||Prostate cancer is the leading cause of cancer in men. The diagnosis and prognosis is based on Gleason grading which is the most widely used system for determining the severity of prostate cancer from tissue samples. However, Gleason grading is highly subjective with significant variation between experienced pathologists. Today about 70% of patients with localized prostate cancer receive aggressive treatment that does not prolong life but often results in debilitating side effects.
The goal of our research is to replace subjective diagnosis of prostate cancer with automatic and objective severity grading based on morphological features that correlate to the disease outcome and that also incorporates other markers for a more accurate prognostication.
In this talk I will describe how prostate cancer is diagnosed and graded today, with particular emphasis on the Gleason grading system, and review our progress to date towards automating the grading process. Please note that I will assume to prior knowledge of cancer grading or image analysis.