Automatic segmentation of data derived from learned features of a predictive statistical model

A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a processor of a data processing system, causes the data processing system to implement a statistical model tool for providing insight into decision making, wherein the computer readable program causes the data processing system to:

• apply, by the statistical model tool, a statistical model to an input image to generate an original classification probability for the input image, wherein the original classification probability represents a probability that the input image belongs to a given classification;
• generate, by a distance map generator executing within the statistical model tool, a distance map data structure, wherein the distance map data structure comprises for each given portion of the input image a probability distance that represents an amount that a change in the given portion of the input image impacts the original classification probability determined by the statistical model;
• perform, by a grouping component executing within the statistical model tool, a grouping operation on the probability distances in the distance map data structure to generate at least one group of portions of the image having similar probability distances;
• mark, by a contour marking component executing within the statistical model tool, contours of the at least one group of portions of the image to form a contour marked image;
• and
• output, by the contour marking component, the contour marked image to a user.

An apparatus comprising:

• a processor;
• and
• a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to implement a statistical model tool for providing insight into decision making, wherein the instructions cause the processor to:
• apply, by the statistical model tool, a statistical model to an input image to generate an original classification probability for the input image wherein the original classification probability represents a probability that the input image belongs to a given classification;
• generate, by a distance map generator executing within the statistical model tool, a distance map data structure, wherein the distance map data structure comprises for each given portion of the input image a probability distance that represents an amount that a change in the given portion of the input image impacts the original classification probability determined by the statistical model;
• perform, by a grouping component executing within the statistical model tool, a grouping operation on the probability distances in the distance map data structure to generate at least one group of portions of the image having similar probability distances;
• mark, by a contour marking component executing within the statistical model tool, contours of the at least one group of portions of the image to form a contour marked image;
• and
• output, by the contour marking component, the contour marked image to a user.