Combined Use of Tissue Morphology, Neural Network Analysis of Chromatin Texture & Clinical Variables to Predict Prostate Cancer Agressiveness from Biopsy Material
Abstract
THE PURPOSE OF THIS REPORT IS TO COMBINE CLINICAL, SERUM, PATHOLOGICAL AND COMPUTER DERIVED INFORMATION INTO AN ARTIFICIAL NEURAL NETWORK TO DEVELOP/VALIDATE A MODEL TO PREDICT PROSTATE CANCER TUMOR AGGRESSIVENESS IN BOTH A RETROSPECTIVE AND PROSPECTIVE COHORT OF MEN WITH CLINICALLY LOCALIZED PROSTATE CANCER BOTH PRIOR TO AND AFTER RADICAL PROSTATECTOMY. Prospective enrollment of 500 men who are scheduled to undergo radical prostatectomy (year 01). Development of a artificial neural network model (year 02). Prospective validation of this model (projected year 03). All models will be tested and developed for biopsy and prostatectomy material. To date, we have completed prospective enrollment of 527 men, collected tissue, serum and clinical/pathological information for 387 and completed computer image data analysis of 171 samples. No model has been developed to date and awaits final enrollment. We anticipate final prospective data to be complete and model developed by 1/4/2000. At this time we will begin enrollment of prospective validation samples.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 01, 1999
- Accession Number
- ADA385853
Entities
People
- Alan Partin
Organizations
- Johns Hopkins University