System and method for structures detection and multi-class image categorization in medical imaging

A system for categorizing clinical or biological images, comprising:

• at least one device for receiving a plurality of biological images depicting one or more structures and a family of multi-resolution, multi-orientation geometric templates that is made translation, orientation and/or scaling invariant by computing correlation at selected pixels within the images;
• at least one computing device;
• and
• an application executable in the at least one computing device, the application comprising logic that:
• a) uses the family of multi-resolution, multi-orientation geometric templates by computing correlation with the templates at the selected pixels within the images;
• b) detects the one or more structures within the images based on the computed correlation;
• and
• c) categorizes the biological or medical images by the one or more structures detected.

A non-transitory computer readable medium employing a program executable in at least one computing device, comprising code that:

• a) receives a plurality of the biological or medical images depicting one or more structures and a family of multi-resolution, multi-orientation geometric templates that is made translation, orientation and/or scaling invariant;
• b) uses the family of multi-resolution, multi-orientation geometric templates by computing correlation with the templates at the selected pixels within the images;
• c) detects the one or more structures within the images based on the computed correlation;
• and
• d) categorizes the biological or medical images by the one or more structures detected.