Machine learning scoring system and methods for tooth position assessment

Patent metadata

Field	Value
Publication number	US-11534272-B2
Application number	US-201916569345-A
Country	US
Kind code	B2
Filing date	Sep 12, 2019
Priority date	Sep 14, 2018
Publication date	Dec 27, 2022
Grant date	Dec 27, 2022

Abstract

Provided herein are systems and methods for scoring a post-treatment tooth position of a patient's teeth. A patient's dentition may be scanned and/or segmented. Raw dental features, principal component analysis (PCA) features, and/or other features may be extracted and compared to those of other teeth, such as those obtained through automated machine learning systems. A classifier can identify and/or output the post-treatment tooth position of the patient's teeth.

First claim

What is claimed is:

1. A method of automatically determining a post-treatment tooth position score of a patient's teeth, the method comprising the steps of:
acquiring, in a computing device, a three-dimensional (3D) model of the patient's teeth;
determining, in the computing device, raw features of the patient's teeth from the 3D model of the patient's teeth;
creating, in the computing device, engineered features from the raw features of the patient's teeth;
applying the engineered features to a binary classifier, a linear classifier, or some combination thereof, of the computing device; and
outputting from the computing device the post-treatment tooth position score of the patient's teeth.

2. The method of claim 1 , further comprising processing, in the computing device, the raw features of the patient's teeth to account for missing teeth, teeth to be extracted, or teeth that are not to be moved during treatment.

3. The method of claim 1 , wherein outputting comprises outputting a binary score indicating that a doctor is likely to reject the post-treatment tooth position or accept the post-treatment tooth position.

4. The method of claim 1 , wherein outputting comprises outputting a linear score indicating along a scale how likely a doctor is to accept or reject the post-treatment tooth position.

5. The method of claim 1 , wherein the creating engineered features step further comprises taking a principal component analysis (PCA) of the raw features of the patient's teeth.

6. The method of claim 1 , wherein the creating engineered features step further comprises which performing automated feature exploration of neighboring teeth dependency and local/regional arch shape from the raw features of the patient's teeth.

7. The method of claim 6 , wherein the automated feature exploration is performed with a neural network.

8. The method of claim 1 , wherein the creating engineered features step further comprises taking a principal component analysis (PCA) of the raw features of the patient's teeth and performing automated feature exploration of neighboring teeth dependency and local/regional arch shape from the raw features of the patient's teeth.

9. The method of claim 1 , further comprises taking the 3D model of the patient's teeth.

10. The method of claim 9 , wherein the 3D model is acquired from a three-dimensional scanner.

11. The method of claim 9 , wherein the 3D model is acquired from a mold of the patient's teeth.

12. A non-transitory computing device readable medium having instructions stored thereon for determining a post-treatment tooth position score of a patient's teeth, wherein the instructions are executable by a processor to cause a computing device to:
acquire a three-dimensional (3D) model of the patient's teeth;
determine raw features of the patient's from the 3D model of the patient's teeth;
create engineered features from the raw features of the patient's teeth;
apply the engineered features to a binary classifier, a linear classifier, or some combination thereof, of the computing device; and
output the post-treatment tooth position score of the patient's teeth.

13. The non-transitory computing device readable medium of claim 12 , wherein the instructions are further configured to process the raw features of the patient's teeth to account for missing teeth, teeth to be extracted, or teeth that are not to be moved during treatment.

14. The non-transitory computing device readable medium of claim 12 , wherein the instructions are further configured so that the output is a binary score indicating that a doctor is likely to reject the post-treatment tooth position or accept the post-treatment tooth position.

15. The non-transitory computing device readable medium of claim 12 , wherein the instructions are further configured so that the output is a linear score indicating along a scale how likely a doctor is to accept or reject the post-treatment tooth position.

16. The non-transitory computing device readable medium of claim 12 , wherein the instructions are further configured to create engineered features by taking a principal component analysis (PCA) of the raw features of the patient's teeth.

17. The non-transitory computing device readable medium of claim 12 , wherein the instructions are further configured to create engineered features by performing automated feature exploration of neighboring teeth dependency and local/regional arch shape from the raw features of the patient's teeth.

18. The non-transitory computing device readable medium of claim 12 , wherein the instructions are further configured to create engineered features by taking a principal component analysis (PCA) of the raw features of the patient's teeth and further configured to create engineered features by performing automated feature exploration of neighboring teeth dependency and local/regional arch shape from the raw features of the patient's teeth.

19. The non-transitory computing device readable medium of claim 17 wherein the automated feature exploration is performed with a neural network.

20. The non-transitory computing device readable medium of claim 12 , wherein the instructions are further configured to acquire the 3D model from a three-dimensional scanner.

21. A method of automatically determining a post-treatment tooth position score of a patient's teeth, the method comprising the steps of:
acquiring, in a computing device, a three-dimensional (3D) model of the patient's teeth;
rendering the 3D model of the patient's teeth into one or more 2D images of the patient's teeth;
determining, in the computing device, raw features of the patient's teeth from the one or more 2D images;
creating, in the computing device, engineered features from the raw features of the patient's teeth;
applying the engineered features to a binary classifier, a linear classifier, or some combination thereof, of the computing device; and
outputting from the computing device the post-treatment tooth position score of the patient's teeth.

22. The method of claim 21 , further comprising processing, in the computing device, the raw features of the patient's teeth to account for missing teeth, teeth to be extracted, or teeth that are not to be moved during treatment.

23. The method of claim 22 , wherein outputting comprises outputting a binary score indicating that a doctor is likely to reject the post-treatment tooth position or accept the post-treatment tooth position.

24. The method of claim 22 , wherein outputting comprises outputting a linear score indicating along a scale how likely a doctor is to accept or reject the post-treatment tooth position.

Assignees

• Align Technology Inc

Inventors

• Li Guotu
• Cramer Christopher E
• Brown Chad Clayton
• Spiridonov Anton

Classifications

• A61C7/08

  Mouthpiece-type retainers {or positioners, e.g. for both the lower and upper arch (arch-shaped medicament applicators for teeth or gums A61C19/063; mouthguards for protecting the teeth of sportsmen A63B71/085)} · CPC title

• A61C9/0053 Primary

  Optical means or methods, e.g. scanning the teeth by a laser or light beam · CPC title

• A61B5/0088

  for oral or dental tissue · CPC title

• A61B5/7264

  Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems · CPC title

• G16H50/20

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