Abstract: Systems and methods are provided for determining the composition of a kidney stone from a medical image. A feature extractor is configured to provide a plurality of features from the medical image. The plurality of features includes either a pair of an attenuation values including a first attenuation value from a first location in or on the kidney stone and a second attenuation value from a second location in or on the kidney stone or a function of the first and second attenuation values. The second location is spatially distinct from the first location. A classifier is configured to select one of a plurality of classes for the kidney stone from the plurality of features. Each class represents a specific constituent material. A user interface is configured to display the class to a user in a human comprehensible form.

Abstract: Systems and methods are provided for determining the composition of a kidney stone from a medical image. A feature extractor is configured to provide a plurality of features from the medical image. The plurality of features includes either a pair of an attenuation values including a first attenuation value from a first location in or on the kidney stone and a second attenuation value from a second location in or on the kidney stone or a function of the first and second attenuation values. The second location is spatially distinct from the first location. A classifier is configured to select one of a plurality of classes for the kidney stone from the plurality of features. Each class represents a specific constituent material.