An Improved Optimization Method for the Relevance Voxel Machine

Melanie Ganz, M. R. Sabuncu, Koen Van Leemput

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

In this paper, we will re-visit the Relevance Voxel Machine (RVoxM), a recently developed sparse Bayesian framework used for predicting biological markers, e.g., presence of disease, from high-dimensional image data, e.g., brain MRI volumes. The proposed improvement, called IRVoxM, mitigates the shortcomings of the greedy optimization scheme of the original RVoxM algorithm by exploiting the form of the marginal likelihood function. In addition, it allows voxels to be added and deleted from the model during the optimization. In our experiments we show that IRVoxM outperforms RVoxM on synthetic data, achieving a better training cost and test root mean square error while yielding sparser models. We further evaluated IRVoxM’s performance on real brain MRI scans from the OASIS data set, and observed the same behavior - IRVoxM retains good prediction performance while yielding much sparser models than RVoxM.
Original languageEnglish
Title of host publicationMachine Learning in Medical Imaging : 4th International Workshop, MLMI 2013, Held in Conjunction with MICCAI 2013, Nagoya, Japan, September 22, 2013. Proceedings
PublisherSpringer
Publication date2013
Pages147-154
ISBN (Print)978-3-319-02266-6
ISBN (Electronic)978-3-319-02267-3
DOIs
Publication statusPublished - 2013
Event16th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2013) : 4th International Workshop on Machine Learning in Medical Imaging (MLMI 2013) - Nagoya, Japan
Duration: 22 Sep 2013 → …
http://www.miccai2013.org/

Conference

Conference16th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2013) : 4th International Workshop on Machine Learning in Medical Imaging (MLMI 2013)
CountryJapan
CityNagoya
Period22/09/2013 → …
Internet address
SeriesLecture Notes in Computer Science
Volume8184
ISSN0302-9743

Fingerprint Dive into the research topics of 'An Improved Optimization Method for the Relevance Voxel Machine'. Together they form a unique fingerprint.

Cite this