Brain Tumor Segmentation Using a Generative Model with an RBM Prior on Tumor Shape

Mikael Agn, Oula Puonti, Per Munck af Rosenschöld, Ian Law, Koen Van Leemput

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

Abstract

In this paper, we present a fully automated generative method for brain tumor segmentation in multi-modal magnetic resonance images. The method is based on the type of generative model often used for segmenting healthy brain tissues, where tissues are modeled by Gaussian mixture models combined with a spatial atlas-based tissue prior. We extend this basic model with a tumor prior, which uses convolutional restricted Boltzmann machines (cRBMs) to model the shape of both tumor core and complete tumor, which includes edema and core. The cRBMs are trained on expert segmentations of training images, without the use of the intensity information in the training images. Experiments on public benchmark data of patients suffering from low- and high-grade gliomas show that the method performs well compared to current state-of-the-art methods, while not being tied to any specific imaging protocol.
Original languageEnglish
Title of host publication1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015) : Revised Selected Papers
PublisherSpringer
Publication date2016
Pages168-180
ISBN (Print)978-3-319-30857-9
ISBN (Electronic)978-3-319-30858-6
DOIs
Publication statusPublished - 2016
Event1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015) - Munich, Germany
Duration: 5 Oct 20155 Oct 2015
Conference number: 1

Workshop

Workshop1st International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Brainles 2015)
Number1
CountryGermany
CityMunich
Period05/10/201505/10/2015
OtherHeld in Conjunction with MICCAI 2015
SeriesLecture Notes in Computer Science
Volume9556
ISSN0302-9743

Fingerprint Dive into the research topics of 'Brain Tumor Segmentation Using a Generative Model with an RBM Prior on Tumor Shape'. Together they form a unique fingerprint.

Cite this