Method for visualizing blood and blood-likelihood in vascualar images

A system for processing intravascular images, comprising:

• an input device for receiving data representative of a plurality of intravascular ultrasound images including a first intravascular ultrasound image of vascular tissue from an imaging catheter positioned within a vessel of a patient;
• a processor in communication with the input device, the processor configured to:
• receive the data representative of the plurality of intravascular ultrasound images;
• process at least a first and a second spatiotemporal feature of at least one pixel representative of a same location in the plurality of intravascular ultrasound images utilizing a non-linear, probabilistic classifier, wherein the first spatiotemporal feature is based on a first image characteristic of the at least one pixel of the first ultrasound image, wherein the second spatiotemporal features is based on a second image characteristic of the at least one pixel of the first ultrasound image, the first image characteristic being different than the second image characteristic, wherein the first spatiotemporal feature and the second spatiotemporal feature represent changes in the first and second image characteristics over the plurality of intravascular ultrasound images between the at least one pixel and the pixels adjacent to the at least one pixel;
• construct a second intravascular ultrasound image based on a blood-likelihood value of at least one pixel;
• and
• construct a blood-likelihood map of the vascular tissue based on the blood-likelihood value of the at least one pixel;
• and
• a display configured to receive at least one of the first or second intravascular images.

A method of characterizing tissue, comprising:

• obtaining at least one energy signal reflected from the tissue with an imaging catheter positioned within a vessel of a patient;
• constructing, with a processor in communication with the imaging catheter, an image of vascular tissue based on said at least one energy signal;
• analyzing, with the processor, at least a first spatiotemporal feature and a second spatiotemporal feature of at least one pixel of the image, wherein the first spatiotemporal feature is based on a first image characteristic in the image, wherein the second spatiotemporal feature is based on a second image characteristic in the image, the first image characteristic being different than the second image characteristic, wherein the first spatiotemporal feature and the second spatiotemporal feature represent changes in the first and second image characteristics between the at least one pixel and other pixels in another image;
• determining, with the processor, a blood-likelihood value for the at least one pixel of the image by applying the first spatiotemporal feature to a non-linear, probabilistic classifier algorithm;
• and
• constructing, with the processor, a blood-likelihood map of the vascular tissue based on the blood-likelihood value of the at least one pixel of the image.