Abstract: There is provided a method for quantifying texture features in histological sample from a tumor sample, comprising: receiving a digital image of the histological sample, then dividing the digital image into a plurality of sub-areas, then using a trained machine learning model to predict a presence of at least one biological feature for each of the sub-areas, where a probability for the presence of the biological feature is represented by a value, then forming a data matrix by arranging the values for the probabilities of the biological features in the same way as the sub-areas are arranged in relation to the digital image, then applying image analysis to the data matrix for a set of texture features, to produce a quantification of at least one texture feature.

Abstract: There is provided a method comprising determining cancer progression risk for a cancer patient by providing a digital image to a trained neural network and allowing the trained neural network to predict cancer progression risk for the patient based on that image, where the neural network has been trained by receiving a training dataset comprising digital images of histology samples from cancer patients where each histology sample is associated in the dataset with one histology grade score selected from a set comprising three histology grade scores: a first histology grade score indicating low risk for progression of the cancer disease, a second histology grade score indicating intermediate risk for progression of the cancer disease and a third histology grade score indicating high risk for progression of the cancer disease, using the digital images of histology samples associated with the first and third histology grade scores, while ignoring digital images associated with the second histology grade score,

Abstract: This invention pertains generally to the field of multivariate statistics, and in particular to new methods for the analysis (e.g., chemometrics) of chemical, biochemical, and biological data, including, for example, spectral data, including but not limited to nuclear magnetic resonance (NMR) spectral data. These methods are useful, for example, in metabonomics, proteomics, transcriptomics, genomics, etc., and form a part of other methods, for example, methods for the identification of chemical species, methods for the identification of biomarkers that are useful in methods of classification, diagnosis, prognosis, etc.

Abstract: This invention pertains generally to the field of multivariate statistics, and in particular to new methods for the analysis (e.g., chemometrics) of chemical, biochemical, and biological data, including, for example, spectral data, including but not limited to nuclear magnetic resonance (NMR) spectral data. These methods are useful, for example, in metabonomics, proteomics, transcriptomics, genomics, etc., and form a part of other methods, for example, methods for the identification of chemical species, methods for the identification of biomarkers that are useful in methods of classification, diagnosis, prognosis, etc.