An automatic method to segment colonic polyps from CT colonography is presented. The method is based on a combination of knowledge-guided intensity adjustment, fuzzy c-mean clustering, and deformable models. The input is a set of polyp seed points generated by filters on geometric properties of the colon surface. First, the potential polyp region is enhanced by a knowledge-guided adjustment. Then, a fuzzy c-mean clustering is applied on a 64*64 pixel sub-image around the seed. Fuzzy membership functions for lumen air, polyp tissues and other tissues are computed for each pixel. Finally, the gradient of the fuzzy membership function is used as the image force to drive a deformable model to the polyp boundary. The segmentation process is first executed on the 2D transverse slice where the polyp seed is located, and then is propagated to neighboring slices to construct a 3D representation of the polyp. Manual segmentation is performed on the same polyps and treated as the ground truth. The automatically generated segmentation is compared with the ground truth segmentation to validate the accuracy of the method. Experimental results showed that the average overlap between the automatic segmentation and manual segmentation is 76.3%. Given the complex polyp boundaries and the small size of the polyp, this is a good result both visually and quantitatively.
For cancer polyp detection based on CT colonography we investigate the sample variance of two methods for estimating the sensitivity and specificity. The goal is the reduction of sample variance for both error estimates, as a first step towards comparison with other detection schemes. Our detection scheme is based on a committee of support vector machines. The two estimates of sensitivity and specificity studied here are a smoothed bootstrap (the 632+ estimator), and ten-fold cross-validation. It is shown that the 632+ estimator generally has lower sample variance than the usual cross-validation estimator. When the number of nonpolyps in the training set is relatively small we obtain approximately 80% sensitivity and 50% specificity (for either method). On the other hand, when the number of nonpolyps in the training set is relatively large, estimated sensitivity (for either method) drops considerably. Finally, we consider the intertwined roles of relative sample sizes (polyp/nonpolyp), misclassification costs, and bias-variance reduction.
To improve computer aided diagnosis (CAD) for CT colonography we designed a hybrid classification scheme that uses a committee of support vector machines (SVMs) combined with a genetic algorithm (GA) for variable selection. The genetic algorithm selects subsets of four features, which are later combined to form a committee, with majority vote for classification across the base classifiers. Cross validation was used to predict the accuracy (sensitivity, specificity, and combined accuracy) of each base classifier SVM. As a comparison for GA, we analyzed a popular approach to feature selection called forward stepwise search (FSS). We conclude that genetic algorithms are effective in comparison to the forward search procedure when used in conjunction with a committee of support vector machine classifiers for the purpose of colonic polyp identification.