Systems and methods for correlating regions of interest in multiple imaging modalities

A method of locating of a lesion within a breast, the method comprising:

• receiving an indication of a location of a target lesion within at least one first image of the breast obtained by a first imaging modality;
• receiving at least one second image of the breast obtained by a second imaging modality, wherein the first and second imaging modalities are different;
• generating, at an artificial intelligence engine, a virtual deformable model via co-registering the at least one first image and the at least one second image;
• analyzing the virtual deformable model to determine a probability mapping for a potential lesion location that corresponds to the target lesion;
• outputting an indicator on a graphical user interface, the indicator including the potential lesion location;
• tracking a real time position of an ultrasound probe;
• navigating the ultrasound probe towards the potential lesion location based at least partially on the tracked real time position provided on the graphical user interface and the outputted indicator;
• receiving an ultrasound image of the breast, the ultrasound image of the breast associated with a potential lesion;
• analyzing, using the artificial intelligence engine, the ultrasound image to generate a confidence score indicating a likelihood that the potential lesion in the ultrasound image matches the target lesion in the at least one first image;
• and
• displaying an output associated with the confidence score on the graphical user interface.

A lesion identification system comprising:

• an ultrasound probe;
• a graphical user interface;
• a processing device;
• and
• memory storing instructions that, when executed by the processing device, perform a set of operations comprising:
• receiving an indication of a location of a target lesion within at least one first image of a breast obtained by a first imaging modality;
• receiving at least one second image of the breast obtained by a second imaging modality, wherein the first and second imaging modalities are different;
• generating, at an artificial intelligence engine, a virtual deformable model via co-registering the at least one first image and the at least one second image;
• analyzing the virtual deformable model to determine a probability mapping for a potential lesion location that corresponds to the target lesion;
• outputting an indicator on the graphical user interface, the indicator including the potential lesion location;
• tracking a real time position of the ultrasound probe;
• providing navigation for the ultrasound probe towards the potential lesion location based at least partially on the tracked real time position provided on the graphical user interface and the outputted indicator;
• receiving an ultrasound image of the breast, the ultrasound image of the breast associated with a potential lesion;
• analyzing, using the artificial intelligence engine, the ultrasound image to generate a confidence score indicating a likelihood that the potential lesion in the ultrasound image matches the target lesion in the at least one first image;
• and
• displaying an output associated with the confidence score on the graphical user interface.