Adaptive Dictionary Learning For Competitive Classification Of Multiple Sclerosis Lesions

Hrishikesh Deshpande 1 Pierre Maurel 1 Christian Barillot 1
1 VisAGeS - Vision, Action et Gestion d'informations en Santé
INSERM - Institut National de la Santé et de la Recherche Médicale : U746, Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : Sparse representations allow modeling data using a few basis elements of an over-complete dictionary and have been used in many image processing applications. We propose to use a sparse representation and an adaptive dictionary learning paradigm to automatically classify Multiple Sclerosis (MS) lesions from MRI. In particular, we investigate the effects of learning dictionaries specific to the lesions and individual healthy brain tissues, which include White Matter (WM), Gray Matter (GM) and Cerebrospinal Fluid (CSF). The dictionary size plays a major role in data representation but it is an even more crucial element in the case of competitive classification. We present an approach that adapts the size of the dictionary for each class, depending on the complexity of the underlying data. The proposed algorithm is evaluated on clinical data demonstrating improved classification.
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-01121110
Contributor : Pierre Maurel <>
Submitted on : Friday, February 27, 2015 - 2:25:59 PM
Last modification on : Monday, March 4, 2019 - 2:07:40 PM
Long-term archiving on : Thursday, May 28, 2015 - 10:21:16 AM

File

ISBI15_0473_MS_ISBI3.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01121110, version 1

Citation

Hrishikesh Deshpande, Pierre Maurel, Christian Barillot. Adaptive Dictionary Learning For Competitive Classification Of Multiple Sclerosis Lesions. International Symposium on BIOMEDICAL IMAGING: From Nano to Macro, Apr 2015, New-York, United States. ⟨hal-01121110⟩

Share

Metrics

Record views

1232

Files downloads

355