Probabilistic One Class Learning for Automatic Detection of Multiple Sclerosis Lesions - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

Probabilistic One Class Learning for Automatic Detection of Multiple Sclerosis Lesions

(1) , (1) , (1)
1

Abstract

This paper presents an automatic algorithm for the detec- tion of multiple sclerosis lesions (MSL) from multi-sequence magnetic resonance imaging (MRI). We build a probabilistic classifier that can recognize MSL as a novel class, trained only on Normal Appearing Brain Tissues (NABT). Patch based intensity information of MRI images is used to train a classifier at the voxel level. The classifier is in turn used to compute a probability characterizing the likelihood of each voxel to be a lesion. This probability is then used to identify a lesion voxel based on simple Otsu thresholding. The pro- posed framework is evaluated on 16 patients and our analysis reveals that our approach is well suited for MSL detection and outperforms other benchmark approaches.
Fichier principal
Vignette du fichier
Yogesh_ISBI_Camera_Ready.pdf (635.34 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inserm-01127690 , version 1 (06-05-2015)

Identifiers

  • HAL Id : inserm-01127690 , version 1

Cite

Yogesh Karpate, Olivier Commowick, Christian Barillot. Probabilistic One Class Learning for Automatic Detection of Multiple Sclerosis Lesions. IEEE International Symposium on Biomedical Imaging (ISBI), Apr 2015, Brooklyn, United States. pp.486-489. ⟨inserm-01127690⟩
204 View
674 Download

Share

Gmail Facebook Twitter LinkedIn More