Predicting shapes of at least partially un-erupted teeth

Patent metadata

Field	Value
Publication number	US-12099342-B2
Application number	US-202318333483-A
Country	US
Kind code	B2
Filing date	Jun 12, 2023
Priority date	Mar 31, 2017
Publication date	Sep 24, 2024
Grant date	Sep 24, 2024

Abstract

Computer readable media for predicting a tooth shape for at least partially un-erupted teeth and dental appliances formed therefrom. In some examples, methods include generating orthoscopic views of virtual representations of an identified tooth type in different orthogonal directions, representing bounding shapes around the orthoscopic views, and applying principal component analysis on the bounding shapes to predict a tooth shape. In some examples, methods include generating a spherical harmonic signature for virtual representations of an identified tooth type, calculating a distance between spherical harmonic signatures to predict the tooth shape. The predicted tooth shape of the at least partially un-erupted tooth may be incorporated into virtual dentition model(s) of a dentition in accordance with an orthodontic treatment plan for treating the dentition.

First claim

What is claimed is:

1. A non-transitory computer-readable medium that has instructions stored thereon and that is executable by a processor to cause one or more computing devices to:
identify a tooth type of an at least partially un-erupted tooth in a patient's dentition;
access a dataset comprising a plurality of three-dimensional (3D) virtual representations of the identified tooth type; and
predict a tooth shape for the at least partially un-erupted tooth using an elliptic Fourier technique or a spherical harmonic technique,
wherein the elliptic Fourier technique comprises:
generating orthoscopic views of each of the plurality of 3D virtual representations in different orthogonal directions;
representing bounding shapes around the orthoscopic views using elliptic Fourier descriptors; and
applying principal component analysis on the bounding shapes to predict the tooth shape for the at least partially un-erupted tooth; and

wherein the spherical harmonic technique comprises:
generating a spherical harmonic 3D signature for each of the plurality of 3D virtual representations; and
calculating a distance between spherical harmonic signatures to predict the tooth shape for the at least partially un-erupted tooth;

incorporate the predicted tooth shape of the at least partially un-erupted tooth into one or more virtual dentition models of the patient's dentition in accordance with an orthodontic treatment plan for treating the patient's dentition.

2. The non-transitory computer-readable medium of claim 1 , wherein the plurality of 3D virtual representations of the identified tooth type are gathered from a database having a plurality of teeth representations of a variety of patient teeth.

3. The non-transitory computer-readable medium of claim 1 , wherein the orthoscopic views are two-dimensional (2D) views.

4. The non-transitory computer-readable medium of claim 1 , wherein generating each of the orthoscopic views includes flattening vertices of a tooth mesh by removing one dimension of a corresponding 3D virtual representation.

5. The non-transitory computer-readable medium of claim 1 , wherein the spherical harmonic 3D signature for each of the plurality of 3D virtual representations are calculated over a set of normalized radii.

6. The non-transitory computer-readable medium of claim 1 , wherein generating the spherical harmonic 3D signature for each of the plurality of 3D virtual representations comprises summing spherical harmonics for each point of a voxelized sphere over a specific frequency range.

7. The non-transitory computer-readable medium of claim 1 , wherein calculating the distance between the spherical harmonic signatures comprises computing a Euclidean distance between the spherical harmonic signatures.

8. The non-transitory computer-readable medium of claim 1 , wherein generating a spherical harmonic 3D signature for each of the plurality of 3D virtual representations comprises:
scaling a length of the longest axis of each tooth of the plurality of 3D virtual representations;
forming a voxelized sphere for each tooth in an array having uniform size; and
summing spherical harmonics for each point of the voxelized sphere of each tooth.

9. The non-transitory computer-readable medium of claim 1 , wherein the instructions further comprise forming a virtual 3D tooth shape for the at least partially un-erupted tooth using the predicted tooth shape.

10. The non-transitory computer-readable medium of claim 1 , wherein the instructions further comprise determining a cavity shape of a dental appliance for accommodating the at least partially un-erupted tooth using the predicted tooth shape.

11. The non-transitory computer-readable medium of claim 10 , wherein determining the cavity shape comprises determining a scaling factor for scaling a size of the predicted tooth shape.

12. The non-transitory computer-readable medium of claim 10 , wherein the instructions further comprise generating instructions for fabricating the dental appliance having a cavity for the at least partially un-erupted tooth determined using the predicted tooth shape, wherein the cavity has the determined cavity shape.

13. A dental aligner comprising:
a plurality of cavities configured to reposition teeth from first arrangement toward second arrangement, the plurality of cavities including:
one or more first cavities configured to receive one or more permanent teeth; and
one or more second cavities located at one or more regions of an at least partially un-erupted tooth, wherein a shape of the one or more second cavities is formed based on a predicted tooth shape for the at least partially un-erupted tooth calculated using an elliptic Fourier technique or a spherical harmonic technique,
wherein the elliptic Fourier technique comprises:
generating orthoscopic views of each of a plurality of three-dimensional (3D) virtual representations in different orthogonal directions;
representing bounding shapes around the orthoscopic views using elliptic Fourier descriptors; and
applying principal component analysis on the bounding shapes to predict the tooth shape for the at least partially un-erupted tooth; and

wherein the spherical harmonic technique comprises:
generating a spherical harmonic 3D signature for each of the plurality of 3D virtual representations; and
calculating a distance between spherical harmonic signatures to predict the tooth shape for the at least partially un-erupted tooth.

14. The dental aligner of claim 13 , wherein the plurality of 3D virtual representations are gathered from a database having a plurality of teeth representations of a variety of patient teeth.

15. The dental aligner of claim 13 , wherein the dental aligner is made of a polymer.

16. The dental aligner of claim 13 , wherein generating each of the orthoscopic views includes flattening vertices of a tooth mesh by removing one dimension of a corresponding 3D virtual representation.

17. The dental aligner of claim 13 , wherein the spherical harmonic 3D signature for each of the plurality of 3D virtual representations is calculated over a set of normalized radii.

18. The dental aligner of claim 13 , wherein generating the spherical harmonic 3D signature for each of the plurality of 3D virtual representations comprises summing spherical harmonics for each point of a voxelized sphere over a specific frequency range.

19. The dental aligner of claim 13 , wherein calculating the distance between the spherical harmonic signatures comprises computing a Euclidean distance between the spherical harmonic signatures.

20. The dental aligner of claim 13 , wherein generating a spherical harmonic 3D signature for each of the plurality of 3D virtual representations comprises:
scaling a length of the longest axis of each tooth of the plurality of 3D virtual representations;
forming a voxelized sphere for each tooth in an array having uniform size; and
summing spherical harmonics for each point of the voxelized sphere of each tooth.

Assignees

• Align Technology Inc

Inventors

• Cramer Christopher Eric
• Choi Jeeyoung

Classifications

• G05B2219/45167

  Dentist, dental manufacture · CPC title

• B33Y50/00

  Data acquisition or data processing for additive manufacturing · CPC title

• G05B2219/35134

  3-D cad-cam · CPC title

• B29L2031/7536

  Artificial teeth · CPC title

• G05B2219/33034

  Online learning, training · CPC title