Clinical progression and decision making process in multiple sclerosis

Multi-Sectional Views Textural Based SVM for MS Lesion Segmentation in Multi-Channels MRIs

In this paper, a new technique is proposed for automatic segmentation of multiple sclerosis (MS) lesions from brain magnetic resonance imaging (MRI) data. The technique uses a trained support vector machine (SVM) to discriminate between the blocks in regions of MS lesions and the blocks in non-MS lesion regions mainly based on the textural features with aid of the other features. The classification is done on each of the axial, sagittal and coronal sectional brain view independently and the resultant segmentations are aggregated to provide more accurate output segmentation. The main contribution of the proposed technique described in this paper is the use of textural features to detect MS lesions in a fully automated approach that does not rely on manually delineating the MS lesions. In addition, the technique introduces the concept of the multi-sectional view segmentation to produce verified segmentation. The proposed textural-based SVM technique was evaluated using three simulated datasets and more than fifty real MRI datasets. The results were compared with state of the art methods. The obtained results indicate that the proposed method would be viable for use in clinical practice for the detection of MS lesions in MRI.

Multi-Sectional Views Textural Based SVM for MS Lesion Segmentation in Multi-Channels MRIs

In this paper, a new technique is proposed for automatic segmentation of multiple sclerosis (MS) lesions from brain magnetic resonance imaging (MRI) data. The technique uses a trained support vector machine (SVM) to discriminate between the blocks in regions of MS lesions and the blocks in non-MS lesion regions mainly based on the textural features with aid of the other features. The classification is done on each of the axial, sagittal and coronal sectional brain view independently and the resultant segmentations are aggregated to provide more accurate output segmentation. The main contribution of the proposed technique described in this paper is the use of textural features to detect MS lesions in a fully automated approach that does not rely on manually delineating the MS lesions. In addition, the technique introduces the concept of the multi-sectional view segmentation to produce verified segmentation. The proposed textural-based SVM technique was evaluated using three simulated datasets and more than fifty real MRI datasets. The results were compared with state of the art methods. The obtained results indicate that the proposed method would be viable for use in clinical practice for the detection of MS lesions in MRI.

Identifying disease modifying genes in multiple sclerosis

Evidence is mounting that genetic variation influences not only susceptibility to multiple sclerosis (MS), but also its course and severity. Identification of disease modifying genes, however, poses unique challenges, especially on how to classify the course and outcome of the disease in ways that may be relevant to analysis of biological factors that might be influenced by genes. The power of the statistical approaches to detect small effects of individual genes in complex disorders such as MS is problematic, and approaches to estimate power must be appropriate for the data. Nonetheless, using contemporary schemes of classification, genetic variants that influence disease course have been found; in fact, a small number have been confirmed to influence disease course in two or more independent studies. This review addresses strategies relevant to identification of disease modifying genes in MS, and summarizes and critically evaluates the current state of knowledge in this area.

Multiple sclerosis: report on 200 cases from Curitiba, Southern Brazil and comparison with other Brazilian series

We reviewed the clinical and laboratory findings of 200 patients in Curitiba, Southern Brazil (25 degrees 25'40" S; 49 degrees 16'23" W-GR), with multiple sclerosis (MS)according to Poser's criteria. The patients were classified as: clinically definite (A1 and A2) - 142 patients (71%); laboratory-supported definite - 42 patients (21%); and clinically probable - 16 patients (8%). Relapsing-remitting (RR) form was the most common clinical presentation, with 182 (91%), followed by primary progressive (PP)(16 cases, 8%), and only 2 cases with secondarily progressive form (SP). Nine women and 7 men totalized the 16 PP cases. The mean age of onset was 32.0+/-9.9 (median 32 years). The gender ratio was female 1.8:1 male. All patients, except 3 African-Brazilian, were white. Seven (3.5%) patients developed a clinical history of Devic's syndrome. The initial clinical picture included brainstem/cerebellar syndrome in 126 (63%) cases, sensorial findings in 106 (53%)patients, motor (pyramidal) syndrome in 102 (49.5%), and optic neuritis in 79 (39.5%) cases. 122 (61%) patients had a final EDSS score < 3.5; 45 (22.5%) a score between 3.5 and 5.5, and 33 (16.5%) a score > or = 6.0. There was no significant correlation between the number of relapses or duration of disease with EDSS scores (Spearman's test). Only 14 (7%) of the total number presented the benign form (EDSS< 3.5 after 10 years of disease). We observed a later age of onset and initial clinical findings with higher frequency of brainstem/cerebellar syndrome and optic neuritis, when compared to other Brazilian and Western series