# US 2013/0155064 A1 · Method and System for Aortic Valve Calcification Evaluation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2013/0155064 A1 - Document ID: US20130155064A1 - Status: Published application - Kind: A1 - Application number: 13/713,603 - Filed: 2012-12-13 - Published: 2013-06-20 - Earliest claimed: 2011-12-15 - Assignees: Siemens Healthcare GmbH - Inventors: Sasa Grbic; Razvan Ioan Ionasec; Fernando Vega-Higuera; Dominik Bernhardt; Dorin Comaniciu - Web page: https://patentgrep.com/patent/US20130155064A1 ## CPC - A61B 6/03: Computed tomography [CT] - G06T 7/11: Region-based segmentation - G06T 7/149: involving deformable models, e.g. active contour models - G06T 7/162: involving graph-based methods - G06T 17/00: Three-dimensional [3D] modelling for computer graphics - G06T 2207/20081: Training; Learning - G06T 2207/20156: Automatic seed setting - G06T 2207/30048: Heart; Cardiac - G06T 2207/30101: Blood vessel; Artery; Vein; Vascular - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A method and system for automatic aortic valve calcification evaluation is disclosed. A patient-specific aortic valve model in a 3D medical image volume, such as a 3D computed tomography (CT) volume. Calcifications in a region of the 3D medical image volume defined based on the aortic valve model. A 2D calcification plot is generated that shows locations of the segmented calcifications relative to aortic valve leaflets of the patient-specific aortic valve model. The 2D calcification plot can be used for assessing the suitability of a patient for a Transcatheter Aortic Valve Replacement (TAVI) procedure, as well as risk assessment, positioning of an aortic valve implant, and selection of a type of aortic valve implant. ## Claims ### Claim 1 A method for automatic aortic valve calcification evaluation, comprising: detecting a patient-specific aortic valve model in a 3D medical image volume; segmenting calcifications in a region of the 3D medical image volume defined based on the aortic valve model; and generating a 2D calcification plot showing locations of the segmented calcifications relative to aortic valve leaflets of the patient-specific aortic valve model. ### Claim 2 (depends on 1) The method of claim 1, wherein detecting a patient-specific aortic valve model in a 3D medical image volume comprises: detecting the patient-specific aortic valve model in the 3D medical volume using a Marginal Space Learning (MSL) framework. ### Claim 3 (depends on 1) The method of claim 1, wherein detecting a patient-specific aortic valve model in a 3D medical image volume comprises: detecting rigid motion parameters in the 3D medical image volume using a first trained detector; detecting anatomical landmarks in the 3D medical image volume based on the detected rigid motion parameters using a second trained detector; and detecting surface aortic valve surface structures in the 3D medical image volume based on the detected anatomical landmarks using a third trained detector. ### Claim 4 (depends on 3) The method of claim 3, wherein the anatomical landmarks include aortic valve hinges and aortic valve commissures and the aortic valve surface structures include an aortic root and the aortic valve leaflets. ### Claim 5 (depends on 1) The method of claim 1, wherein segmenting calcifications in a region of the 3D medical image volume defined based on the aortic valve model comprises: segmenting the calcifications in the region of the 3D medical image volume using graph cuts segmentation. ### Claim 6 (depends on 5) The method of claim 5, wherein segmenting the calcifications in the region of the 3D medical image volume using graph cuts segmentation comprises: determining a probability score for each of a plurality of voxels in the region of the 3D medical image using a trained calcification detector; assigning a voxel having a highest probability score as a positive seed point and a voxel having a lowest probability score as a negative seed point; and segmenting a set of calcification voxels from the plurality of voxels using graph cuts segmentation based on the positive seed point, the negative seed point, and the probability scores for the plurality of voxels. ### Claim 7 (depends on 1) The method of claim 1, wherein segmenting calcifications in a region of the 3D medical image volume defined based on the aortic valve model comprises: detecting a set of calcification voxels from a plurality of voxels in the region of the 3D medical image volume. ### Claim 8 (depends on 1) The method of claim 1, wherein generating a 2D calcification plot showing locations of the segmented calcifications relative to aortic valve leaflets of the patient-specific aortic valve model comprises: mapping the segmented calcifications closest mesh points on the aortic valve leaflets of the patient-specific aortic valve model; and projecting the calcifications mapped to each of the mesh points on the aortic valve leaflets of the patient-specific aortic valve model to a corresponding point on a circular 2D plot, wherein each aortic valve leaflet is represented as one third of the circular 2D plot. ### Claim 9 (depends on 1) The method of claim 1, wherein the 2D calcification plot shows relative severity of the calcifications using relative levels of transparency. ### Claim 10 (depends on 1) The method of claim 1, further comprising: determining a patient's suitability for a Transcatheter Aortic Valve Replacement (TAVI) procedure based on the 2D calcification plot using a trained classifier. ### Claim 11 (depends on 1) The method of claim 1, further comprising: determining a risk of stroke for a patient based on the 2D calcification plot using a trained classifier. ### Claim 12 (depends on 1) The method of claim 1, further comprising: determining a best position for an aortic valve implant based on the 2D calcification plot. ### Claim 13 (depends on 1) The method of claim 1, further comprising: automatically selecting a type of aortic valve implant device based on the 2D calcification plot. ### Claim 14 An apparatus for automatic aortic valve calcification evaluation, comprising: means for detecting a patient-specific aortic valve model in a 3D medical image volume; means for segmenting calcifications in a region of the 3D medical image volume defined based on the aortic valve model; and means for generating a 2D calcification plot showing locations of the segmented calcifications relative to aortic valve leaflets of the patient-specific aortic valve model. ### Claim 15 (depends on 14) The apparatus of claim 14, wherein the patient-specific aortic valve model comprises an aortic root surface model and aortic valve leaflet surface models. ### Claim 16 (depends on 14) The apparatus of claim 14, wherein the means for segmenting calcifications in a region of the 3D medical image volume defined based on the aortic valve model comprises: means for segmenting the calcifications in the region of the 3D medical image volume using graph cuts segmentation. ### Claim 17 (depends on 14) The apparatus of claim 14, wherein the means for segmenting calcifications in a region of the 3D medical image volume defined based on the aortic valve model comprises: means for detecting a set of calcification voxels from a plurality of voxels in the region of the 3D medical image volume. ### Claim 18 (depends on 14) The apparatus of claim 14, wherein the means for generating a 2D calcification plot showing locations of the segmented calcifications relative to aortic valve leaflets of the patient-specific aortic valve model comprises: means for mapping the segmented calcifications closest mesh points on the aortic valve leaflets of the patient-specific aortic valve model; and means for projecting the calcifications mapped to each of the mesh points on the aortic valve leaflets of the patient-specific aortic valve model to a corresponding point on a circular 2D plot, wherein each aortic valve leaflet is represented as one third of the circular 2D plot. ### Claim 19 (depends on 14) The apparatus of claim 14, wherein the 2D calcification plot shows relative severity of the calcifications using relative levels of transparency. ### Claim 20 A non-transitory computer readable medium storing computer program instructions for automatic aortic valve calcification evaluation, the computer program instructions when executed on a processor cause the processor to perform operations comprising: detecting a patient-specific aortic valve model in a 3D medical image volume; segmenting calcifications in a region of the 3D medical image volume defined based on the aortic valve model; and generating a 2D calcification plot showing locations of the segmented calcifications relative to aortic valve leaflets of the patient-specific aortic valve model. ### Claim 21 (depends on 20) The non-transitory computer readable medium of claim 20, wherein detecting a patient-specific aortic valve model in a 3D medical image volume comprises: detecting rigid motion parameters in the 3D medical image volume using a first trained detector; detecting anatomical landmarks in the 3D medical image volume based on the detected rigid motion parameters using a second trained detector; and detecting surface aortic valve surface structures in the 3D medical image volume based on the detected anatomical landmarks using a third trained detector. ### Claim 22 (depends on 21) The non-transitory computer readable medium of claim 21, wherein the anatomical landmarks include aortic valve hinges and aortic valve commissures and the aortic valve surface structures include an aortic root and the aortic valve leaflets. ### Claim 23 (depends on 20) The non-transitory computer readable medium of claim 20, wherein segmenting calcifications in a region of the 3D medical image volume defined based on the aortic valve model comprises: segmenting the calcifications in the region of the 3D medical image volume using graph cuts segmentation. ### Claim 24 (depends on 23) The non-transitory computer readable medium of claim 23, wherein segmenting the calcifications in the region of the 3D medical image volume using graph cuts segmentation comprises: determining a probability score for each of a plurality of voxels in the region of the 3D medical image using a trained calcification detector; assigning a voxel having a highest probability score as a positive seed point and a voxel having a lowest probability score as a negative seed point; and segmenting a set of calcification voxels from the plurality of voxels using graph cuts segmentation based on the positive seed point, the negative seed point, and the probability scores for the plurality of voxels. ### Claim 25 (depends on 20) The non-transitory computer readable medium of claim 20, wherein generating a 2D calcification plot showing locations of the segmented calcifications relative to aortic valve leaflets of the patient-specific aortic valve model comprises: mapping the segmented calcifications closest mesh points on the aortic valve leaflets of the patient-specific aortic valve model; and projecting the calcifications mapped to each of the mesh points on the aortic valve leaflets of the patient-specific aortic valve model to a corresponding point on a circular 2D plot, wherein each aortic valve leaflet is represented as one third of the circular 2D plot. ### Claim 26 (depends on 25) The non-transitory computer readable medium of claim 25, wherein the 2D calcification plot shows relative severity of the calcifications using relative levels of transparency. ### Claim 27 (depends on 20) The non-transitory computer readable medium of claim 20, wherein the operations further comprise: determining a patient's suitability for a Transcatheter Aortic Valve Replacement (TAVI) procedure based on the 2D calcification plot using a trained classifier. ### Claim 28 (depends on 20) The non-transitory computer readable medium of claim 20, wherein the operations further comprise: determining a risk of stroke for a patient based on the 2D calcification plot using a trained classifier. ### Claim 29 (depends on 20) The non-transitory computer readable medium of claim 20, wherein the operations further comprise: determining a best position for an aortic valve implant based on the 2D calcification plot. ### Claim 30 (depends on 20) The non-transitory computer readable medium of claim 20, wherein the operations further comprise: automatically selecting a type of aortic valve implant device based on the 2D calcification plot.