# US 12,008,073 B2 · Myocardium image analysis method and device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,008,073 B2 - Document ID: US12008073B2 - Status: Granted - Kind: B2 - Application number: 17/293,638 - Filed: 2019-11-07 - Published: 2022-01-13 - Granted: 2024-06-11 - Earliest claimed: 2018-11-14 - Assignees: The Asan Foundation; University of Ulsan Foundation for Industry Cooperation - Applicants: The Asan Foundation; University of Ulsan Foundation for Industry Cooperation - Inventors: Dong Hyun Yang; June Goo Lee; Young-Hak Kim - Web page: https://patentgrep.com/patent/US12008073B2 ## CPC - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - A61B 6/481: {involving the use of contrast agents} - A61B 6/503: {for diagnosis of the heart} - G06F 18/2163: {Partitioning the feature space} - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - G16H 30/40: for processing medical images, e.g. editing - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - A61B 6/032: {Transmission computed tomography [CT]} - A61B 6/504: {for diagnosis of blood vessels, e.g. by angiography} - A61B 6/5217: {extracting a diagnostic or physiological parameter from medical diagnostic data} - G06V 2201/03: Recognition of patterns in medical or anatomical images - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A myocardium image analysis method comprising acquiring a target image including precontrast-enhanced myocardium, based on a type of coronary artery related to the myocardium, distinguishing the myocardium included in the target image, using an artificial neural network, providing information on the distinguished myocardium, wherein the artificial neural network is trained based on a training database generated by matching images for training of precontrast-enhanced coronary artery and myocardium and images for training of postcontrast-enhanced coronary artery and myocardium. ## Claims ### Claim 1 A myocardium image analysis method comprising: acquiring a target image including precontrast-enhanced myocardium; based on a type of coronary artery related to the myocardium, dividing up the myocardium included in the target image, using an artificial neural network; and providing information on the distinguished myocardium, wherein the artificial neural network is trained based on a training database generated by matching images for training of precontrast-enhanced coronary artery and myocardium and pre-acquired images for training of postcontrast-enhanced coronary artery and myocardium. ### Claim 2 (depends on 1) The myocardium image analysis method of claim 1, wherein the type of coronary arteries includes a left coronary artery (LCA), a left main coronary artery (LMCA), a left anterior descending coronary artery (LAD), a proximal left anterior descending artery, a middle left anterior descending artery, a distal left anterior descending artery, a right coronary artery (RCA), a proximal right coronary artery, a middle right coronary artery, a distal right coronary artery, and a posterior descending artery (PDA). ### Claim 3 (depends on 1) The myocardium image analysis method of claim 1, wherein the dividing up of the myocardium includes dividing up the myocardium according to the type of coronary artery which is adjacent to the myocardium and exerts an influence on the myocardium. ### Claim 4 (depends on 1) The myocardium image analysis method of claim 1, wherein the training database includes information on at least one of a size, a location, a shape, and a length of a region of the myocardium related for each type of the coronary artery, the artificial neural network includes a fully convolutional network (FCN), and the region of the myocardium includes a myocardium region connected to the left coronary artery, a myocardium region connected to the left main coronary artery, a myocardium region connected to the left anterior descending coronary artery, a myocardium region connected to the proximal left anterior descending artery, a myocardium region connected to the middle left anterior descending artery, a myocardium region connected to the distal left anterior descending artery, a myocardium region connected to the right coronary artery, a myocardium region connected to the proximal right coronary artery, a myocardium region connected to the middle right coronary artery, a myocardium region connected to the distal right coronary artery, and a myocardium region connected to the posterior descending artery. ### Claim 5 (depends on 1) The myocardium image analysis method of claim 1, wherein the images for training of the precontrast-enhanced coronary artery and myocardium and the images for training of the postcontrast-enhanced coronary artery and myocardium are images on the same target. ### Claim 6 (depends on 1) The myocardium image analysis method of claim 1, wherein the target image is a computed tomography (CT) image. ### Claim 7 A myocardium image analysis device comprising: a target image acquisition unit acquiring a target image including precontrast-enhanced myocardium; based on a type of coronary artery related to the myocardium, a myocardium distinguishing unit dividing up the myocardium included in the target image, using an artificial neural network; and providing information on the distinguished myocardium, wherein the artificial neural network is trained based on a training database generated by matching images for training of precontrast-enhanced coronary artery and myocardium and images for training of postcontrast-enhanced coronary artery and myocardium. ### Claim 8 (depends on 7) The myocardium image analysis device of claim 7, wherein the type of coronary arteries includes a left coronary artery (LCA), a left main coronary artery (LMCA), a left anterior descending coronary artery (LAD), a proximal left anterior descending artery, a middle left anterior descending artery, a distal left anterior descending artery, a right coronary artery (RCA), a proximal right coronary artery, a middle right coronary artery, a distal right coronary artery, and a posterior descending artery (PDA). ### Claim 9 (depends on 7) The myocardium image analysis device of claim 7, wherein the myocardium distinguishing unit divides the myocardium according to the type of coronary artery which is adjacent to the myocardium and exerts an influence on the myocardium. ### Claim 10 (depends on 7) The myocardium image analysis device of claim 7, wherein the training database includes information on at least one of a size, a location, a shape, and a length of a region of the myocardium related for each type of the coronary artery, the artificial neural network includes a fully convolutional network (FCN), and the distinguished region of the myocardium includes a myocardium region connected to the left coronary artery, a myocardium region connected to the left main coronary artery, a myocardium region connected to the left anterior descending coronary artery, a myocardium region connected to the proximal left anterior descending artery, a myocardium region connected to the middle left anterior descending artery, a myocardium region connected to the distal left anterior descending artery, a myocardium region connected to the right coronary artery, a myocardium region connected to the proximal right coronary artery, a myocardium region connected to the middle right coronary artery, a myocardium region connected to the distal right coronary artery, and a myocardium region connected to the posterior descending artery. ### Claim 11 (depends on 7) The myocardium image analysis device of claim 7, wherein the images for training of the precontrast-enhanced coronary artery and myocardium and the images for training of the postcontrast-enhanced coronary artery and myocardium are images for the same target. ### Claim 12 (depends on 7) The myocardium image analysis device of claim 7, wherein the target image is a computed tomography (CT) image. ### Claim 13 A computer readable recording medium storing a computer program, comprising: acquiring a target image including precontrast-enhanced myocardium; based on a type of coronary artery related to the myocardium, dividing up the myocardium included in the target image, using an artificial neural network; and providing information on the distinguished myocardium, wherein the artificial neural network includes a command for allowing a processor to perform a myocardium image analysis method in which training is performed based on a training database generated by matching images for training of precontrast-enhanced coronary artery and myocardium and images for training of postcontrast-enhanced coronary artery and myocardium.