Classifying Cancer Grades Using Temporal Ultrasound for Transrectal Prostate Biopsy

摘要: We propose a cancer grading approach for transrectal ultrasound-guided prostate biopsy based on analysis of temporal ultrasound signals. Histopathological reports the statistics distribution in core. coarse-to-fine classification approach, similar to histopathology reporting, that uses statistical and deep learning determine aggressive image regions surrounding target. Our consists two steps; first step, we learn high-level latent features maximally differentiate benign from cancerous tissue. In second model grades space features. study with 197 cores 132 subjects, our can effectively separate clinically significant disease low-grade tumors Further, achieve area under curve 0.8 separating tissue large tumors.