Computer-aided Detection For Virtual Colonoscopy Based On Texture Analysis

As a new technique, computer-aided detection (CAD) for virtual colonoscopy (VC) utilizes the difference in morphology and other features between polyps and normal tissues to detect colonic polyps automatically. Compared with physicians'performance using VC directly, CAD-based system can provide objective and consistent results, facilitate interpretation process, and be anticipated a promising mass screening for colorectal cancer in clinics. With the development of VC in past several years, many CAD schemes based on morphological features have been studied and a relatively high sensitivity has been achieved for polyp detection. However, geometry-based CAD may cause many false positives in detection results because the densities of the CT image voxels inside a polyp differ only subtly from those of the surrounding tissues and the shape of the colon surface contains a variety of structures that can mimic polyp shapes. Besides geometric features,a polyp also has different texture distribution patterns from normal colon tissues and other things in colon, such as stool. To lower false negatives rate, a 3D geometric/texture-base CAD for VC is proposed in this paper. The geometric and texture features are all utilized. Geometric features i.e., curvedness(CV) and shape index (SI) are employed for extracting the suspicious patch. A 3DeROI model was established via finding inner/outer border of each suspicious patch. Then two traditional texture analyses were performed to extract 3D texture information from each candidate with 3DeROI model. i.e., grey level cooccurrence matrix (GLCM) and grey level-gradient cooccurrence matrix (GLGCM). And two kinds of classifiers, i.e., the back propagation neural network (BPNN) and the support vector machine (SVM), were used to classify polyps from normal tissues. These two classifiers were trained and tested by 7 patients'CT data acquired at both prone and supine position. Experimental result shows that the CAD method proposed in this paper could detect polyps in colon effectively and eliminate 77.5% false positives.