Automated Prostate Cancer Diagnosis and Gleason Grading of Tissue Microarrays

摘要

We present the results on the development of an automated system for prostate cancer diagnosis and Gleason grading.Images of representative areas of the original Hematoxylin-and-Eosin (H&E)-stained tissue retrieved from each patient,either from a tissue microarray (TMA) core or whole section, were captured and analyzed. The image sets consisted of367 and 268 color images for the diagnosis and Gleason grading problems, respectively. In diagnosis, the goal is toclassify a tissue image into tumor versus non-tumor classes. In Gleason grading, which characterizes tumoraggressiveness, the objective is to classify a tissue image as being from either a low- or high-grade tumor. Severalfeature sets were computed from the image. The feature sets considered were: (i) color channel histograms, (ii) fractaldimension features, (iii) fractal code features, (iv) wavelet features, and (v) color, shape and texture features computedusing Aureon Biosciences' MAGIC™ system. The linear and quadratic Gaussian classifiers together with a greedysearch feature selection algorithm were used. For cancer diagnosis, a classification accuracy of 94.5% was obtained onan independent test set. For Gleason grading, the achieved accuracy of classification into low- and high-grade classes ofan independent test set was 77.6%.