Segmentação de placas de esclerose múltipla em imagens de ressonância magnética usando modelos de mistura de distribuições t-Student e detecção de outliers
Ano de defesa: | 2016 |
---|---|
Autor(a) principal: | |
Orientador(a): | |
Banca de defesa: | |
Tipo de documento: | Dissertação |
Tipo de acesso: | Acesso aberto |
Idioma: | por |
Instituição de defesa: |
Universidade Federal de São Carlos
Câmpus São Carlos |
Programa de Pós-Graduação: |
Programa de Pós-Graduação em Ciência da Computação - PPGCC
|
Departamento: |
Não Informado pela instituição
|
País: |
Não Informado pela instituição
|
Palavras-chave em Português: | |
Palavras-chave em Inglês: | |
Área do conhecimento CNPq: | |
Link de acesso: | https://repositorio.ufscar.br/handle/20.500.14289/7736 |
Resumo: | Multiple Sclerosis (MS) is an inflammatory demyelinating (that is, with myelin loss) disease of the Central Nervous System (CNS). It is considered an autoimmune disease in which the immune system wrongly recognizes the myelin sheath of the CNS as an external element and attacks it, resulting in inflammation and scarring (sclerosis) of multiple areas of CNS’s white matter. Multi-contrast magnetic resonance imaging (MRI) has been successfully used in diagnosing and monitoring MS due to its excellent properties such as high resolution and good differentiation between soft tissues. Nowadays, the preferred method to segment MS lesions is the manual segmentation, which is done by specialists with limited help of a computer. However, this approach is tiresome, expensive and prone to error due to inter- and intra-variability between observers caused by low contrast on lesion edges. The challenge in automatic detection and segmentation of MS lesions in MR images is related to the variability of size and location of lesions, low contrast due to partial volume effect and the high range of forms that lesions can take depending on the stage of the disease. Recently, many researchers have turned their efforts into developing techniques that aim to accurately measure volumes of brain tissues and MS lesions, and also to reduce the amount of time spent on image analysis. In this context, this project proposes the study and development of an automatic computational technique based on an outlier detection approach, Student’s t-distribution finite mixture models and probabilistic atlases to segment and measure MS lesions volumes in MR images. |