Automatic Detection of Irritable Bowel Syndrome for 3D Images Using Supervoxel and Graph Cut Algorithm

Abstract

Medical image processing is a complex exercise and involves a number of stages to identify the disease in the arena of medical imaging. Irritable bowel syndrome is an acute disorder that causes intense abdominal pain and leads to changes in the bowel system. It gives rise to various indications like bleeding, bloating, celiac disease, gastric cancer, ulcer, etc. The system proposed here seeks to segment and classify each symptom of the irritable bowel syndrome individually with the aid of supervoxel segmentation algorithm. Features are extracted depending on the color, shape, and texture of the object. The extracted features are fed into the multi-support vector machine to identify the specific region in the medical image. The experiment provides the result of a test set 100 images stored in the data set which improves accuracy that refines the final output.