Etiology-based classification of brain white matter hyperintensity on magnetic resonance imaging

Autor(es)

Leite, Mariana ^[1] ; Rittner, Leticia ^[1] ; Appenzeller, Simone ^[2] ; Ruocco, Heloisa Helena ^[3] ; Lotufo, Roberto ^[1]

Afiliação do(s) autor(es)

^[1] Univ Estadual Campinas, Dept Comp Engn & Ind Automat, Fac Elect & Comp Engn, Albert Einstein Ave, BR-13083852 Campinas, SP - Brazil

^[2] Univ Estadual Campinas, Fac Med Sci, Div Rheumatol, BR-13083970 Campinas, SP - Brazil

^[3] CHospital Fac Med Jundiai, Multiple Sclerosis Ctr, BR-13202550 Jundia - Brazil

• Tipo de documento: Artigo Científico
• Fonte: JOURNAL OF MEDICAL IMAGING; v. 2, n. 1 JAN-MAR 2015.
• Citações Web of Science: 9

Resumo

Brain white matter lesions found upon magnetic resonance imaging are often observed in psychiatric or neurological patients. Individuals with these lesions present a more significant cognitive impairment when compared with individuals without them. We propose a computerized method to distinguish tissue containing white matter lesions of different etiologies (e.g., demyelinating or ischemic) using texture-based classifiers. Texture attributes were extracted from manually selected regions of interest and used to train and test supervised classifiers. Experiments were conducted to evaluate texture attribute discrimination and classifiers' performances. The most discriminating texture attributes were obtained from the gray-level histogram and from the co-occurrence matrix. The best classifier was the support vector machine, which achieved an accuracy of 87.9% in distinguishing lesions with different etiologies and an accuracy of 99.29% in distinguishing normal white matter from white matter lesions. (c) 2015 Society of Photo-Optical Instrumentation Engineers (SPIE) (AU)

• Processo FAPESP: 13/07559-3 - Instituto Brasileiro de Neurociência e Neurotecnologia - BRAINN
• Beneficiário: Fernando Cendes
• Linha de fomento: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs
• Processo FAPESP: 12/21826-1 - Identificação semi-automática e caracterização de lesões de substância branca no cérebro em imagens volumétricas de ressonância magnética
• Beneficiário: Mariana Pinheiro Bento Leite
• Linha de fomento: Bolsas no Brasil - Doutorado