# US 11,443,423 B2 · System and method for constructing elements of interest (EoI)-focused panoramas of an oral complex > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,423 B2 - Document ID: US11443423B2 - Status: Granted - Kind: B2 - Application number: 16/783,615 - Filed: 2020-02-06 - Published: 2020-06-04 - Granted: 2022-09-13 - Earliest claimed: 2018-10-30 - Assignees: Dgnct LLC - Applicants: Diagnocat, inc. - Inventors: Matvey Dmitrievich Ezhov; Vladimir Leonidovich Aleksandrovskiy; Evgeny Sergeevich Shumilov; Maxim Gusarev - Web page: https://patentgrep.com/patent/US11443423B2 ## CPC - G06T 7/0012: {Biomedical image inspection} - G06T 7/11: Region-based segmentation - G06T 3/047: Fisheye or wide-angle transformations - G06T 7/10: Segmentation; Edge detection (motion-based segmentation G06T7/215) - G06T 11/20: Drawing from basic elements - G06T 2207/10081: Computed x-ray tomography [CT] - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30008: Bone - G06T 2207/30036: Dental; Teeth - G06T 2210/12: Bounding box - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A method for constructing a panorama of teeth arch with elements of interest emphasized, comprising the steps of: extracting a teeth arch from a volumetric image; unfolding the extracted teeth arch into a panoramic ribbon; assigning weighted priorities to at least two points in the panoramic ribbon, wherein priorities are weighted higher for points inside or proximal to elements of interest and applying a weighted summation in a direction perpendicular to teeth arch resulting in the panorama with elements of interest emphasized. ## Claims ### Claim 1 A method for constructing a panorama of teeth arch with elements of interest (EoI) visually emphasized for an accurate diagnostic-treatment approach, said method comprising the steps of: extracting a teeth arch from a volumetric image; unfolding the extracted teeth arch into a panoramic ribbon; assigning a higher weight to at least a point in the panoramic ribbon, wherein the at least one point is inside or proximal to an element of interest; and applying a weighted summation in a direction perpendicular to the teeth arch resulting in the panorama with the (EoI) visually emphasized. ### Claim 2 (depends on 1) The method of claim 1, wherein the panorama is at least one of a general panorama or split panorama. ### Claim 3 (depends on 1) The method of claim 1, wherein the teeth arch is extracted using segmentations of at least one of a teeth or anatomy. ### Claim 4 (depends on 1) The method of claim 1, wherein the panoramic ribbon is a curved sub-volume passing along the teeth arch. ### Claim 5 (depends on 1) The method of claim 1, further comprising the step of applying a transformation grid to the extracted teeth arch image for unfolding the extracted teeth arch image into the panoramic ribbon. ### Claim 6 (depends on 1) The method of claim 1, further comprising tilting of the ribbon to maximize perceptibility of a frontal teeth apex. ### Claim 7 (depends on 1) The method of claim 1, wherein the higher weights are assigned to a plurality of points, each point arbitrarily chosen on the panoramic ribbon. ### Claim 8 (depends on 7) The method of claim 7, wherein the arbitrarily chosen points are evenly spaced along the length of the panoramic ribbon. ### Claim 9 (depends on 1) The method of claim 1, wherein the elements of interest are at least one of a bone, tooth, teeth, or mandibular canals. ### Claim 10 (depends on 1) The method of claim 1, wherein weights are assigned highest to points inside or most proximal to elements of interest with a pre-defined highest value, wherein segmentation of at least one of an anatomy or teeth are applied to assign the weights. ### Claim 11 (depends on 1) The method of claim 1, further comprising the step of obtaining at least one of a two-dimensional (2D) or three-dimensional (3D) teeth segmentation masks and numbering from an original Cone Beam Computed Tomography (CBCT) scan. ### Claim 12 (depends on 11) The method of claim 11, further comprising the step of retrieving a three-dimensional bounding box inferred from a two-dimensional panoramic instance from the ribbon; and submit the three-dimensional bounding box as the element of interest for a three-dimensional teeth segmentation mask and numbering from the original CBCT scan. ### Claim 13 (depends on 1) The method of claim 1, further comprising the step of projecting a two-dimensional (2D) and three-dimensional (3D) teeth segmentation masks onto the panorama; calculating Intersection over Union (IoU) for 2D masks and the projected 3D masks; and selecting the best 3D projections for every 2D instance on the panoramic image. ### Claim 14 A method for constructing a panorama of teeth arch with elements of interest (EoI) visually emphasized for an accurate diagnostic-treatment approach, said method comprising the steps of: unfolding an extracted teeth arch into a panoramic ribbon; and assigning a higher weight to at least one point in the panoramic ribbon, wherein higher weights are assigned for points inside or proximal to an EoI resulting in the panorama with the EoI visually emphasized in a non-distorting manner. ### Claim 15 A system for constructing an Element of Interest (EoI)-focused panorama emphasized for an accurate diagnostic-treatment approach, said system comprising: a processor; a non-transitory storage element coupled to the processor; encoded instructions stored in the non-transitory storage element, wherein the encoded instructions when implemented by the processor, configure the system to: extract a teeth arch from a volumetric image; unfold the extracted teeth arch into a panoramic ribbon; assign higher weights to at least a point in the panoramic ribbon, wherein higher weights are assigned for points inside or proximal to an EoI; and applying a weighted summation in a direction perpendicular to the teeth arch, resulting in the panorama with the EoI visually emphasized for an accurate diagnostic-treatment approach. ### Claim 16 The system of 15, wherein the EoI is pre-defined by an end-user, wherein a plurality of EoI's are ranked in terms of weight by the end-user. ### Claim 17 (depends on 15) The system of claim 15, further comprising an instance segmentation module to generate a two-dimensional segmentation mask from a generated panorama to impose on the three-dimensional panoramic ribbon to retrieve inferred three-dimensional bounding box from the two-dimensional panoramic instance. ### Claim 18 (depends on 17) The system of claim 17, further comprising submitting the three-dimensional bonding box to a three-dimensional segmentation module for generating a three-dimensional segmentation mask for segmentation and numbering in original three-dimensional CBCT fine scale. ### Claim 19 (depends on 15) The system of claim 15, further comprising selecting a two-dimensional instance for each or either a three-dimensional UNet or three-dimensional Region Based Convolutional Neural Network (R-CNN) and selecting a best three-dimensional projection for every two-dimensional instance on the panoramic image. ### Claim 20 A system for constructing an Elements of Interest (EoI)-focused panorama for an accurate diagnostic-treatment approach, said system comprising: an instance segmentation module; a processor; a non-transitory storage element coupled to the processor; encoded instructions stored in the non-transitory storage element, wherein the encoded instructions when implemented by the processor, configure the system to: extract a teeth arch from a volumetric image; form a study image from the extracted teeth arch; unfold the study image into a panoramic ribbon; tilt the panoramic ribbon for maximal frontal teeth exposure; assign higher weight to at least a point in the panoramic ribbon, wherein the point is weighted higher for points inside or proximal to an EoI resulting in the panorama with the EoI emphasized; and apply the instance segmentation module to accurately provide a segmentation mask and numbering with the EoI visually emphasized for an accurate diagnostic-treatment approach. ### Claim 21 (depends on 20) The system of claim 20, wherein the instance segmentation module is a 3D-R-CNN instance segmentation module. ### Claim 22 (depends on 20) The system of claim 20, wherein the segmentation is for at least one of a tooth, teeth, mandible, mandibular canal, root, root canal, pulp chamber for each tooth, maxilla, or sinuses.