Label-free assessment of biomarker expression by vibrational spectroscopy

Abstract

The present disclosure relates to automated systems and methods for predicting the expression of one or more biomarkers in a sample of a biological specimen. In some embodiments, the sample has an unknown fixation state or the duration of fixation the sample was subjected to is unknown. In some embodiments, the predicted expression is a quantitative estimate of the positivity rate of one or more biomarkers. In other embodiments, the predicted expression is a quantitative estimate of the staining intensity of one or more biomarkers. In some embodiments, the systems and methods utilize a trained biomarker expression estimation engine trained with a plurality of training samples, the trained biomarker expression estimation engine adapted to derive biomarker expression features from the samples. In some embodiments, the trained biomarker expression estimation engine comprises a machine learning algorithm based on projection onto a latent structure regression model. In some embodiments, the trained biomarker expression estimation engine comprises a neural network.