Diagnostic intraoral methods and apparatuses

Patent metadata

Field	Value
Publication number	US-12268574-B2
Application number	US-202318365201-A
Country	US
Kind code	B2
Filing date	Aug 3, 2023
Priority date	Jan 26, 2018
Publication date	Apr 8, 2025
Grant date	Apr 8, 2025

Abstract

Intraoral scanning systems configured to perform computer-implemented methods for identifying dental features. The methods may include engaging a trained machine learning network to identify one or more dental features in one or more regions of a patient's dentition. Each of the dental features may be present in at least one of multiple records. Each of the records may include multiple images of the patient's dentition and may be taken with a different imaging modality. The confidence score may be determined or adjusted using a 3 D model of the patient's dentition. The confidence score may be determined or adjusted based on the region of the patient's dentition within each record. The methods may include displaying an indicator of each dental feature that has a confidence score that is above a threshold on the 3 D model of the patient's dentition, and modifying the display as a user adjusts the threshold.

First claim

What is claimed is:

1. An intraoral scanning system, the system comprising:
an imaging sensor; and
one or more processors, the one or more processors having a memory configured to store computer-program instructions, that, when executed by the one or more processors, perform a computer-implemented method comprising:
engaging a trained machine learning network to identify one or more dental features in one or more regions of a patient's dentition, wherein each of the one or more dental features is present in at least one of a plurality of records, wherein each of the plurality of records comprises a plurality of images of the patient's dentition, and wherein each of the plurality of records is taken with a different imaging modality;
determining or adjusting a confidence score for the one or more dental features using a three-dimensional (3D) model of the patient's dentition, wherein each of the plurality of records is correlated to the 3D model of the patient's dentition, further wherein the confidence score is determined or adjusted based on the region of the patient's dentition within each of the plurality of records;
displaying an indicator of each dental feature of the one or more dental features that has a confidence score that is above a threshold on the 3D model of the patient's dentition; and
modifying the display as a user adjusts the threshold.

2. The system of claim 1 , further comprising segmenting the 3D model of the patient's dentition.

3. The system of claim 1 , wherein the one or more dental features comprises one or more of: cracks, gum recess, tartar, enamel thickness, pits, caries, fissures, evidence of grinding, and interproximal voids.

4. The system of claim 1 , wherein the one or more dental features comprises caries.

5. The system of claim 1 , wherein engaging the trained machine learning network to identify the one or more dental features comprises engaging the trained machine learning network to identify the one or more dental features from a first record taken in a near-infrared (near IR) modality.

6. The system of claim 5 , further comprising mapping the regions corresponding to each of the one or more dental features to one or more additional records taken in a different imaging modality using the 3D model of the patient's dentition.

7. The system of claim 6 , wherein determining or adjusting the confidence score for the one or more dental features is based on the regions corresponding to each of the one or more dental features from the one or more additional records.

8. The system of claim 1 , wherein displaying comprises displaying an indicator of the confidence score.

9. The system of claim 1 , wherein modifying comprises making the threshold more or less stringent and showing an addition or removal of corresponding one or more dental features.

10. An intraoral scanning system, the system comprising:
an imaging sensor; and
one or more processors, the one or more processors having a memory configured to store computer-program instructions, that, when executed by the one or more processors, perform a computer-implemented method comprising:
engaging a trained machine learning network to identify one or more dental features in one or more regions of a patient's dentition, wherein each of the one or more dental features is present in at least one of a plurality of records, wherein each of the plurality of records comprises a plurality of images of the patient's dentition, and wherein each of the plurality of records is taken with a different imaging modality;
mapping the regions corresponding to each of the one or more dental features to one or more additional records taken in a different imaging modality using a three-dimensional (3D) model of the patient's dentition;
determining or adjusting a confidence score for the one or more dental features using the 3D model of the patient's dentition, wherein each of the plurality of records is correlated to the 3D model of the patient's dentition, further wherein the confidence score is determined or adjusted based on the region of the patient's dentition within each of the plurality of records;
displaying an indicator of each dental feature of the one or more dental features that has a confidence score that is above a threshold on the 3D model of the patient's dentition; and
modifying the display as a user adjusts the threshold.

11. The system of claim 10 , wherein determining or adjusting the confidence score for the one or more dental features is based on the regions corresponding to each of the one or more dental features from the one or more additional records.

12. The system of claim 10 , further comprising segmenting the 3D model of the patient's dentition.

13. The system of claim 10 , wherein engaging the trained machine learning network to identify the one or more dental features comprises engaging the trained machine learning network to identify the one or more dental features from a first record taken in a near-infrared (near IR) modality.

14. The system of claim 13 , wherein identifying the one or more dental features in the first record comprises identifying one or more of: cracks, gum recess, tartar, enamel thickness, pits, caries, fissures, evidence of grinding, and interproximal voids.

15. The system of claim 14 , wherein identifying the dental feature in the first record comprises identifying caries.

16. The system of claim 10 , wherein displaying comprises displaying an indicator of the confidence score.

17. The system of claim 10 , wherein modifying comprises making the threshold more or less stringent and showing an addition or removal of corresponding one or more dental features.

18. An intraoral scanning system, the system comprising:
a dental scanning wand including an imaging sensor; and
one or more processors, the one or more processors having a memory configured to store computer-program instructions, that, when executed by the one or more processors, perform a computer-implemented method comprising:
engaging a trained machine learning network to identify one or more dental features in one or more regions of a patient's dentition, wherein each of the one or more dental features is present in at least one of a plurality of records, wherein each of the plurality of records comprises a plurality of images of the patient's dentition, and wherein each of the plurality of records is taken with a different imaging modality;
determining or adjusting a confidence score for the one or more dental features using a three-dimensional (3D) model of the patient's dentition, wherein each of the plurality of records is correlated to the 3D model of the patient's dentition, further wherein the confidence score is determined or adjusted based on the region of the patient's dentition within each of the plurality of records;
displaying an indicator of each dental feature of the one or more dental features that has a confidence score that is above a threshold on the 3D model of the patient's dentition; and
modifying the display as a user adjusts the threshold.

19. The system of claim 18 , wherein engaging the trained machine learning network to identify the one or more dental features comprises engaging the trained machine learning network to identify the one or more dental features from a first record taken in a near-infrared (near IR) modality.

20. The system of claim 19 , further comprising mapping the regions corresponding to each of the one or more dental features to one or more additional records taken in a different imagin

Assignees

• Align Technology Inc

Inventors

• Sabina Michael
• Kopelman Avi
• Kuo Eric
• Elbaz Gilad
• Weiss Assaf
• Malka Doron
• Saphier Ofer
• Nizard Eliahou Franklin
• Tishel Ido
• Ayal Shai
• Moshe Maayan

Classifications

• G06T2207/30036

  Dental; Teeth · CPC title

• A61C13/0019

  using three dimensional printing · CPC title

• A61B5/0086

  using infrared radiation · CPC title

• A61B5/0066

  Optical coherence imaging · CPC title

• A61C13/34

  Making or working of models, e.g. preliminary castings, trial dentures; Dowel pins [4] · CPC title