Coarse label refinement for improving prostate cancer detection in ultrasound imaging

Minh Nguyen Nhat To, Fahimeh Fooladgar, Golara Javadi, Sharareh Bayat, Samira Sojoudi, Antonio Hurtado, Silvia D. Chang, Peter C. Black, Parvin Mousavi, Purang Abolmaesumi

Abstract: Ultrasound-guided biopsy plays a major role in prostate cancer (PCa) detection, yet is limited by a high rate of false negatives and low diagnostic yield of the current systematic, non-targeted approaches. Developing machine learning models for accurately identifying cancerous tissue in ultrasound would help sample tissues from regions with higher cancer likelihood. A plausible approach for this purpose is to use individual ultrasound signals corresponding to a core as inputs and consider the histopathology diagnosis for the entire core as labels. However, this introduces significant amount of label noise to training and degrades the classification performance. Previously, we suggested that histopathology-reported cancer involvement can be a reasonable approximation for the label noise.