This paper presents a method for selecting Regions of Interest in brain Magnetic Resonance Imaging for diagnostic purposes, using statistical learning and vector quantization techniques. The proposed method models the distribution of GM and WM tissues grouping the voxels belonging to each tissue in ROIs associated to a specific neurological disorder. Tissue distribution of normal and abnormal images is modelled by a Self-Organizing map, generating a set of representative prototypes, and the rece…
Read moreThis paper presents a method for selecting Regions of Interest in brain Magnetic Resonance Imaging for diagnostic purposes, using statistical learning and vector quantization techniques. The proposed method models the distribution of GM and WM tissues grouping the voxels belonging to each tissue in ROIs associated to a specific neurological disorder. Tissue distribution of normal and abnormal images is modelled by a Self-Organizing map, generating a set of representative prototypes, and the receptive field of each SOM prototype defines a ROI. Moreover, the proposed method computes the relative importance of each ROI by means of its discriminative power. The devised method has been assessed using 818 images from the Alzheimer's disease Neuroimaging Initiative which were previously segmented through Statistical Parametric Mapping. The proposed algorithm was used over these images to parcel ROIs associated to the Alzheimer's Disease. Additionally, this method can be used to extract a reduced set of discriminative features for classification, since it compresses discriminative information contained in the brain. Voxels marked by ROIs which were computed using the proposed method, yield classification results up to 90% of accuracy for controls and Alzheimer's disease patients, and 84% of accuracy for Mild Cognitive Impairment and AD patients.
