Characterizing lesions in radiology images

An apparatus for use in characterizing lesions in radiology images, comprising:

• an analyzing unit for performing a computer-based analysis comprising one or more of:
• advanced image analytics, machine learning, or artificial intelligence of a pathology image of a sample of a lesion of a subject in order to recognize tissue and/or cellular characteristics of the lesion, wherein the analysis produces a derived pathology image that representative of the recognized tissue and/or cellular characteristics,
• a co-registering unit for co-registering a radiology image of the lesion and the derived pathology image;
• a computing unit for computing one or more radiology features for the radiology image of the lesion,
• a determining unit for determining correlations between the computed one or more radiology features and recognized tissue and/or cellular characteristics in the derived pathology image;
• and.
• a characterization unit for characterizing the lesion in the radiology image based on at least a subset of the one or more computed radiology features and the corresponding determined correlations.

A non-transitory computer readable medium storing instructions for use in characterizing lesions in radiology images that, when executed by one or more processors, cause the one or more processors to:

• perform a computer-based analysis comprising one or more of:
• advanced image analytics, machine learning, or artificial intelligence of a pathology image of a sample of a lesion of a subject in order to recognize tissue and/or cellular characteristics of the lesion, wherein the analysis produces a derived pathology image representative of the recognized tissue and/or cellular characteristics, co-registering a radiology image of the lesion and the derived pathology image;
• compute one or more radiology features for the radiology image of the lesion;
• determine correlations between the computed one or more radiology features and recognized tissue and/or cellular characteristics in the derived pathology image;
• and
• characterize the lesion in the radiology image based on at least a subset of the one or more computed radiology features and the corresponding determined correlations.