Classification of prostatic biopsy
Shao-Kuo Tai, Chengyi Li, Yen-Chih Wu, Yee‐Jee Jan, Shu‐Chuan Lin · 6th International Conference on Digital Content, Multimedia Technology and its Applications · 2010
Prostatic biopsies provide the information for the determined diagnosis of prostatic cancer. Computer-aid investigation of biopsies can reduce the loading of pathologists and also inter- and intra-observer variability as well. In this paper, we proposed a novel method to classify prostatic biopsies according to the Gleason Grading System. This method analyzes the fractal dimension of sub-bands derived from the images of prostatic biopsies. In the experiments, we adopted Support vector machine as the classifier and the leave-one-out approach to estimate error rate. The present experimental results demonstrated that 86.3% of accuracy for a set of 1000 pathological images. These images are randomly selected from 50 cases which were prepared within last five years.