Quantitatively characterizing disease morphology with cell orientation entropy

Abstract

Apparatus, methods, and other embodiments associated with objectively predicting biochemical recurrence (BCR) with cell orientation entropy (COrE) are described. One example apparatus includes a set of logics that associate directional disorder with a risk of biochemical recurrence in a tissue. A first logic detects a cell in the tissue, segments boundaries of the cell, and calculates a cell direction for the cell. A second logic constructs a localized sparsified subgraph whose nodes represent centroids of the cells, defines pairwise spatial relationships between the cells, and constructs a directional co-occurrence matrix based on the spatial relationships. A third logic derives second order statistical features from the co-occurrence matrix, and produces a BCR risk score as a function of the second order statistical features. The second order statistical features include the entropy of the directional organization of the cells.