Online Brain Image Database System for Diagnosis of Subtle Brain Injury

Subtle changes in brain tissue that reflect the pathological processes of disorders such as mild cognitive impairment (MCI) are much more difficult to observe on a patient´s magnetic resonance imaging (MRI) scan than those obvious abnormalities such as large strokes or tumors. Thus, it is necessary to develop an automated computer-aided diagnosis (CAD) system which will be more efficient and accurate than the manual and quantitative analysis of functional brain images. In this paper, we present an online human brain image database system with its associated image processing, diagnosis and visualization functions for determination of subtle brain injury. The current system provides the capability of MCI diagnosis which accuracy is 94.1% by using the trained support vector machine (SVM)-based classifier.