# US 2026/0134625 A1 · Method for augmented intelligence in dental pattern recognition

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0134625 A1
- Document ID: US20260134625A1
- Status: Published application
- Kind: A1
- Application number: 19/032,233
- Filed: 2025-01-20
- Published: 2026-05-14
- Earliest claimed: 2021-08-25
- Assignees: AiCAD Dental Inc.
- Applicants: AiCAD Dental Inc.
- Inventors: Fabien Coulombe; Akshaykumar Ketankumar Patel
- Web page: https://patentgrep.com/patent/US20260134625A1

## CPC

- G06T 17/20: Finite element generation, e.g. wire-frame surface description, {tesselation}
- G06T 19/00: Manipulating three-dimensional [3D] models or images for computer graphics
- A61C 13/0004: {Computer-assisted sizing or machining of dental prostheses}
- G06T 15/06: Ray-tracing
- G06V 10/82: using neural networks
- G06V 20/64: Three-dimensional [3D] objects
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 30/40: for processing medical images, e.g. editing
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06T 2210/41: Medical
- G06T 2219/008: Cut plane or projection plane definition
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G16H 20/40: relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61C: DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE (non-driven toothbrushes A46B; {tongue scrapers A61B17/24;} preparations for dentistry A61K6/00; preparations for cleaning the teeth or mouth A61K8/00, A61Q11/00)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A system and method for dental image file capture and manipulation for the purpose of dental, orthodontic, and periodontic tracking, diagnostics, and dental prosthetic and implant design. Augmented intelligence in dental file segmentation using descriptor matrixes with a common centroid or reference locus as a reference point describing related dental surface structures reduces the data size of dental image files such that dental images can be manipulated and compared to other dental files and can be used in machine learning and matching systems. This expedites the design and manufacture of dental prosthetics, appliances, and in dental monitoring and treatment.

## Claims

### Claim 1

A computer-implemented method for creating a 2D descriptor matrix representation of a 3D dental image comprising:
receiving, by a processor, a three dimensional (3D) dental image comprising a surface boundary;
slicing the 3D dental image into a plurality of two dimensional (2D) cross-sectional slicing planes;
for each of the 2D cross-sectional slicing planes:
extending a plurality of indexing rays from a reference locus to the surface boundary in the cross-sectional slicing plane; and
measuring a length from the reference locus to the surface boundary to generate a plurality of indexing ray lengths; and
storing the plurality of indexing ray lengths for each of the plurality of 2D cross-sectional slicing planes in a 2D matrix to create the 2D descriptor matrix of the 3D dental image.

### Claim 2 (depends on 1)

The method of claim 1, wherein the reference locus is a centroid or a basal plane on the slicing plane.

### Claim 3 (depends on 1)

The method of claim 1, wherein the surface boundary comprises one or more of a tooth surface, surface of a plurality of teeth, bitewing surface, gumline surface, dental arch surface, gum surface, neighbouring tooth surface, occlusal tooth surface on an opposite jaw to the dental object, arch surface, inside prosthetic surface, post surface, outside prosthetic surface, and appliance surface.

### Claim 4 (depends on 1)

The method of claim 1, further comprising training a convolutional autoencoder model using a convolutional neural network to identify matching 2D descriptor matrixes in a descriptor database.

### Claim 5 (depends on 1)

The method of claim 1, further comprising assigning a dental object type to the 2D descriptor matrix.

### Claim 6 (depends on 5)

The method of claim 5, wherein the dental object is a group of adjacent teeth, and wherein the method further comprises creating a matrix descriptor stack comprising a tooth 2D descriptor submatrix for each tooth in the group of adjacent teeth.

### Claim 7 (depends on 5)

The method of claim 5, further comprising matching the 2D descriptor matrix to a matched 2D descriptor matrix describing a matching dental object having the same dental object type.

### Claim 8 (depends on 1)

The method of claim 1, further comprising applying a visualization scheme to visualize the 2D descriptor matrix.

### Claim 9 (depends on 1)

The method of claim 1, further comprising using the 2D descriptor matrix in dental tracking, orthodontic tracking, periodontic tracking, oral diagnostics, dental prosthetic design, orthodontic device design, dental implant design, or surgery planning.

### Claim 10

A computer-implemented method for creating a 2D descriptor matrix representation of a 3D dental image comprising:
receiving, by a processor, a three dimensional (3D) dental image comprising a surface boundary;
extending a plurality of indexing rays from a centroid through the 3D image such that each of the plurality of indexing rays intersects with a point on the surface boundary of the 3D dental image;
for each of the plurality of indexing rays, measuring a length from the centroid to the surface boundary to generate a plurality of indexing ray lengths; and
storing the plurality of indexing ray lengths in a 2D matrix to create a 2D descriptor matrix of the 3D dental image.

### Claim 11 (depends on 10)

The method of claim 10, wherein the surface boundary comprises one or more of a tooth surface, surface of a plurality of teeth, bitewing surface, gumline surface, dental arch surface, gum surface, neighbouring tooth surface, occlusal tooth surface on an opposite jaw to the dental object, arch surface, inside prosthetic surface, post surface, outside prosthetic surface, and appliance surface.

### Claim 12 (depends on 10)

The method of claim 10, further comprising training a convolutional autoencoder model using a convolutional neural network to identify matching 2D descriptor matrixes in a descriptor database.

### Claim 13 (depends on 10)

The method of claim 10, further comprising assigning a dental object type to part of the 2D descriptor matrix.

### Claim 14 (depends on 13)

The method of claim 13, further comprising matching the 2D descriptor matrix to a matched 2D descriptor matrix describing a matching dental object having the same dental object type.

### Claim 15 (depends on 10)

The method of claim 10, wherein the dental object comprises one or more of a tooth, plurality of teeth, bitewing, gumline, dental arch, gum surface, neighbouring tooth surface, occlusal tooth surface on an opposite jaw to the dental object, arch surface, inside prosthetic surface, post surface, outside prosthetic surface, and appliance surface.

### Claim 16 (depends on 10)

The method of claim 10, further comprising applying a visualization scheme to visualize the 2D descriptor matrix.

### Claim 17

A computer-implemented method for creating a 2D descriptor matrix representation of a 3D image comprising:
receiving a three dimensional (3D) image;
extending a plurality of indexing rays from a reference locus through the 3D image such that each of the plurality of indexing rays intersects with a surface boundary of the 3D image
for each of the plurality of indexing rays, measuring a length from the reference locus to the surface boundary to generate a plurality of indexing ray lengths; and
storing the plurality of indexing ray lengths in a 2D matrix to create the 2D descriptor matrix of the 3D image.

### Claim 18 (depends on 17)

The method of claim 17, wherein the reference locus is a centroid or a basal plane.
