# US 12,183,004 B2 · Method and device for extracting blood vessel wall > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,183,004 B2 - Document ID: US12183004B2 - Status: Granted - Kind: B2 - Application number: 17/644,268 - Filed: 2021-12-14 - Published: 2022-06-23 - Granted: 2024-12-31 - Earliest claimed: 2020-12-17 - Assignees: GE Precision Healthcare LLC - Applicants: GE Precision Healthcare LLC - Inventors: Zhoushe Zhao; Yingbin Nie; Chen Zhang - Web page: https://patentgrep.com/patent/US12183004B2 ## CPC - G06T 7/0014: {using an image reference approach} - G06T 7/12: Edge-based segmentation - G06N 3/02: Neural networks - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06T 7/11: Region-based segmentation - G06T 7/136: involving thresholding - G06T 7/155: involving morphological operators - G06T 7/187: involving region growing; involving region merging; involving connected component labelling - G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI] - G06V 10/26: Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion - G06V 10/267: {by performing operations on regions, e.g. growing, shrinking or watersheds} - G06V 10/82: using neural networks - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30101: Blood vessel; Artery; Vein; Vascular - G06T 2207/30104: Vascular flow; Blood flow; Perfusion - G06V 2201/03: Recognition of patterns in medical or anatomical images - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Provided in the present application are a method and a device for extracting a blood vessel wall, a medical imaging system, and a non-transitory computer-readable storage medium. The method for extracting a blood vessel wall comprises acquiring a medical image, determining at least one first-order feature in the medical image, and extracting, on the basis of the at least one first-order feature, a blood vessel wall image from the medical image. ## Claims ### Claim 1 A method for extracting a blood vessel wall, comprising: performing image segmentation on an original scanned image and determining a region of interest; expanding an expansion extent of the region of interest to provide an expanded region of interest; acquiring a medical image based on the expanded region of interest; determining at least one first-order feature in the medical image; and extracting, on the basis of the at least one first-order feature, a blood vessel wall image from the medical image. ### Claim 2 (depends on 1) The method for extracting a blood vessel wall according to claim 1, wherein the acquiring a medical image comprises preprocessing the original scanned image. ### Claim 3 (depends on 1) The method for extracting a blood vessel wall according to claim 1, wherein the image segmentation comprises: determining, on the basis of a deep learning network, the region of interest comprising a blood vessel lumen in the original scanned image. ### Claim 4 (depends on 3) The method for extracting a blood vessel wall according to claim 3, comprising optimizing the region of interest on the basis of at least one of a region growing algorithm and a threshold method prior to the expanding the expansion extent of the region of interest. ### Claim 5 (depends on 1) The method for extracting a blood vessel wall according to claim 1, further comprising: performing a plaque analysis on the basis of the blood vessel wall image. ### Claim 6 (depends on 5) The method for extracting a blood vessel wall according to claim 5, further comprising: correcting the expansion extent of the region of interest on the basis of a result of the plaque analysis. ### Claim 7 (depends on 1) The method for extracting a blood vessel wall according to claim 1, wherein the at least one first-order feature comprises at least one of an energy value, a maximum value, a mean value, a variance value, a mean absolute deviation value, a regional uniformity, and an entropy value. ### Claim 8 (depends on 1) A non-transitory computer-readable storage medium for storing a computer program, wherein when executed by a computer, the computer program causes the computer to perform the method for extracting a blood vessel wall according to claim 1. ### Claim 9 A method for visualizing a blood vessel wall, comprising: performing image segmentation on an original scanned image and determining a region of interest; expanding an expansion extent of the region of interest to provide an expanded region of interest; acquiring a medical image based on the expanded region of interest; determining at least one first-order feature in the image to be extracted; and mapping the at least one first-order feature in the medical image to visualize the blood vessel wall. ### Claim 10 A device for extracting a blood vessel wall, comprising: an image acquisition module, configured to acquire a medical image, wherein the image acquisition module comprises: an image segmentation unit, configured to perform image segmentation on an original scanned image and determine a region of interest; and a region expansion unit, configured to: expand an expansion extend of the region of interest to provide an expanded region of interest; and acquire the medical image based on the expanded region of interest; a feature calculation module, configured to determine at least one first-order feature in the medical image; and an image extraction module, configured to extract a blood vessel wall image from the medical image on the basis of the at least one first-order feature. ### Claim 11 (depends on 10) The device for extracting a blood vessel wall according to claim 10, wherein the image acquisition module comprises a preprocessing unit, the preprocessing unit being configured to preprocess the original scanned image. ### Claim 12 (depends on 10) The device for extracting a blood vessel wall according to claim 10, wherein the image segmentation unit is further configured to determine, on the basis of a deep learning network, the region of interest comprising a blood vessel lumen in the original scanned image. ### Claim 13 (depends on 10) The device for extracting a blood vessel wall according to claim 10, wherein the image acquisition module further comprises: a region optimization unit, configured to optimize the region of interest on the basis of at least one of a region growing algorithm and a threshold method prior to the region expansion unit expanding the expansion extent of the region of interest. ### Claim 14 (depends on 10) The device for extracting a blood vessel wall according to claim 10, further comprising: a plaque analysis module, configured to perform a plaque analysis on the basis of the blood vessel wall image. ### Claim 15 (depends on 14) The device for extracting a blood vessel according to claim 14, further comprising: a feedback module, configured to correct the expansion extent of the region of interest on the basis of a result of the plaque analysis. ### Claim 16 (depends on 10) A medical imaging system, comprising the device for extracting a blood vessel wall according to claim 10.