AUTOMATIC CLASSIFICATION OF STRUCTURAL MRI FOR DIAGNOSIS OF NEURODEGENERATIVE DISEASES
AUTOMATIC CLASSIFICATION OF STRUCTURAL MRI FOR DIAGNOSIS OF NEURODEGENERATIVE DISEASES
This paper presents an automatic approach which classifies structural Magnetic Resonance images into pathological or healthy controls. A classification model was trained to find the boundaries that allow to separate the study groups. The method uses the deformation values from a set of regions, auto...
| Título de la revista: | Acta Biológica Colombiana |
|---|---|
| Autor principal: | Eduardo Romero |
| Otros autores: | Gloria Diaz; Juan Antonio Hernández-Tamames; Vicente Molina; Norberto Malpica; |
| Palabras clave: | |
| Idioma: | Español |
| Enlace del documento: | http://www.revistas.unal.edu.co/index.php/actabiol/article/view/16701 |
| Tipo de recurso: | Documento de revista |
| Fuente: | Acta Biológica Colombiana; Vol 15, No 3 (Año 2010). |
| Entidad editora: | Universidad Nacional de Colombia |
| Derechos de uso: | Sin permisos preestablecidos |
| Materias: | Ciencias --> Bioquímica y Biología Molecular Ciencias --> Conservación de la Biodiversidad Ciencias --> Biología Ciencias --> Biología Celular Ciencias --> Ecología Ciencias --> Ciencias Ambientales Ciencias --> Biología Evolutiva Ciencias --> Genética Ciencias --> Limnología Ciencias --> Biología Marina y de Agua Dulce Ciencias --> Micología Ciencias --> Ornitología Ciencias --> Paleontología Ciencias --> Parasitología Ciencias --> Botánica Ciencias --> Zoología Ciencias Aplicadas --> Agricultura |
| Resumen: | This paper presents an automatic approach which classifies structural Magnetic Resonance images into pathological or healthy controls. A classification model was trained to find the boundaries that allow to separate the study groups. The method uses the deformation values from a set of regions, automatically identified as relevant, in a process that selects the statistically significant regions of a t-test under the restriction that this significance must be spatially coherent within a neighborhood of 5 voxels. The proposed method was assessed to distinguish healthy controls from schizophrenia patients. Classification results showed accuracy between 74% and 89%, depending on the stage of the disease and number of training samples. |
|---|
