Abstract: A method for selecting treatment options for patients is provided. The method comprises a procedure for selecting patients that should not be placed on Active Surveillance (AS) but receive active treatment even though the morphologic analysis of the patient's biopsy may show a Gleason score that would traditionally have placed the patient in AS without any further treatment. In accordance with one embodiment, the patient is selected for active treatment if a biomarker associated with prostate cancer is detected. In yet a further embodiment, the patient is selected for additional treatment if the biomarker's concentration is determined to be higher in the benign section of the tissue sample than in the cancerous section. In another embodiment, biochemical recurrence is predicted identifying patients for treatment.

Abstract: A method for screening individuals at risk for prostate cancer progression is disclosed. The method is useful for evaluating cells from patients at risk for recurrence of prostate cancer following surgery for prostate cancer. Specifically, the method uses specific Markovian nuclear texture factors, alone or in combination with other biomarkers, to determine whether the cancer will progress or lose organ confinement. In addition, methods of predicting the development of fatal metastatic disease by statistical analysis of selected biomarkers is also disclosed. The invention also contemplates a method that uses a neural network to analyze and interpret cell morphology data. Utilizing Markovian factors and other biomarkers as parameters, the network is first trained with a sets of cell data from known progressors and known non-progressors. The trained network is then used to predict prostate cancer progression in patient samples.