IP Library › Granted Patent US 12,048,600
Granted Patent B2
US 12,048,600 · App. 17/321,831 · Granted Jul 30, 2024

Dental CAD automation using deep learning

Inventors: Sergei Azernikov (Irvine, CA); Sergey Nikolskiy (Irvine, CA)
Assignee: James R. Glidewell Dental Ceramics, Inc.
A61C13/0004A61C9/0053G06F30/00G06N3/045G06N3/08
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,048,600
App. No.
17/321,831
Granted
Jul 30, 2024
Kind
B2
Abstract

Computer-implemented methods for generating a 3D dental prosthesis model are disclosed herein. The methods comprise training a deep neural network to generate a first 3D dental prosthesis model using a training data set; receiving a patient scan data representing at least a portion of a patient's dentition; and generating, using the trained deep neural network, the first 3D dental prosthesis model based on the received patient scan data.

Claims (26)

1. A computer-implemented method for generating dental restoration associated with dental model of dentition, the method comprising:

receiving, a the one or more computing devices, a patient scan data representing at least a portion of a patient's dentition; and

generating, using a trained deep neural network, a first 3D dental prosthesis model based on the received patient scan data,

wherein the trained deep neural network comprises a generative adversarial network (GAN).

2. The method of claim 1 , wherein the trained deep neural network is trained to generate the first 3D dental prosthesis model using a training data set.

3. The method of claim 2 , wherein the training data set comprises a dentition scan data set with preparation site data and a dental prosthesis data set, wherein the dental prosthesis data set comprises scanned prosthesis data associated with each preparation site in the dentition scan data set.

4. The method of claim 3 , wherein the dental prosthesis data set comprises scanned data of real crowns created based on a library tooth template.

5. The method of claim 4 , wherein the library tooth template comprises 32 tooth templates.

6. The method of claim 5 , wherein the real crowns are created by technicians using the 32 tooth templates.

7. The method of claim 3 , wherein the dentition scan data set with preparation site data comprises scanned data of real preparation sites from patients' scanned dentitions.

8. The method of claim 3 , further comprising generating, using a second trained deep neural network, a second 3D dental prosthesis model based on the received patient scan data.

9. The method of claim 8 , wherein the second trained deep neural network is trained using a natural dentition scan data set with digitally fabricated preparation site data and a natural dental prosthesis data set, wherein the natural dental prosthesis data set comprises segmented tooth associated with each digitally fabricated preparation site in the dentition scan data set.

10. The method of claim 8 , further comprising blending together features of the first and second 3D dental prosthesis models to generate a blended 3D dental prosthesis model.

11. The method of claim 2 , wherein the training data set comprises a natural dentition scan data set with digitally fabricated preparation site data and a natural dental prosthesis data set, wherein the dental prosthesis data set comprises segmented tooth data associated with each digitally fabricated preparation site in the dentition scan data set.

12. The method of claim 11 , wherein the segmented tooth data are generated by segmenting tooth data from the natural dentition scan data set.

13. The method of claim 12 , further comprising:

receiving a patient's profile information; and

selecting one or more dentition scan data sets that match with the patient's profile information, wherein the natural dentition scan data only include matched dentition scan data sets.

14. The method of claim 1 , wherein the first 3D dental prosthesis model comprises a crown, an inlay, a bridge or an implant.

15. A computer-implemented method for generating dental restoration associated with dental model of dentition, the method comprising:

receiving, by a one or more computing devices, a patient scan data representing at least a portion of a patient's dentition; and

generating, using a trained deep neural network, a first 3D dental prosthesis model based on the received patient scan data,

generating, using a second trained deep neural network, a second 3D dental prosthesis model based on the received patient scan data,

wherein the trained deep neural network comprises a generative adversarial network (GAN).

16. The method of claim 15 , wherein the trained deep neural network is trained using a dentition scan data set with preparation site data and a dental prosthesis data set and wherein the second trained deep neural network is trained using a natural dentition scan data set with digitally fabricated preparation site data and a natural dental prosthesis data set, wherein the natural dental prosthesis data set comprises segmented tooth associated with each digitally fabricated preparation site in the dentition scan data set.

17. The method of claim 15 , further comprising blending together features of the first and second 3D dental prosthesis models to generate a blended 3D dental prosthesis model.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 13, 2021
From: AZERNIKOV, SERGEI; NIKOLSKIY, SERGEY
To: JAMES R. GLIDEWELL DENTAL CERAMICS, INC.
Reel/Frame 057171/0141 →
Continuity (2)
Continuation 15925078 · Mar 19, 2018
Related Publication 20210267730A1 · Sep 2, 2021
Cited By (7)
US 12,496,137 US 12,636,082 US 12,648,815 US 12,661,133 US 12,678,173 US 12,702,484 US 12,740,830