# US 2012/0075638 A1 · Segmentation and quantification for intravascular optical coherence tomography images > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2012/0075638 A1 - Document ID: US20120075638A1 - Status: Published application - Kind: A1 - Application number: 13/196,845 - Filed: 2011-08-02 - Published: 2012-03-29 - Earliest claimed: 2010-08-02 - Assignees: Case Western Reserve University - Inventors: Andrew Rollins; David Wilson; Marco Costa; Hiram Bezerra; Zhao Wang - Web page: https://patentgrep.com/patent/US20120075638A1 ## CPC - G06T 7/0012: {Biomedical image inspection} - A61B 1/000094: {extracting biological structures} - A61B 1/000096: {using artificial intelligence} - A61B 1/3137: {for examination of the interior of blood vessels} - A61B 5/0066: {Optical coherence imaging} - A61B 5/0084: {for introduction into the body, e.g. by catheters (A61B5/1459 takes precedence)} - A61B 5/02007: {Evaluating blood vessel condition, e.g. elasticity, compliance} - G01B 9/02091: Tomographic interferometers, e.g. based on optical coherence - G06T 7/12: Edge-based segmentation - G06T 7/62: of area, perimeter, diameter or volume - A61B 5/06: Devices, other than using radiation, for detecting or locating foreign bodies {; Determining position of diagnostic devices within or on the body of the patient} - G06T 2200/24: involving graphical user interfaces [GUIs] - G06T 2207/10101: Optical tomography; Optical coherence tomography [OCT] - G06T 2207/20116: Active contour; Active surface; Snakes - G06T 2207/20161: Level set - G06T 2207/30021: Catheter; Guide wire - G06T 2207/30101: Blood vessel; Artery; Vein; Vascular - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G01B: MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS ## Abstract A system and related methods for automatic or semi-automatic segmentation and quantification of blood vessel structure and physiology, including segmentation and quantification of lumen, guide wire, vessel wall, calcified plaques, fibrous caps, macrophages, metallic and bioresorbable stents are described, and including visualization of results. Calcified plaque segmentation can be used to estimate the distribution of superficial calcification and inform strategies stenting. Volumetric segmentation and quantification of fibrous caps can provide more comprehensive information of the mechanisms behind plaque rupture. Quantification of macrophages can aid diagnosis and prediction of unstable plaque and associated acute coronary events. Automated detection and quantification of metallic and bioresorbable stents can greatly reduce the analysis time and facilitate timely decision making for intervention procedures. ## Claims ### Claim 1 Computer-implemented segmentation and quantification method using an intravascular optical coherence tomography (OCT) system having an OCT signal emitting and receiving instrument comprising: obtaining an OCT image set comprising one or more images of a portion of a blood vessel; segmenting a lumen portion of at least one of the one or more images; segmenting an OCT signal emitting and receiving instrument portion of the at least one of the one or more images; segmenting a vessel wall portion of the at least one of the one or more images; and, segmenting a calcified plaque portion of the at least one of the one or more images. ### Claim 2 (depends on 1) The method of claim 1, wherein the segmenting the lumen portion step comprises: obtaining at least one binary image by applying Otsu's method to at least one of the one or more images. ### Claim 3 (depends on 2) The method of claim 2 wherein the segmenting the lumen portion step comprises: determining the first pixel corresponding to a border of the lumen in a light propagation direction corresponding to the OCT signal emitting and receiving instrument. ### Claim 4 (depends on 1) The method of claim 1 wherein the segmenting the lumen portion step comprises: obtaining at least one binary image by applying Otsu's method to at least one of the one or more images; determining a boundary from the at least one binary image giving a global maximum for an energy function defined at least in part by an intensity difference of pixels inside and outside the boundary. ### Claim 5 (depends on 1) The method of claim 1 wherein the segmenting the OCT signal emitting and receiving instrument portion step comprises: obtaining at least one binary image of a bright superficial layer of the blood vessel; and, determining a location of a gap in the bright superficial layer. ### Claim 6 (depends on 1) The method of claim 1 wherein the segmenting the vessel wall portion step comprises: obtaining at least one texture mapping by processing at least one of the one or more images with at least one Gabor filter; and, determining a contour having maximum texture difference inside and outside the contour by applying active contour processing to the at least one texture mapping. ### Claim 7 (depends on 6) The method of claim 6 further comprising: obtaining an initial contour for the active contour processing from a boundary determined in the segmenting the lumen portion step. ### Claim 8 (depends on 1) The method of claim 1 wherein the segmenting a calcified plaque portion step comprises: obtaining a segmented vessel wall portion of at least one of the one or more images from the segmenting the vessel wall portion step; and detecting the edge of a calcified plaque within the segmented vessel wall portion in at least one of the one or more images. ### Claim 9 (depends on 8) The method of claim 8 further comprising: determining at least one initial contour from the detecting the edge of a calcified plaque step; inputting the at least one initial contour and at least one of the one or more images to an active contour model; determining at least one boundary of a calcified plaque having a local maximum intensity difference between outside and inside the at least one boundary in at least one of the one or more images. ### Claim 10 (depends on 1) The method of claim 1 wherein the segmenting a calcified plaque portion step comprises: obtaining at least one initial contour; inputting the at least one initial contour and at least one of the one or more images to an active contour model; determining at least one boundary of a calcified plaque having a local maximum intensity difference between outside and inside the at least one boundary in at least one of the one or more images. ### Claim 11 Computer-implemented segmentation and quantification method using an intravascular optical coherence tomography (OCT) system having an OCT signal emitting and receiving instrument comprising: obtaining an OCT image set comprising one or more images of a portion of a blood vessel; segmenting a lumen portion of at least one of the one or more images; segmenting an OCT signal emitting and receiving instrument portion of the at least one of the one or more images; segmenting a vessel wall portion of the at least one of the one or more images; and, segmenting a macrophage portion of the at least one of the one or more images. ### Claim 12 (depends on 11) The method of claim 11, wherein the segmenting the lumen portion step comprises: obtaining at least one binary image by applying Otsu's method to at least one of the one or more images. ### Claim 13 (depends on 12) The method of claim 12 wherein the segmenting the lumen portion step comprises: determining the first pixel corresponding to a border of the lumen in a light propagation direction corresponding to the OCT signal emitting and receiving instrument. ### Claim 14 (depends on 11) The method of claim 11 wherein the segmenting the lumen portion step comprises: obtaining at least one binary image by applying Otsu's method to at least one of the one or more images; determining a boundary from the at least one binary image giving a global maximum for an energy function defined at least in part by an intensity difference of pixels inside and outside the boundary. ### Claim 15 (depends on 11) The method of claim 11 wherein the segmenting the OCT signal emitting and receiving instrument portion step comprises: obtaining at least one binary image of a bright superficial layer of the blood vessel; and, determining a location of a gap in the bright superficial layer. ### Claim 16 (depends on 11) The method of claim 11 wherein the segmenting the vessel wall portion step comprises: obtaining at least one texture mapping by processing at least one of the one or more images with at least one Gabor filter; and, determining a contour having maximum texture difference inside and outside the contour by applying active contour processing to the at least one texture mapping. ### Claim 17 (depends on 16) The method of claim 16 further comprising: obtaining an initial contour for the active contour processing from a boundary determined in the segmenting the lumen portion step. ### Claim 18 (depends on 11) The method of claim 11 wherein the segmenting a macrophage portion step comprises: classifying macrophages based on a decision tree dependent on manually segmented training images. ### Claim 19 (depends on 18) The method of claim 18 wherein the decision tree is dependent on one or more training features of the training images. ### Claim 20 An optical coherence tomography (OCT) system, comprising: an OCT signal emitting and receiving instrument; a computer readable medium comprising: instructions that upon execution obtain an OCT image set comprising one or more images of a portion of a blood vessel; instructions that upon execution segment a lumen portion of at least one of the one or more images; instructions that upon execution segment an OCT signal emitting and receiving instrument portion of the at least one of the one or more images; instructions that upon execution segment a vessel wall portion of the at least one of the one or more images; and, instructions that upon execution segment a calcified plaque portion of the at least one of the one or more images.