Toward digital staining using imaging mass spectrometry and random forests.

摘要: We show on imaging mass spectrometry (IMS) data that the Random Forest classifier can be used for automated tissue classification and it results in predictions with high sensitivities positive predictive values, even when intersample variability is present data. further demonstrate how Markov Fields vector-valued median filtering applied to reduce noise effects improve a posthoc smoothing step. Our study gives clear evidence digital staining by means of IMS constitutes promising complement chemical techniques.