Based on the present investigation of the Medical Imaging Based Computer Aided Diagnosis (MICAD), main methods of the imaging analysis and process technologies used in MICAD are discussed in this paper. As an example, the imaging segmentation for MICAD is introduced in little more detail for the k-Nearest Neighbor (KNN) and Fuzzy k-Nearest Neighbor (FKNN) methods. The idea how to increase the segmentation accuracy was presented, and the mixture-based segmentation maybe a solution. Accurate segmentation is an important technology for the computer automatic pattern recognition, which inversely as the main fundamental role in intelligent MICAD.
Segmentation for brain tissue becomes more and more important in clinical diagnosis and treatment for dis-eases as well as for basic research such as for virtual human subjects. In this paper, pattern recognition methods wereused to perform the segmentation for Multi-Spectral MR images. The k Nearest Neighbor (kNN) and the Fuzzy NearestPrototype (FNP) algorithms[1]were adopted. Combination of the consideration on the feature of MR image and the anatomicknowledge, a set of neighborhood rules were established. Generally, kNN and FNP algorithms classify the samples intheir state space, ignoring the information between pixels in the image. The neighborhood rules were added to deter-mine the uncertain results after state space classification. The result from the segmentation was obviously better thenthat from previous kNN or FNP algorithm.