Computational pathology approach for retrospective analysis of tissue-based companion diagnostic driven clinical trial studies

A system comprising:

• a processing system;
• and
• a computer-readable medium storing instructions which, when executed by the processing system, cause the system to perform operations comprising:
• calculating a first correlation matrix based on first tissue feature data for a first patient population, the first tissue feature data generated based on a first feature metric calculated from a plurality of first images of a plurality of first biological samples derived from the first patient population;
• calculating a second correlation matrix based on second tissue feature data for a second patient population, the second tissue feature data generated based on a second feature metric calculated from a plurality of second images of a plurality of second biological samples derived from the second patient population;
• and
• determining, based on a comparison of the first correlation matrix and second correlation matrix, that the first tissue feature data is similar to the second tissue feature data.

A non-transitory computer-readable medium storing computer-readable instructions that, when executed by a processing system, cause a system to perform operations comprising:

• calculating a first correlation matrix based on first tissue feature data for a first patient population, the first tissue feature data generated based on a first feature metric calculated from a plurality of first images of a plurality of first biological samples derived from the first patient population;
• calculating a second correlation matrix based on second tissue feature data for a second patient population, the second tissue feature data generated based on a second feature metric calculated from a plurality of second images of a plurality of second biological samples derived from the second patient population;
• and
• determining, based on a comparison of the first correlation matrix and second correlation matrix, that the first tissue feature data is similar to the second tissue feature data.