Neural network analysis of DNA flow cytometry histograms

Open Access
Publisher Website
Google Scholar
Abstract
A pattern recognition system based on Neural Network Analysis, a form of artificial intelligence, was used to search DNA flow cytometry histograms for features that correlated with breast cancer patients' risk of relapse. DNA flow cytometry histograms and clinical followup information from 796 breast cancer patients were used to train a Neural Network to predict the clinical outcome of patients in a separate independent set of 794 patients. Median follow-up in this patient data base was short, 23 months. Neural Network Analysis resulted in a model that evaluated DNA flow cytometry histograms differently than conventional analysis, which categorizes the histograms by ploidy and S-phase fraction. Neural Network Analysis appeared to identify low risk and high risk subsets of patients as accurately as conventional analysis. Neural Network Analysis placed heavy emphasis on the region to the right of the diploid G2/M peak, where a subpopulation of nuclei with high DNA content is seen even in many histograms scored as diploid by conventional techniques. The number of nuclei in this region was found to be a powerful predictor of patient outcome, and multivariate analysis showed that the number of nuclei in this region and the S-phase fraction both were independently predictive of relapse. This pilot study suggests that conventional analysis (based on a mechanistic interpretation of regions in flow cytometry histograms) might be used in conjunction with and improved by pattern recognition systems or insights derived from them.