Back close

IMaGe: Iterative Multilevel Probabilistic Graphical Model for Detection and Segmentation of Multiple Sclerosis Lesions in Brain MRI

Publication Type : Conference Paper

Thematic Areas : Wireless Network and Application

Publisher : Proceedings of Information Processing for Medical Imaging (IPMI) .

Source : Proceedings of Information Processing for Medical Imaging (IPMI), 2015. (Acceptance Rate in IPMI 2015: 31%)

Url : https://pubmed.ncbi.nlm.nih.gov/26221699/

Campus : Amritapuri

School : School of Engineering

Center : Amrita Center for Wireless Networks and Applications (AmritaWNA)

Department : Wireless Networks and Applications (AWNA)

Year : 2015

Abstract : In this paper, we present IMaGe, a new, iterative two-stage probabilistic graphical model for detection and segmentation of Multiple Sclerosis (MS) lesions. Our model includes two levels of Markov Random Fields (MRFs). At the bottom level, a regular grid voxel-based MRF identifies potential lesion voxels, as well as other tissue classes, using local and neighbourhood intensities and class priors. Contiguous voxels of a particular tissue type are grouped into regions. A higher, non-lattice MRF is then constructed, in which each node corresponds to a region, and edges are defined based on neighbourhood relationships between regions. The goal of this MRF is to evaluate the probability of candidate lesions, based on group intensity, texture and neighbouring regions. The inferred information is then propagated to the voxel-level MRF. This process of iterative inference between the two levels repeats as long as desired. The iterations suppress false positives and refine lesion boundaries. The framework is trained on 660 MRI volumes of MS patients enrolled in clinical trials from 174 different centres, and tested on a separate multi-centre clinical trial data set with 535 MRI volumes. All data consists of T1, T2, PD and FLAIR contrasts. In comparison to other MRF methods, such as, and a traditional MRF, IMaGe is much more sensitive (with slightly better PPV). It outperforms its nearest competitor by around 20% when detecting very small lesions (3-10 voxels). This is a significant result, as such lesions constitute around 40% of the total number of lesions.

Cite this Research Publication : N.K. Subbanna, D. Precup, D.L. Arnold, and T. Arbel, “IMaGE: Iterative Multilevel Probabilistic Graphical Model for Detection and Segmentation of Multiple Sclerosis Lesions in Brain MRI”, in Proceedings of Information Processing for Medical Imaging (IPMI), 2015. (Acceptance Rate in IPMI 2015: 31%) DOI: 10.1007/978-3-319-19992-4_40

Admissions Apply Now