Automated localization and quantification of protein multiplexes via multispectral fluorescence imaging

We present a new system for automated localization and quantification of the expression of protein biomarkers in immunofluorescence (IF) microscopic images. The system includes a novel method for discriminating the biomarker signal from background, where signal may be the expression of any of the many biomarkers or counterstains used in IF. The method is based on supervised learning and represents the biomarker intensity threshold as a function of image background characteristics. The utility of the proposed system is demonstrated in predicting prostate cancer recurrence in patients undergoing prostatectomy. Specifically, features representing androgen receptor (AR) expression are shown to be statistically significantly associated with poor outcome in univariate analysis. AR features are also shown to be valuable for multivariate recurrence prediction.