Dyslexia diagnostics by 3D texture analysis of cerebral white matter gyrifications

摘要: The importance of accurate early diagnostics dyslexia that severely affects the learning abilities children cannot be overstated. Neuropathological studies have revealed an abnormal anatomy cerebral white matter (CWM) in dyslexic brains. We explore a possibility distinguishing between and normal (control) brains by quantitative shape analysis CWM gyrifications on 3D Magnetic Resonance (MR) images. Our approach consists (i) segmentation brain image using deformable boundary; (ii) extraction from segmented CWM, (iii) to quantify thickness extracted classify subjects. boundary evolution is controlled two probabilistic models visual appearance CWM: learned prior current model. Initial experimental results suggest proposed texture promising supplement techniques for diagnosing dyslexia.