IP Library › Granted Patent US 12,725,254
Granted Patent B2
US 12,725,254 · App. 18/570,698 · Granted Sep 1, 2026

Dental procedures

Inventors: Hans-Christian Schneider (Einhausen, DE); David Schader (Burstadt, DE); Helmut Seibert (Alsbach-Hahnlein, DE)
Assignee: Dentsply Sirona Inc.
G06T7/0012G06T19/20G06T2207/30036
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 12,725,254
App. No.
18/570,698
Granted
Sep 1, 2026
Kind
B2
Abstract

The present teachings relate to a method for transforming a digital 3D dental model to a 2D dental image, the method including: providing, at least two selected images from the 3D dental model; converting, each of the selected images, to a respective color component of a color model; obtaining, by combining the respective color components, the 2D image in a computer-readable format of the color model. The present teachings also relate to a method of classification of the 2D image, a dental procedure assisting system, uses and computer software products.

Claims (44)

1 . A computer-implemented method for classifying a dental structure using a trained data-driven logic comprising:

accessing a first 2D image and a second 2D image, the first and second 2D images of a color 3D model of the dental structure;

converting the first 2D image to include only a first color component of a multi-color model, the first color component being a constituent color channel from the multi-color model;

converting the second 2D image to include only a second color component of the multi-color model, the second color component being a different constituent color channel than that of the first color component;

compositing the converted first 2D image and the converted second 2D image to produce a composite 2D image;

providing, as an input, a composite 2D image to the trained data-driven logic;

determining, via the trained data-driven logic, a classification value of the composite 2D image;

wherein the first and second 2D images are dissimilar computerized acquisitions of the dental structure that were used to generate the color 3D model.

2 . The method of claim 1 , wherein the data-driven logic comprises a convolutional neural network.

3 . The method of claim 1 , further comprising:

generating, in response to the classification value, an output signal.

4 . The method of claim 3 , wherein the classification value and/or the output signal is provided to a human machine interface (“HMI”).

5 . The method of claim 4 , wherein the output signal is indicative of a dental procedure.

6 . The method of claim 5 , further comprising:

automatically selecting and configuring, in response to the classification value and/or the output signal, a tool from a plurality of available tools for use in the dental procedure, wherein the plurality of available tools include a milling tool, a grinding tool, and a printing tool.

7 . The method of claim 5 , further comprising:

receiving, via the HMI, a feedback input indicative of whether the dental procedure indicated by the output signal is to be performed or not.

8 . The method of claim 3 , further comprising:

using the classification value and/or the output signal for assisting and/or performing a dental procedure.

9 . The method of claim 1 , further comprising:

providing, at a memory storage, the composite 2D image, and optionally also a feedback input.

10 . The method of claim 1 , further comprising:

providing, at an input of data-driven logic, model training data comprising a plurality of 2D images, and optionally also a feedback input; whereby the model training data is used to train the data-driven logic to obtain the trained data-driven logic.

11 . The method of claim 10 , further comprising:

using the model training data for: training a data-driven model, and/or validating a data-driven model, and/or determination of a classification value and/or an output signal indicative of a dental procedure and/or selection of a tool for use in a dental procedure.

12 . A computer-implemented method for transforming a digital three-dimensional (“3D”) dental model to a non-photorealistic two-dimensional (“2D”) dental image, comprising:

accessing a first 2D image and a second 2D image, the first and second 2D images being of the 3D dental model, wherein the first and second 2D images are dissimilar acquisitions of a dental structure,

converting the first 2D image to include only a first color component of a multi-color model, the first color component being a constituent color channel from the multi-color model;

converting the second 2D image to include only a second color component of the multi-color model, the second color component being a different constituent color channel than that of the first color component,

obtaining, by combining the converted first 2D image and the converted second 2D image, the non-photorealistic 2D dental image in a computer-readable format of the multi-color model,

wherein the first and second 2D images are dissimilar computerized acquisitions of the dental structure that were used to generate the 3D dental model.

13 . The method of claim 12 , wherein at least one of the first or second 2D images is a depth map representation of the dental structure.

14 . The method of claim 12 , wherein at least one of the first or second 2D images is a feature layer representative of boundaries and/or regions of interest and/or attributes of the dental structure.

15 . The method of claim 12 , further comprising:

providing, as an input, the non-photorealistic dental 2D image to a trained data-driven logic;

determining, via a data-driven logic, a classification value of the non-photorealistic 2D dental image.

16 . A system for classifying a dental structure using a trained data-driven logic comprising a processor configured to:

provide, as an input, a composite 2D image to the trained data-driven logic;

determine, via the trained data-driven logic, a classification value of the composite 2D image;

wherein the composite 2D image is in a computer-readable format of a color 3D model, and wherein the composite 2D image is obtained by converting a first 2D image of a digital 3D model to include only a first color component of a multi-color model, the first color component being a constituent color channel from the multi-color model, converting a second 2D image of the digital 3D model to include only a second color component of the multi-color model, the second color component being a different constituent color channel than that of the first color component, and compositing the converted first 2D image and the converted second 2D image to produce the composite 2D image, and wherein the first and second 2D images are dissimilar computerized acquisitions of the dental structure that were used to generate the color 3D model.

17 . A non-transitory computer-readable storage medium storing a program, comprising instructions for classifying a dental structure using a trained data-driven logic, which when executed by a computing unit cause the computing unit to:

provide, as an input, a composite 2D image to the trained data-driven logic;

determine, via the trained data-driven logic, a classification value of the composite 2D image;

wherein the composite 2D image is in a computer-readable format of a color 3D model, and wherein the composite 2D image is obtained by converting a first 2D image of a digital 3D model to include only a first color component of a multi-color model, the first color component being a constituent color channel from the multi-color model, converting a second 2D image of the digital 3D model to include only a second color component of the multi-color model, the second color component being a different constituent color channel than that of the first color component, and compositing the converted first 2D image and the converted second 2D image to produce the composite 2D image, and wherein the first and second 2D images are dissimilar computerized acquisitions of the dental structure that were used to generate the color 3D model.

Priority Claims (1)
EP 21020339 · Jul 1, 2021 · regional
Continuity (1)
Related Publication 20240303809A1 · Sep 12, 2024
References Cited (51)
US 9008417B2 · Rohner · 2015 [cited by examiner]
US 10390913B2 · Sabina · 2019 [cited by examiner]
US 10916053B1 · Katzman · 2021 [cited by examiner]
US 11151753B2 · Gao · 2021 [cited by examiner]
US 11250580B2 · Meyer · 2022 [cited by examiner]
US 11291532B2 · Azernikov · 2022 [cited by examiner]
US 11348257B2 · Lang · 2022 [cited by examiner]
US 11985414B2 · Cramer · 2024 [cited by examiner]
US 12211151B1 · Chiou · 2025 [cited by examiner]
US 12446994B2 · Salah · 2025 [cited by examiner]
US 20160125601A1 · Wu · 2016 [cited by examiner]
US 20170112590A1 · Brown · 2017 [cited by examiner]
US 20180028294A1 · Azernikov · 2018 [cited by examiner]
US 20190259220A1 · Lancelle · 2019 [cited by examiner]
US 20190282344A1 · Azernikov · 2019 [cited by examiner]
US 20200000562A1 · Wey · 2020 [cited by examiner]
US 20200105028A1 · Gao · 2020 [cited by examiner]
US 20200273248A1 · Jørgensen · 2020 [cited by examiner]
US 20200320769A1 · Chen · 2020 [cited by examiner]
US 20210074425A1 · Carter · 2021 [cited by examiner]
US 20210090272A1 · Meyer · 2021 [cited by examiner]
US 20210153986A1 · Wirjadi et al. · 2021 [cited by applicant]
US 20210251729A1 · Schneider · 2021 [cited by examiner]
US 20210321872A1 · Saphier · 2021 [cited by examiner]
US 20210353153A1 · Saphier · 2021 [cited by examiner]
US 20220083807A1 · Zhang · 2022 [cited by examiner]
US 20220165388A1 · Chernov · 2022 [cited by examiner]
US 20220223285A1 · Hirsch · 2022 [cited by examiner]
US 20220262007A1 · Cramer · 2022 [cited by examiner]
US 20220304782A1 · Derzapf · 2022 [cited by examiner]
US 20230153476A1 · Fabbri · 2023 [cited by examiner]
US 20240303809A1 · Schneider · 2024 [cited by examiner]
US 20250009483A1 · Ezhov · 2025 [cited by examiner]
CN 107564090 · 2018 [cited by applicant]
EP 3948786A1 · 2022 [cited by applicant]
EP 4113373A1 · 2023 [cited by applicant]
JP 2020508734A · 2020 [cited by applicant]
JP 2024526606A · 2024 [cited by applicant]
WO WO2019244254A1 · 2019 [cited by applicant]
WO WO2020156896A1 · 2020 [cited by applicant]
WO WO2020201623A1 · 2020 [cited by applicant]
WO 2023274622 · 2023 [cited by applicant]
“European Application Serial No. 21020339.4, Extended European Search Report mailed Mar. 29, 2022”, 10 pgs. [cited by applicant]
“European Application Serial No. 21020339.4, Response filed Jul. 4, 2023 to Extended European Search Report mailed Mar. 29, 2022”, 83 pgs. [cited by applicant]
“European Application Serial No. 22730135.5, Noting of Loss of Rights mailed Feb. 22, 2024”, 2 pgs. [cited by applicant]
“European Application Serial No. 21020339.4, Communication Pursuant to Article 94(3) EPC mailed Jan. 23, 2025”, 4 pgs. [cited by applicant]
“International Application Serial No. PCT EP2022 063351, International Search Report mailed Sep. 1, 2022”, 5 pgs. [cited by applicant]
“International Application Serial No. PCT EP2022 063351, Written Opinion mailed Sep. 1, 2022”, 8 pgs. [cited by applicant]
“International Application Serial No. PCT EP2022 063351, International Preliminary Report on Patentability mailed Jan. 11, 2024”, 10 pgs. [cited by applicant]
“European Application Serial No. 21020339.4, Response Filed May 23, 2025 to Communication Pursuant to Article 94(3) EPC mailed Jan. 23, 2025”, 8 pgs. [cited by applicant]
“Japanese Application Serial No. 2023-580417, Notification of Reasons for Rejection mailed Feb. 3, 2026”, w/ English Translation, 11 pgs. [cited by applicant]