Noninvasive multimodal oral assessment systems

Patent metadata

Field	Value
Publication number	US-12400754-B2
Application number	US-202418673295-A
Country	US
Kind code	B2
Filing date	May 23, 2024
Priority date	Dec 11, 2020
Publication date	Aug 26, 2025
Grant date	Aug 26, 2025

Abstract

Methods and apparatuses (e.g., systems) for assessing oral health. In some examples, one or more periodontal pockets in a 3D model of a dental arch may be identified. The digital 3D model may be generated from scan data collected from an oral scan, where the scan data may include 3D surface data and one or more of: color image data, near-infrared (NIR) data, and fluorescence imaging data. A periodontal pocket depth may be determined for each periodontal pocket using a trained machine learning model, which may be trained on image data including previous 3D surface data and one or more of: previous color image data, previous NIR data, and previous fluorescence imaging data. An indicator of the determined periodontal pocket depth may be displayed on one or more 2D images and/or the digital 3D model of the subject's dental arch.

First claim

What is claimed is:

1. A system, the system comprising:
one or more processors;
a memory, accessible by the one or more processors and storing computer-program instructions, that, when executed by the one or more processors, perform a computer-implemented method comprising:
receiving or accessing a digital three-dimensional (3D) model of a dental arch of a subject, wherein the digital 3D model is generated from scan data collected from an oral scan of the subject's oral cavity including the dental arch, the scan data including 3D surface data and one or more of: color image data, near-infrared (NIR) data, and fluorescence imaging data;
identifying one or more periodontal pockets in the digital 3D model;
determining a periodontal pocket depth for each periodontal pocket of the identified one or more periodontal pockets at one or more locations of the digital 3D model using a trained machine learning model, wherein the trained machine learning model is trained on image data including previous 3D surface data and one or more of: previous color image data, previous NIR data, and previous fluorescence imaging data; and
outputting an indicator of the determined periodontal pocket depth for each periodontal pocket of the identified one or more periodontal pockets on one or more two-dimensional (2D) images and/or the digital 3D model of the subject's dental arch on a display.

2. The system of claim 1 , further comprising a hand-held wand having at least one image sensor and a plurality of light sources.

3. The system of claim 2 , wherein the plurality of light sources is configured to emit light at a visible light range, an infrared light range, and a fluorescence imaging range.

4. The system of claim 1 , wherein the computer-implemented method further comprises: capturing data of at least a portion of the subject's teeth as an intraoral scanner is moved over the subject's teeth, wherein the captured data includes the 3D surface data and the one or more of: color image data, NIR data, and fluorescence imaging data.

5. The system of claim 1 , wherein the scan data used to train the trained machine learning model is filtered based on a threshold angle between images of the color image data and a threshold distance between the images of the color image data.

6. The system of claim 1 , wherein identifying the one or more periodontal pockets comprises identifying the one or more periodontal pockets at a plurality of different locations of the digital 3D model.

7. The system of claim 1 , wherein the trained machine learning model is further trained based on periodontal chart data and/or visual inspection/tactile data.

8. The system of claim 1 , wherein the computer-implemented method further comprises monitoring changes to the one or more periodontal pockets at the one or more locations over time.

9. The system of claim 1 , further comprising accessing one or more previous scans for the subject and identifying one or more periodontal pockets and corresponding one or more periodontal pocket depths at the one or more locations using the one or more previous scans.

10. The system of claim 1 , wherein the computer-implemented method further comprises providing a time lapse video showing changes to the one or more periodontal pockets at the one or more locations over time.

11. The system of claim 1 , wherein the previous 3D surface data and the one or more of, the previous color image data, the previous NIR data, and the previous fluorescence imaging data is taken from the same patient or of one or more other patients.

12. The system of claim 1 , wherein the computer-implemented method further comprises outputting color-coded periodontal pocket depth indicators for each periodontal pocket of the identified one or more periodontal pockets on the one or more 2D images.

13. The system of claim 1 , wherein the computer-implemented method further comprises segmenting the scan data to identify teeth and the one or more periodontal pockets.

14. The system of claim 1 , wherein the 3D model is generated from the scan data that only includes the 3D surface data and the one or more of: color image data, NIR data, and fluorescence imaging data.

15. The system of claim 1 , wherein the scan data does not include x-ray image data.

16. A system, the system comprising:
a hand-held wand comprising at least one image sensor and one or more light sources configured to emit light at a visible light range, an infrared light range and a fluorescence imaging range;
one or more processors;
a memory, accessible by the one or more processors and storing computer-program instructions, that, when executed by the one or more processors, perform a computer-implemented method comprising:
receiving or accessing a digital three-dimensional (3D) model of a dental arch of a subject, wherein the digital 3D model is generated from scan data collected from a scan of the subject's oral cavity, including the dental arch, the scan data including 3D surface data and one or more of: color image data, near-infrared (NIR) data, and fluorescence imaging data;
segmenting the digital 3D model to identify teeth and one or more periodontal pockets in the digital 3D model;
identifying a corresponding periodontal pocket depth for each periodontal pocket of the identified one or more periodontal pockets at one or more locations of the digital 3D model using a trained machine learning model, wherein the trained machine learning model is trained on image data including previous 3D surface data and one or more of: previous color image data, previous NIR data, and previous fluorescence imaging data; and
outputting the corresponding periodontal pocket depth for each periodontal pocket of the identified one or more periodontal pockets on one or more two-dimensional (2D) images and/or the digital 3D model of the subject's dental arch on a display.

17. The system of claim 16 , wherein the scan data used to train the trained machine learning model is filtered based on a threshold angle between images of the color image data and a threshold distance between the images of the color image data.

18. The system of claim 16 , wherein the trained machine learning model is further trained based on periodontal chart data and/or visual inspection/tactile data.

19. The system of claim 16 , wherein the computer-implemented method further comprises monitoring changes to the one or more periodontal pockets at the one or more locations over time.

20. The system of claim 16 , further comprising accessing one or more previous scans for the subject and identifying one or more periodontal pockets and corresponding one or more periodontal pocket depths at the one or more locations using the one or more previous scans.

21. The system of claim 16 , wherein the computer-implemented method further comprises providing a time lapse video showing changes to the one or more periodontal pockets at the one or more locations over time.

22. The system of claim 16 , wherein the previous 3D surface data and the one or more of, the previous color image data, the previous NIR data, and the previous fluorescence imaging data is taken from the same patient or of one or more other patients.

23. The system of claim 16 , wherein the computer-implemented method further comprises outputting color-coded periodontal pocket depth indicators for each periodontal pocket of the identified one or more periodontal pockets on the one or more 2D images.

24. A system

Assignees

• Align Technology Inc

Inventors

• Farkash Shai
• Atiya Yossef
• Moshe Maayan
• Ben-Dov Moti
• Levy Raphael
• Malka Doron

Classifications

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G06T2207/30096

  Tumor; Lesion · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10064

  Fluorescence image · CPC title

• G06T2207/10048

  Infrared image · CPC title