunes all its free parameters during the training phase, and offers the additional advantage of producing probabilistic prediction outcomes. Experiments on age prediction from structural brain MRI indicate that RVoxM yields biologically meaningful models that provide excellent predictive accuracy.

KW - MRI

KW - Multivariate Pattern Analysis

U2 - 10.1007/978-3-642-23626-6_13

DO - 10.1007/978-3-642-23626-6_13

M3 - Article in proceedings

SN - 978-3-642-23625-9

VL - 3

T3 - Lecture Notes in Computer Science

SP - 99

EP - 106

BT - Medical Image Computing and Computer-Assisted Intervention –MICCAI2011

PB - Springer

T2 - 14th International Conference on Medical Image Computing and Computer-Assisted Intervention

Y2 - 18 September 2011 through 22 September 2011

ER -

Sabuncu MR, Van Leemput K. The Relevance Voxel Machine (RVoxM): A Bayesian Method for Image-Based Prediction. In Medical Image Computing and Computer-Assisted Intervention –MICCAI2011: 14th International Conference Toronto, Canada, September 18-22, 2011 Proceedings. Vol. 3. Springer. 2011. p. 99-106. (Lecture Notes in Computer Science; No. 6893). doi: 10.1007/978-3-642-23626-6_13

The Relevance Voxel Machine (RVoxM): A Bayesian Method for Image-Based Prediction

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this