IP Library Granted Patent US 12,450,848
Granted Patent B2
US 12,450,848 · App. 17/916,278 · Granted Oct 21, 2025

Method for automatic creation of 3D models for dental and orthodontic use

Inventors: Marc Lemchen (New York, NY); Todd Blankenbecler (Atlanta, GA); Alan Yan (New York, NY); Ryan Goy (Redondo Beach, CA); Vijay Dhaka (Huntington Beach, CA)
Assignee: CADFLOW
G06T19/20A61C7/02A61C7/146G06T2210/41G06T2219/2021
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 12,450,848
App. No.
17/916,278
Filed
Sep 30, 2022
Granted
Oct 21, 2025
Kind
B2
Art Unit
3772
USPC
433/24
Abstract

A system and method that is a web based application for creating and managing 3D models used in orthodontic laboratory prescriptions within a dental clinic or lab. The method includes automatically detecting and removing any appliances contained within the 3D image file. After the appliances have been removed, the system then automatically replaces the removed image data with new image data that is calculated to approximate the surface of the tooth disposed beneath the deleted appliance in order to create a clean, second 3D image. The method may further automatically refine the second 3D image of the patients teeth or delete any artifacts which remain after creation of the second 3D image. The second 3D image may then be used as the basis on which to change the patients orthodontic or dental prescription.

Claims (20)

1. A method for automatically creating a 3D dental model comprising:

uploading a first 3D image to an uploads database;

detecting image data corresponding to at least one appliance within the first 3D image, wherein detecting the image data comprises dividing the first 3D image into a segmented mesh and a plurality of bracket meshes;

deleting the detected image data corresponding to the at least one appliance from the first 3D image, wherein deleting the detected image data comprises deleting the detected image data from the segmented mesh;

inferring, using machine learning techniques trained on a dataset of intraoral scans without brackets, 3D image data calculated to approximate the surface of a tooth disposed beneath the deleted image data to create a second 3D image, wherein inferring 3D image data comprises inferring 3D image data from the plurality of bracket meshes; and

saving the second 3D image to a processed database,

wherein the steps of detecting and deleting the image data corresponding to the at least one appliance from the first 3D image and the step of inferring 3D image data calculated to approximate the surface of a tooth to create a second 3D image are automatically performed in sequence.

2. The method of claim 1 further comprising refining the inferred 3D image data of the second 3D image corresponding to the surface of the tooth disposed beneath the deleted image data corresponding to the at least one appliance.

3. The method of claim 2 wherein refining the inferred 3D image data of the second 3D image corresponding to the surface of the tooth disposed beneath the deleted image data corresponding to the at least one appliance comprises trimming at least a portion of the inferred 3D image data of the second 3D image corresponding to the surface of the tooth disposed beneath the deleted image data corresponding to the at least one appliance.

4. The method of claim 2 wherein refining the inferred 3D image data of the second 3D image corresponding to the surface of the tooth disposed beneath the deleted image data corresponding to the at least one appliance comprises adding to at least a portion of the inferred 3D image data corresponding to the surface of the tooth disposed beneath the deleted image data corresponding to the at least one appliance.

5. The method of claim 2 wherein refining the inferred 3D image data of the second 3D image corresponding to the surface of the tooth disposed beneath the deleted image data corresponding to the at least one appliance comprises defining an intersection between the inferred 3D image data corresponding to the surface of the tooth disposed beneath the deleted image data corresponding to the at least one appliance and image data corresponding to a gumline of the patient within the second 3D image.

6. The method of claim 2 wherein refining the inferred 3D image data of the second 3D image corresponding to the surface of the tooth disposed beneath the deleted image data corresponding to the at least one appliance comprises smoothening at least a portion of the inferred 3D image data corresponding to the surface of the tooth disposed beneath the deleted image data corresponding to the at least one appliance.

7. The method of claim 2 wherein refining the inferred 3D image data of the second 3D image corresponding to the surface of the tooth disposed beneath the deleted image data corresponding to the at least one appliance comprises deleting any artifacts from the inferred 3D image data of the second 3D image.

8. The method of claim 1 wherein saving the second 3D image to the processed database is performed automatically in sequence after inferring the 3D image data calculated to approximate the surface of the tooth disposed beneath the deleted image data.

9. The method of claim 1 wherein detecting the image data corresponding to the at least one appliance within the first 3D image comprises detecting image data corresponding to an orthodontic bracket.

10. The method of claim 1 further comprising transmitting metadata related to the first 3D image to a server in communication with the uploads database and the processed database.

11. The method of claim 10 further comprising sending the first 3D image from the server to a queue before detecting image data corresponding to at least one appliance within the first 3D image.

12. The method of claim 1 wherein uploading the first 3D image to the uploads database comprises automatically saving the first 3D image to a file storage within the uploads database.

13. The method of claim 1 wherein uploading a first 3D image to the uploads database comprises uploading a first STL file comprising the first 3D image.

14. The method of claim 1 wherein saving the second 3D image to the processed database comprises saving the second 3D image to a file storage within the processed database.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 11, 2022
From: LEMCHEN, MARC; BLANKENBECLER, TODD; YAN, ALAN; GOY, RYAN; DHAKA, VIJAY
To: CADFLOW
Reel/Frame 061382/0182 →
Continuity (2)
Provisional Application 63003568 · Apr 1, 2020
Related Publication 20230149130A1 · May 18, 2023
References Cited (26)
US 5748199A · Palm · 1998 [cited by examiner]
US 6476803B1 · Zhang · 2002 [cited by examiner]
US 9503282B2 · Kody · 2016 [cited by examiner]
US 9737257B2 · Ribnick · 2017 [cited by examiner]
US 10413385B2 · Sherwood · 2019 [cited by examiner]
US 10548691B2 · Lemchen · 2020 [cited by examiner]
US 11103330B2 · Webber · 2021 [cited by examiner]
US 20030021453A1 · Weise · 2003 [cited by applicant]
US 20090310846A1 · Lemchen · 2009 [cited by examiner]
US 20110004331A1 · Cinader, Jr. · 2011 [cited by applicant]
US 20130325431A1 · See · 2013 [cited by examiner]
US 20140067334A1 · Kuo · 2014 [cited by examiner]
US 20140195892A1 · Hampton · 2014 [cited by examiner]
US 20150097827A1 · Cohen · 2015 [cited by examiner]
US 20150235399A1 · Shechtman · 2015 [cited by examiner]
US 20160027151A1 · Edwin · 2016 [cited by examiner]
US 20180206939A1 · Kim · 2018 [cited by examiner]
US 20190147666A1 · Keustermans · 2019 [cited by examiner]
US 20190231490A1 · Sabina et al. · 2019 [cited by applicant]
US 20190287224A1 · Amirghodsi · 2019 [cited by examiner]
US 20200015936A1 · Ye · 2020 [cited by examiner]
US 20230048898A1 · Cofar · 2023 [cited by examiner]
US 20230051506A1 · Cofar · 2023 [cited by examiner]
US 20230068727A1 · Saphier · 2023 [cited by examiner]
WO 2018170426 · 2018 [cited by applicant]
Extended European Search Report dated Jun. 18, 2024, EP Application No. 21782069, 10 pages. [cited by applicant]