# US 2017/0281112 A1 · Method for segmenting small features in an image volume > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2017/0281112 A1 - Document ID: US20170281112A1 - Status: Published application - Kind: A1 - Application number: 15/085,577 - Filed: 2016-03-30 - Published: 2017-10-05 - Earliest claimed: 2016-03-30 - Assignees: General Electric Company - Applicants: General Electric Company - Inventors: Jed Douglas PACK; Brian Edward NETT; Sathish RAMANI - Web page: https://patentgrep.com/patent/US20170281112A1 ## CPC - A61B 6/5264: {due to motion} - A61B 6/032: {Transmission computed tomography [CT]} - G06T 3/18: Image warping, e.g. rearranging pixels individually - G06T 5/20: using local operators - G06T 5/70: Denoising; Smoothing - G06T 7/0012: {Biomedical image inspection} - G06T 7/11: Region-based segmentation - G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments - G06T 7/33: using feature-based methods - G06T 12/10: Image preprocessing, e.g. calibration, positioning of sources or scatter correction - G06T 2207/10081: Computed x-ray tomography [CT] - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract According to some embodiments, system and methods are provided comprising determining one or more image locations at which motion occurred within an image volume of an object containing movable anatomical features prior to segmenting the movable anatomical features; estimating motion at each of the one or more image locations; correcting one or more motion artifacts in the image volume at each of the one or more image locations, where motion was estimated resulting in the generation of a final motion compensated image; and segmenting one or more features of interest in the final motion compensated image. Numerous other aspects are provided. ## Claims ### Claim 1 A method comprising: determining one or more image locations at which motion occurred within an image volume of an object containing movable anatomical features prior to segmenting the movable anatomical features; estimating motion at each of the one or more image locations; correcting one or more motion artifacts in the image volume at each of the one or more image locations, where motion was estimated resulting in the generation of a final motion compensated image; and segmenting one or more features of interest in the final motion compensated image. ### Claim 2 (depends on 1) The method of claim 1, further comprising: obtaining at least two image volumes prior to determining one or more image locations at which motion occurred. ### Claim 3 (depends on 1) The method of claim 1, further comprising: generating a smooth motion field from the estimated motion at the one or more image locations at which motion was estimated; and decomposing the image volume into a series of two or more image volumes that sum to the original image volume. ### Claim 4 (depends on 3) The method of claim 3, wherein decomposing is based on one of a time at which the projection data were acquired or an angle at which the projection data were acquired. ### Claim 5 (depends on 3) The method of claim 3, wherein each image volume in the series of two or more image volumes represents a snapshot in time. ### Claim 6 (depends on 4) The method of claim 4, further comprising: warping each image volume in the series of two or more image volumes according to the motion estimate at the corresponding time or angle at which the projection data that contributed to each volume were acquired. ### Claim 7 (depends on 6) The method of claim 6, wherein correcting one or more motion artifacts in the image volume further comprises: summing the two or more warped image volumes in the series. ### Claim 8 (depends on 1) The method of claim 1, wherein determining one or more image locations at which motion occurred within an image volume further comprises: selecting two image volumes from a set of acquired image volumes. determining a difference between the two image volumes; filtering the difference between the two image volumes with one or more steerable ridge filters to generate one or more filtered image volumes. ### Claim 9 (depends on 8) The method of claim 8, further comprising: determining a mean absolute value across each element in the one or more filtered image volumes to produce a mean absolute value volume, wherein the mean absolute value volume highlights one or more areas in the filtered image volumes where motion is occurring; and applying a smoothing filter to the mean absolute value volume to generate a smoothed absolute value image volume. ### Claim 10 (depends on 9) The method of claim 9, further comprising: identifying one or more image locations distributed within each of the one or more areas in the smoothed absolute value image volume where motion is occurring. ### Claim 11 (depends on 10) The method of claim 10, wherein the one or more image locations are identified by: slicing the image volume into one or more slices; identifying one or more disconnected regions in each slice; determining the locations corresponding to a well-distributed set of bright points in each disconnected region. ### Claim 12 A system comprising: an image acquisition device operative to obtain an image of a movable anatomical feature, the image having an image volume; a segmentation module; and a memory in communication with the image acquisition device and storing program instructions, the segmentation module operative with the program instructions to perform the functions as follows: determining one or more image locations at which motion occurred within the image volume; estimating motion at each of the one or more image locations; correcting one or more motion artifacts in the image volume at each of the one or more image locations where motion was estimated, resulting in the generation of a final motion compensated image volume; and. segmenting one or more features of interest in the final motion compensated image. ### Claim 13 (depends on 12) The system of claim 12, wherein a smooth motion field is generated, via the segmentation module, from the one or more image locations at which motion was estimated; and wherein the image volume is decomposed, via the segmentation module, into a series of two or more image volumes that sum to the original image volume. ### Claim 14 (depends on 13) The system of claim 13, wherein decomposing is based on one of a time at which the relevant projection data were acquired or an angle at which the relevant projection data were acquired. ### Claim 15 (depends on 14) The system of claim 14, wherein each image volume in the series of two or more image volumes is warped according to the motion estimate at the corresponding time or angle at which the relevant projection data were acquired. ### Claim 16 (depends on 15) The system of claim 15, wherein the two or more warped image volumes in the series are summed to correct one or more motion artifacts in the image volume. ### Claim 17 (depends on 12) The system of claim 12, wherein the segmentation module is further operative to determine one or more image locations at which motion occurred within an image volume by: selecting two image volumes from a set of acquired image volumes; determining a difference between the two image volumes; filtering the difference between the two image volumes with one or more steerable ridge filters to generate one or more filtered image volumes. ### Claim 18 (depends on 17) The system of claim 17, wherein the segmentation module is further operative to: determine a mean absolute value across each element in the one or more filtered image volumes to produce a mean absolute value volume, wherein the mean absolute value volume highlights one or more areas in the filtered image volumes where motion is occurring; and apply a smoothing filter to the mean absolute value volume to generate a smoothed absolute value image volume. ### Claim 19 (depends on 18) The system of claim 18, wherein the segmentation module is further operative to: identify one or more image locations distributed within each of the one or more areas in the smoothed absolute value image volume where motion is occurring. ### Claim 20 (depends on 19) The system of claim 19, wherein the segmentation module is further operative to identify the one or more image locations by: slicing the image volume into one or more slices; identifying one or more disconnected regions in each slice; determining the locations corresponding to a well-distributed set of bright points in each disconnected region.