Mapping of breast arterial calcifications

A system, comprising:

• an imaging device;
• and
• a computing device in communication with the imaging device, the computing device including a processor and a memory, the memory bearing computer executable code configured to perform the steps of:
• receiving a first image of a breast of a patient obtained during a mammogram;
• removing noise from the first image thereby creating a de-noised image;
• creating a search unit for searching the de-noised image, the search unit comprises predefined angular regions in a circle having a predefined radius;
• creating one or more search points on the de-noised image, the one or more search points comprise one or more local maxima in brightness in the breast;
• interpolating, for each search unit associated with a search point, pixel intensity from the de-noised image onto the search unit;
• computing one or more points of interest on the de-noised image based on the interpolation;
• creating one or more mesoscale regions of interest on the de-noised image;
• computing a connectivity for each of the one or more mesoscale regions of interest,
• identifying one or more connected components using the computed connectivity, wherein each connected component represents a branch of a global curvilinear structure;
• selecting a set of branches based on the computed physical properties for each branch of the global curvilinear structure;
• pruning each branch in the selected set of branches based on an error-tolerant, adaptive polynomial fit;
• identifying remaining regions of interest in each pruned branch;
• and
• growing a chain formed by remaining points of interest included in the remaining regions of interest, wherein the chain represents a macroscopic, global curvilinear calcified arterial structure.

A computer program product comprising computer executable code embodied in a non-transitory computer readable medium that, when executing on one or more computing devices, performs the steps of:

• receiving a first image of a breast of a patient obtained during a mammogram;
• removing noise from the first image thereby creating a de-noised image;
• creating a search unit for searching the de-noised image, the search unit comprises predefined angular regions in a circle having a predefined radius;
• creating one or more search points on the de-noised image, the one or more search points comprise one or more local maxima in brightness in the breast;
• interpolating, for each search unit associated with a search point, pixel intensity from the de-noised image onto the search unit;
• computing one or more points of interest on the de-noised image based on the interpolation;
• creating one or more mesoscale regions of interest on the de-noised image;
• computing a connectivity for each of the one or more mesoscale regions of interest, identifying one or more connected components using the computed connectivity, wherein each connected component represents a branch of a global curvilinear structure;
• selecting a set of branches based on the computed physical properties for each branch of the global curvilinear structure;
• pruning each branch in the selected set of branches based on an error-tolerant, adaptive polynomial fit;
• identifying remaining regions of interest in each pruned branch;
• and
• growing a chain formed by remaining points of interest included in the remaining regions of interest, wherein the chain represents a macroscopic, global curvilinear calcified arterial structure.