Knowledge-driven automated extraction of the human cerebral ventricular system from MR images.

This work presents an efficient and automated method to extract the human cerebral ventricular system from MRI driven by anatomic knowledge. The ventricular system is divided into six three-dimensional regions; six ROIs are defined based on the anatomy and literature studies regarding variability of the cerebral ventricular system. The distribution histogram of radiological properties is calculated in each ROI, and the intensity thresholds for extracting each region are automatically determined. Intensity inhomogeneities are accounted for by adjusting intensity threshold to match local situation. The extracting method is based on region-growing and anatomical knowledge, and is designed to include all ventricular parts, even if they appear unconnected on the image. The ventricle extraction method was implemented on the Window platform using C++, and was validated qualitatively on 30 MRI studies with variable parameters.