An image-based analysis for classifying multimodal brain images in the Image-guided Medical Diagnosis Model

Classifying images into meaningful categories according to its imaging modalities is beginning to play an increasingly important role in providing a foundation on which to build the next generation of the medical database management system. Since medical images often represent some form of diagnosis capabilities, the ability to follow-up and classify these images to support doctor´s diagnosis, treatment, and prescription is becoming a pressing issue. This paper proposed to introduce a method for classifying input images in association to their diseases and diagnosis. We studied the connection between disease and its tumor image properties in three different image perspectives: binary image, intensity image and selected-pixel intensity image. Binary and intensity image slice profiling are based on texture and shape-based classification technique while selected-pixel intensity image slice profiling is based on content-based classification technique. In this study, we looked at whether gender and age has played any role during input images slice profiling of both healthy and cancer patients. Experimental results reveal our algorithms suitability in classifying input images using the pixel-based approach for multimodal image datasets.