IP Library › Granted Patent US 12,232,923
Granted Patent B2
US 12,232,923 · App. 17/272,460 · Granted Feb 25, 2025

Automated orthodontic treatment planning using deep learning

Inventors: David Anssari Moin (The Hague, NL); Frank Theodorus Catharina Claessen (The Hague, NL)
Assignee: PROMATON HOLDING B.V.
A61C7/002A61C7/08A61C9/0053G06N3/082G06T7/0012G06T7/168G06V10/454G06V10/764G06V10/82G16H30/40G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30036
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 12,232,923
App. No.
17/272,460
Granted
Feb 25, 2025
Kind
B2
Abstract

A method of the invention comprises obtaining training dental CT scans, identifying individual teeth and jaw bone in each of these CT scans, and training a deep neural network with training input data obtained from these CT scans and training target data. A further method of the invention comprises obtaining a patient dental CT scan, identifying individual teeth and jaw bone in this CT scan and using the trained deep learning network to determine a desired final position from input data obtained from this CT scan. The (training) input data represents all teeth and the entire alveolar process and identifies the individual teeth and the jaw bone. The determined desired final positions are used to determine a sequence of desired intermediate positions per tooth and the intermediate and final positions and attachment types are used to create three-dimensional representations of teeth and/or aligners.

Claims (52)

1. A system comprising a deep neural network and at least one processor configured to:

obtain a plurality of training dental computed tomography scans which reflect a moment before respective successful orthodontic treatments,

identify individual teeth and jaw bone in each of said training dental computed tomography scans, and

train said deep neural network with training input data obtained from said plurality of training dental computed tomography scans and training target data per training dental computed tomography scan to determine a desired final position per tooth from input data obtained from a patient dental computed tomography scan, wherein training input data obtained from each training dental computed tomography scan represents all teeth and an entire alveolar process and identifies said individual teeth and said jaw bone,

wherein said input data comprises an image data set or a 3D data set along with information delineating said individual teeth and said jaw bone, said image data set representing an entire computed tomography scan, or multiple 3D data sets, said multiple 3D data sets comprising a 3D data set per tooth and a 3D data set for said jaw bone, and wherein

said training target data comprises an indicator indicating an achieved transformation per tooth for one or more of said plurality of training dental computed tomography scans, said transformation comprising a translation and/or a rotation per tooth, and/or

said training target data comprises data obtained from one or more further training dental computed tomography scans which reflect a moment after a successful orthodontic treatment, each of said one or more further training dental computed tomography scans being associated with a training dental computed tomography scan of said plurality of training dental computed tomography scans.

2. The system as claimed in claim 1 , wherein said at least one processor is configured to use said identification of said individual teeth and said jaw bone to determine dento-physical properties for each of said training dental computed tomography scans and facilitate an encoding of information reflecting said dento-physical properties in said deep neural network.

3. The system as claimed in claim 2 , wherein said dento-physical properties are encoded in said deep neural network by training said deep neural network with a loss function which depends on said determined dento-physical properties.

4. The system as claimed in claim 1 , wherein said training data obtained from said training dental computed tomography scan further represents all basal bone.

5. The system as claimed in claim 1 , wherein one or more of said plurality of training dental computed tomography scans are each associated with an indicator indicating an attachment type per tooth, said indicator being included in said training target data.

6. The system as claimed in claim 1 , wherein said at least one processor is configured to obtain at least one of said one or more training dental computer tomography scans by transforming data resulting from one of said further training dental computed tomography scans.

7. The system as claimed in claim 1 , wherein said at least one processor is configured to train said deep neural network with said training input data obtained from said plurality of training dental computed tomography scans and said training target data per training dental computed tomography scan to determine said desired final position and an attachment type per tooth from said input data obtained from said patient dental computed tomography scan.

8. The system as claimed in claim 1 , wherein said individual teeth and said jaw bone are identified from said computer tomography scan using a further deep neural network.

9. A system comprising a deep neural network and at least one processor,

said deep neural network being trained with training input data obtained from a plurality of training dental computed tomography scans and training target data per training dental computed tomography scan to determine a desired final position per tooth from input data obtained from a patient dental computed tomography scan,

wherein said plurality of training dental computed tomography scans reflect a moment before respective successful orthodontic treatments, individual teeth and jaw bone are identified in each of said training dental computed tomography scans, and training input data obtained from each training dental computed tomography scan represents all teeth and an entire alveolar process and identifies said individual teeth and said jaw bone, and

wherein said training target data comprises an indicator indicating an achieved transformation per tooth for one or more of said plurality of training dental computed tomography scans, said transformation comprising a translation and/or a rotation per tooth, and/or

said training target data comprises data obtained from one or more further training dental computed tomography scans which reflect a moment after a successful orthodontic treatment, each of said one or more further training dental computed tomography scans being associated with a training dental computed tomography scan of said plurality of training dental computed tomography scans, and

said at least one processor being configured to:

obtain a patient dental computed tomography scan,

identify individual teeth and the jaw bone in said patient dental computed tomography scan, and

use said deep neural network to determine a desired final position per tooth from input data obtained from said patient dental computed tomography scan, wherein said input data represents all teeth and the entire alveolar process and identifies said individual teeth and said jaw bone,

wherein said input data comprises an image data set or a 3D data set along with information delineating said individual teeth and said jaw bone, said image data set representing an entire computed tomography scan, or multiple 3D data sets, said multiple 3D data sets comprising a 3D data set per tooth and a 3D data set for said jaw bone, and

wherein said determined desired final positions are used to determine a sequence of desired intermediate positions per tooth and said determined intermediate positions and said determined final positions are used to create three-dimensional representations of teeth and/or aligners.

10. The system as claimed in claim 9 , wherein said at least one processor is configured to determine said sequence of desired intermediate positions per tooth based on said determined desired final positions and create said three-dimensional representations of said aligners based on said intermediate and final positions.

11. The system as claimed in claim 10 , wherein said at least one processor is configured to determine three-dimensional representations of said teeth in each of said intermediate and final positions per tooth for a purpose of manufacturing aligners based on said three-dimensional representations.

12. The system as claimed in claim 11 , wherein said at least one processor is configured to create said three dimensional representations of said teeth further based on data relating to tooth crowns obtained from an intraoral scan.

13. The system as claimed in claim 9 , wherein said at least one processor is configured to:

use said deep neural network to determine said desired final position and an attachment type per tooth from said input data obtained from said patient dental computed tomography scan,

wherein said determined intermediate positions, said determined final positions and said attachment types are used to create said three-dimensional representations of said teeth and/or said aligners.

14. A computer-implemented method to create three-dimensional representations of teeth and/or aligners, the method comprising:

providing a deep neural network trained with training input data obtained from a plurality of training dental computed tomography scans and training target data per training dental computed tomography scan to determine a desired final position per tooth from input data obtained from a patient dental computed tomography scan, wherein said plurality of training dental computed tomography scans reflect a moment before respective successful orthodontic treatments, individual teeth and jaw bone are identified in each of said training dental computed tomography scans, and training input data obtained from each training dental computed tomography scan represents all teeth and an entire alveolar process and identifies said individual teeth and said jaw bone, and wherein said training target data comprises an indicator indicating an achieved transformation per tooth for one or more of said plurality of training dental computed tomography scans, said transformation comprising a translation and/or a rotation per tooth, and/or said training target data comprises data obtained from one or more further training dental computed tomography scans which reflect a moment after a successful orthodontic treatment, each of said one or more further training dental computed tomography scans being associated with a training dental computed tomography scan of said plurality of training dental computed tomography scans,

obtaining input data from a patient dental computed tomography scan, wherein said input data comprises an image data set or a 3D data set along with information delineating said individual teeth and said jaw bone, said image data set representing an entire computed tomography scan, or multiple 3D data sets, said multiple 3D data sets comprising a 3D data set per tooth and a 3D data set for said jaw bone,

identifying individual teeth and the jaw bone in said patient dental computed tomography scan,

using at least one processor and said deep neural network to determine a desired final position per tooth from said input data obtained from said patient dental computed tomography scan, wherein said input data represents all teeth and the entire alveolar process and identifies said individual teeth and said jaw bone,

using the at least one processor and said determined desired final positions to determine a sequence of desired intermediate positions per tooth and said determined intermediate positions, and

using the at least one processor and said determined final positions to create three-dimensional representations of teeth and/or aligners.

15. The computer-implemented method as claimed in claim 14 , wherein

using the at least one processor and said deep neural network to determine said desired final position, includes determining an attachment type per tooth from said input data obtained from said patient dental computed tomography scan, and

wherein said determined intermediate positions, said determined final positions and said attachment types are used to create said three-dimensional representations of said teeth and/or said aligners.

16. A computer-implemented method comprising:

obtaining a plurality of training dental computed tomography scans which reflect a moment before respective successful orthodontic treatments,

identifying individual teeth and jaw bone in each of said training dental computed tomography scans, and

training a deep neural network using at least one processor with training input data obtained from said plurality of training dental computed tomography scans and training target data per training dental computed tomography scan to determine a desired final position per tooth from input data obtained from a patient dental computed tomography scan, wherein training input data obtained from each training dental computed tomography scan represents all teeth and an entire alveolar process and identifies said individual teeth and said jaw bone,

wherein said input data comprises an image data set or a 3D data set along with information delineating said individual teeth and said jaw bone, said image data set representing an entire computed tomography scan, or multiple 3D data sets, said multiple 3D data sets comprising a 3D data set per tooth and a 3D data set for said jaw bone, and wherein

said training target data comprises an indicator indicating an achieved transformation per tooth for one or more of said plurality of training dental computed tomography scans, said transformation comprising a translation and/or a rotation per tooth, and/or

said training target data comprises data obtained from one or more further training dental computed tomography scans which reflect a moment after a successful orthodontic treatment, each of said one or more further training dental computed tomography scans being associated with a training dental computed tomography scan of said plurality of training dental computed tomography scans.

17. The computer-implemented method as claimed in claim 16 , further comprising using the at least one processor and said identification of said individual teeth and said jaw bone to determine dento-physical properties for each of said training dental computed tomography scans and facilitate an encoding of information reflecting said dento-physical properties in said deep neural network.

18. The computer-implemented method as claimed in claim 17 , wherein said dento-physical properties are encoded in said deep neural network by training said deep neural network with a loss function which depends on said determined dento-physical properties.

19. The computer-implemented method as claimed in claim 16 , wherein said training data obtained from said training dental computed tomography scan further represents all basal bone.

20. The computer-implemented method as claimed in claim 16 , wherein one or more of said plurality of training dental computed tomography scans are each associated with an indicator indicating an attachment type per tooth, said indicator being included in said training target data.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 13, 2021
From: ANSSARI MOIN, DAVID; CLAESSEN, FRANK THEODORUS CATHARINA
To: PROMATON HOLDING B.V.
Reel/Frame 056841/0605 →
Priority Claims (1)
EP 18192483 · Sep 4, 2018 · regional
Continuity (1)
Related Publication 20210322136A1 · Oct 21, 2021
References Cited (187)
US 6721387B1 · Naidu et al. · 2004 [cited by applicant]
US 7987099B2 · Kuo et al. · 2011 [cited by applicant]
US 8099305B2 · Kuo et al. · 2012 [cited by applicant]
US 8135569B2 · Matov et al. · 2012 [cited by applicant]
US 8439672B2 · Matov et al. · 2013 [cited by applicant]
US 8639477B2 · Chelnokov et al. · 2014 [cited by applicant]
US 9107722B2 · Matov et al. · 2015 [cited by applicant]
US 9135498B2 · Andreiko et al. · 2015 [cited by applicant]
US 9904999B2 · Andreiko et al. · 2018 [cited by applicant]
US 10032271B2 · Somasundaram et al. · 2018 [cited by applicant]
US 10235606B2 · Miao et al. · 2019 [cited by applicant]
US 10456229B2 · Fisker et al. · 2019 [cited by applicant]
US 10610185B2 · Taguchi et al. · 2020 [cited by applicant]
US 10685259B2 · Salah et al. · 2020 [cited by applicant]
US 10932890B1 · Sant et al. · 2021 [cited by applicant]
US 10997727B2 · Xue et al. · 2021 [cited by applicant]
US 11007036B2 · Pokotilov et al. · 2021 [cited by applicant]
US 11107218B2 · Salah et al. · 2021 [cited by applicant]
US 20050019732A1 · Kaufmann et al. · 2005 [cited by applicant]
US 20050192835A1 · Kuo et al. · 2005 [cited by applicant]
US 20080085487A1 · Kuo et al. · 2008 [cited by applicant]
US 20080253635A1 · Spies et al. · 2008 [cited by applicant]
US 20090191503A1 · Matov et al. · 2009 [cited by applicant]
US 20100069741A1 · Kuhn et al. · 2010 [cited by applicant]
US 20110038516A1 · Koehler et al. · 2011 [cited by applicant]
US 20110081071A1 · Benson et al. · 2011 [cited by applicant]
US 20110255765A1 · Carlson et al. · 2011 [cited by applicant]
US 20120063655A1 · Dean et al. · 2012 [cited by applicant]
US 20130022251A1 · Chen et al. · 2013 [cited by applicant]
US 20130039556A1 · Kachelriess et al. · 2013 [cited by applicant]
US 20130230818A1 · Matov et al. · 2013 [cited by applicant]
US 20140169648A1 · Andreiko · 2014 [cited by examiner]
US 20140227655A1 · Andreiko et al. · 2014 [cited by applicant]
US 20150029178A1 · Claus et al. · 2015 [cited by applicant]
US 20160008095A1 · Matov et al. · 2016 [cited by applicant]
US 20160034788A1 · Lin et al. · 2016 [cited by applicant]
US 20160042509A1 · Andreiko et al. · 2016 [cited by applicant]
US 20160078647A1 · Schildkraut et al. · 2016 [cited by applicant]
US 20160117850A1 · Jin et al. · 2016 [cited by applicant]
US 20160324499A1 · Sen Sharma et al. · 2016 [cited by applicant]
US 20160371862A1 · Silver et al. · 2016 [cited by applicant]
US 20170024634A1 · Miao et al. · 2017 [cited by applicant]
US 20170046616A1 · Socher et al. · 2017 [cited by applicant]
US 20170100212A1 · Sherwood et al. · 2017 [cited by applicant]
US 20170150937A1 · Stille et al. · 2017 [cited by applicant]
US 20170169562A1 · Somasundaram et al. · 2017 [cited by applicant]
US 20170265977A1 · Fisker et al. · 2017 [cited by applicant]
US 20170270687A1 · Manhart · 2017 [cited by applicant]
US 20180005377A1 · Alvarez · 2018 [cited by examiner]
US 20180028294A1 · Azernikov · 2018 [cited by examiner]
US 20180110590A1 · Maraj · 2018 [cited by examiner]
US 20180182098A1 · Andreiko et al. · 2018 [cited by applicant]
US 20180253866A1 · Jain et al. · 2018 [cited by applicant]
US 20180300877A1 · Somasundaram et al. · 2018 [cited by applicant]
US 20190026599A1 · Salah et al. · 2019 [cited by applicant]
US 20190147245A1 · Qi et al. · 2019 [cited by applicant]
US 20190147666A1 · Keustermans · 2019 [cited by examiner]
US 20190148005A1 · Domracheva · 2019 [cited by examiner]
US 20190164288A1 · Wang et al. · 2019 [cited by applicant]
US 20190172200A1 · Andreiko et al. · 2019 [cited by applicant]
US 20190282333A1 · Matov et al. · 2019 [cited by applicant]
US 20190328489A1 · Capron-Richard et al. · 2019 [cited by applicant]
US 20200015948A1 · Fisker et al. · 2020 [cited by applicant]
US 20200022790A1 · Fisker · 2020 [cited by applicant]
US 20200085535A1 · Pokotilov et al. · 2020 [cited by applicant]
US 20200179089A1 · Serval et al. · 2020 [cited by applicant]
US 20200320685A1 · Anssari Moin et al. · 2020 [cited by applicant]
US 20210045843A1 · Pokotilov et al. · 2021 [cited by applicant]
US 20210082184A1 · Claessen et al. · 2021 [cited by applicant]
US 20210110584A1 · Claessen et al. · 2021 [cited by applicant]
US 20210150702A1 · Claessen et al. · 2021 [cited by applicant]
US 20210174543A1 · Claessen et al. · 2021 [cited by applicant]
US 20210217233A1 · Feng et al. · 2021 [cited by applicant]
US 20210264611A1 · Xue et al. · 2021 [cited by applicant]
US 20220067943A1 · Claessen et al. · 2022 [cited by applicant]
US 20230186476A1 · Ghazvinian Zanjani et al. · 2023 [cited by applicant]
US 20230263605A1 · Madden et al. · 2023 [cited by applicant]
CN 101977564A · 2011 [cited by applicant]
CN 106618760A · 2017 [cited by applicant]
CN 108205806A · 2018 [cited by applicant]
CN 108305684A · 2018 [cited by applicant]
EP 2742857A1 · 2014 [cited by applicant]
EP 3121789A1 · 2017 [cited by applicant]
EP 3462373A1 · 2019 [cited by applicant]
EP 3591616A1 · 2020 [cited by applicant]
EP 3671531A1 · 2020 [cited by applicant]
EP 3767521A1 · 2021 [cited by applicant]
JP 2007525289A · 2007 [cited by applicant]
JP 2010220742A · 2010 [cited by applicant]
JP 2013537445A · 2013 [cited by applicant]
JP 2017102622A · 2017 [cited by applicant]
JP 2017520292A · 2017 [cited by applicant]
JP 2017157138A · 2017 [cited by applicant]
JP 2022501299A · 2022 [cited by applicant]
WO 2015169910A1 · 2015 [cited by applicant]
WO 2016143022A1 · 2016 [cited by applicant]
WO 2017099990A1 · 2017 [cited by applicant]
WO 2019002616A1 · 2019 [cited by applicant]
WO 2019002631A1 · 2019 [cited by applicant]
WO 2019068741A2 · 2019 [cited by applicant]
WO 2019122373A1 · 2019 [cited by applicant]
WO 2019207144A1 · 2019 [cited by applicant]
WO 2020007941A1 · 2020 [cited by applicant]
WO 2020127398A1 · 2020 [cited by applicant]
WO 2021009258A1 · 2021 [cited by applicant]
Gutierrez-Becker et al. “Learning Optimization Updates for Multimodal Registration”, Medical Image Computing and Computer-Assisted Intervention—MICCAI 2016, 2016, pp. 19-27. [cited by applicant]
Hosntalab et al. “A Hybrid Segmentation Framework for Computer-Assisted Dental Procedures”, IEICE Transactions on Information and Systems, Oct. 2009, pp. 2137-2151, vol. E92D, No. 10. [cited by applicant]
Studholme et al. “Automated Three-Dimensional Registration of Magnetic Resonance and Positron Emission Tomography Brain Images by Multiresolution Optimization of Voxel Similarity Measures”, Medical Physics, 1997, pp. 25… [cited by applicant]
Ahn, B, “The Compact 3D Convolutional Neural Network for Medical Images”, Jul. 2, 2017, pp. 1-9, http://cs231n.standord.edu/reports/2017/pdfs/23/pdf, retrieved Dec. 18, 2018. [cited by applicant]
Auro Tripathy, “Five Insights from GoogLeNet You Could Use in Your Own Deep Learning Nets”, Sep. 20, 2016, pp. 1-21, https://www.slideshare.net/aurot/googlenet-insights?from_action=save, retrieved Dec. 18, 2018. [cited by applicant]
Bustos et al., “An Experimental Comparison of Feature-Based 3D Retrieval Methods” 2nd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2004, Sep. 6-9, 2004, pp. 215-222. [cited by applicant]
Chaouch, M. and Verroust-Blondet, A., “Alignment of 3D Models”, Graphical Models, Mar. 2009, pp. 63-76, vol. 71, No. 2. [cited by applicant]
Çiçek et al., “3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation”, Medical Image Computing and Computer-Assisted Intervention—MICCAI 2016, Part II, Oct. 2, 2016, pp. 424-432. [cited by applicant]
Duda et al., “Pattern Classification: Introduction”, 2001, Pattern Classification, New York, John Wiley & Sons, US, pp. 1-13. [cited by applicant]
Duy et al., “Automatic Detection and Classification of Teeth in CT Data”, International Conference on Medical Image Computing and Computer-Assisted Intervention—MICCAI 2012, 2012, pp. 609-616. [cited by applicant]
Everingham et al., “The PASCAL Visual Object Classes (VOC) Challenge”, International Journal of Computer Vision, Sep. 9, 2009, pp. 303-338, vol. 88, No. 2. [cited by applicant]
Fechter et al., “A 3D Fully Convolutional Neural Network and a Random Walker to Segment the Esophagus in CT”, Apr. 21, 2017, 23 pages, https://arxiv.org/pdf/1704.06544.pdf, retrieved Dec. 18, 2018. [cited by applicant]
Gjesteby et al., “Deep Learning Methods for CT Image-Domain Metal Artifact Reduction”, SPIE, Developments in X-Ray Tomography XI, Sep. 25, 2017, 6 pages, vol. 10391. [cited by applicant]
Gkantidis et al. “Evaluation of 3-Dimensional Superimposition Techniques on Various Skeletal Structures of the Head Using Surface Models”, PLOS ONE, Feb. 23, 2015, 20 pages, vol. 10, No. 2. [cited by applicant]
Hall, P. and Owen, M. “Simple Canonical Views”, Proceedings of the British Machine Vision Conference (BMVC), Sep. 2005, 10 pages. [cited by applicant]
Han et al., “Deep Residual Learning for Compressed Sensing CT Reconstruction Via Persistent Homology Analysis”, Cornell University Library, Nov. 19, 2016, pp. 1-10. [cited by applicant]
He et al., “Deep Residual Learning for Image Recognition”, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CPR), Jun. 2016, pp. 770-778. [cited by applicant]
Hongming Li, Y. “Non-Rigid Image Registration Using Fully Convolutional Networks With Deep Self-Supervision”, Sep. 3, 2017, 8 pages. [cited by applicant]
Isola et al., “Image-to-Image Translation with Conditional Adversarial Networks”, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, pp. 5967-5976. [cited by applicant]
Joda, T. and Gallucci, G. “Systematic Literature Review of Digital Three-Dimensional Superimposition Techniques to Create Virtual Dental Patients”, The International Journal of Oral & Maxillofacial Implants, 2015, pp. 3… [cited by applicant]
Jung et al., “Combining Volumetric Dental CT and Optical Scan Data for Teeth Modeling”, Computer-Aided Design, Oct. 2015, pp. 24-37, vol. 67-68. [cited by applicant]
Klinder et al., “Automated Model-Based Vertebra Detection, Identification, and Segmentation in CT Images”, Medical Image Analysis, Jun. 2009, pp. 471-482, vol. 13, No. 3. [cited by applicant]
Li et al., “PointCNN: Convolution on X-Transformed Points”, Neural Information Processing Systems (NIPS), Nov. 5, 2018, 11 pages. [cited by applicant]
Liao et al. “Automatic Tooth Segmentation of Dental Mesh Based on Harmonic Fields”, Biomedical Research International, 2015, 10 pages, vol. 2015. [cited by applicant]
Litjens et al. “A Survey on Deep Learning in Medical Image Analysis”, Medical Image Analysis, Dec. 2017, pp. 60-88, vol. 42. [cited by applicant]
Meyer et al. “Normalized Metal Artifact Reduction (NMAR) in Computed Tomography”, Medical Physics, Oct. 2010, pp. 5482-5493, vol. 37, No. 10. [cited by applicant]
Miki et al. “Tooth Labeling in Cone-Beam CT Using Deep Convolutional Neural Network for Forensic Identification”, SPIE 10134, Medical Imaging 2017: Computer-Aided Diagnosis, Mar. 3, 2017, 6 pages. [cited by applicant]
Miki et al. “Classification of Teeth in Cone-Beam CT Using Deep Convolutional Neural Network”, Computers in Biology and Medicine, Jan. 2017, pp. 24-29, vol. 1, No. 80. [cited by applicant]
Pavaloiu et al., “Automatic Segmentation for 3D Dental Reconstruction”, IEEE 6th ICCCNT, Jul. 13-15, 2015, 6 pages. [cited by applicant]
Pavaloiu et al., “Neural Network Based Edge Detection for CBCT Segmentation”, 5th IEEE EHB, Nov. 19-21, 2015. [cited by applicant]
Qi et al., “PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation”, Computer Vision and Pattern Recognition (CVPR), 2017, 19 pages. [cited by applicant]
Ruellas et al. “3D Mandibular Superimposition: Comparison of Regions of Reference for Voxel-Based Registration” PLOS ONE, Jun. 23, 2016, 13 pages. [cited by applicant]
Ryu et al. “Analysis of Skin Movement With Respect to Flexional Bone Motion Using MR Images of a Hand”, Journal of Biomechanics, 2006, pp. 844-852, vol. 39, No. 5. [cited by applicant]
Schulze et al., “Artefacts in CBCT: A Review”, Dentomaxillofacial Radiology, Jul. 1, 2011, pp. 265-273, vol. 40, No. 5. [cited by applicant]
Sekuboyina et al., “A Localisation-Segmentation Approach for Multi-Label Annotation of Lumbar Vertebrae Using Deep Nuts”, Cornell University Library, 201 Olin Library Cornell University Ithaca, NY 14853, Mar. 13, 2017, … [cited by applicant]
Simonovsky et al. “A Deep Metric for Multimodal Registration” International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2016, pp. 10-18, vol. 9902. [cited by applicant]
Szegedy et al., “Going Deeper With Convolutions”, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2015, pp. 1-9. [cited by applicant]
Tonioni et al., “Learning to Detect Good 3D Keypoints”, International Journal of Computer Vision, 2018, pp. 1-20, vol. 126. [cited by applicant]
Wang et al., “Dynamic Graph CNN for Learning on Point Clouds”, ACM Trans. Graph, Jan. 2019, vol. 1, No. 1, 13 pages. [cited by applicant]
Wu et al. “Tooth Segmentation on Dental Meshes Using Morphologic Skeleton”, Computers & Graphics, Feb. 2014, pp. 199-211, vol. 38. [cited by applicant]
Wu et al., “Model-Based Teeth Reconstruction”, ACM Transactions on Graphics (TOG), ACM, US, Nov. 11, 2016, pp. 1-13, vol. 35, No. 6. [cited by applicant]
Yau et al., “Tooth Model Reconstruction Based Upon Data Fusion for Orthodontic Treatment Simulation”, Computers in Biology and Medicine, May 1, 2014, pp. 8-16, vol. 48. [cited by applicant]
Yu, Y. “Machine Learning for Dental Image Analysis”, Nov. 2016, 61 pages, https://arxiv.org/ftp/arxiv/papers/1611/1611.09958.pdf, retrieved Nov. 30, 2017. [cited by applicant]
Zhang, Y. and Yu, H., “Convolutional Neural Network Based Metal Artifact Reduction in X-Ray Computed Tomography”, IEEE Transactions on Medical Imaging, Jun. 2018, pp. 1370-1381, vol. 37, No. 6. [cited by applicant]
Zhang, C. and Xing, Y., “CT Artifact Reduction Via U-Net CNN”, SPIE, Medical Imaging 2018: Image Processing, Mar. 2, 2018, 6 pages, vol. 10574. [cited by applicant]
International Search Report and Written Opinion for International Patent Application No. PCT/EP2019/073438, dated Nov. 20, 2019. [cited by applicant]
Office Action in corresponding Chinese Patent Application No. 201980057692.4 dated Aug. 27, 2021. [cited by applicant]
Chen et al. “Deep RBFNet: Point Cloud Feature Learning Using Radial Basis Functions”, Cornell University Library, Dec. 11, 2018, 11 pages. [cited by applicant]
Chen et al. “Fast Resampling of 3D Point Clouds Via Graphs”, IEEE Transactions on Signal Processing, Feb. 1, 2018, pp. 666-681, vol. 66, No. 3. [cited by applicant]
Eun, H. and Kim, C. “Oriented Tooth Localization for Periapical Dental X-ray Images via Convolutional Neural Network”, Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), De… [cited by applicant]
Fang et al. “3D Deep Shape Descriptor”, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 2319-2328. [cited by applicant]
Ghafoorian et al. “EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection”, Computer Vision—ECCV 2018 Workshops, Jan. 23, 2019, pp. 256-272, vol. 11129. [cited by applicant]
Ghazvinian Zanjani et al. “Deep Learning Approach to Semantic Segmentation in 3D Point Cloud Intra-oral Scans of Teeth”, Proceedings of the 2nd International Conference on Medical Imaging with Deep Learning, 2019, 22 pa… [cited by applicant]
Gomes et al. “Efficient 3D Object Recognition Using Foveated Point Clouds”, Computers & Graphics, May 1, 2013, pp. 496-508, vol. 37. [cited by applicant]
Gorler, O. and Akkoyun, S. “Artificial Neural Networks Can be Used as Alternative Method to Estimate Loss Tooth Root Sizes for Prediction of Dental Implants”, Cumhuriyet University Faculty of Science Science Journal (CS… [cited by applicant]
Guo et al. “3D Mesh Labeling Via Deep Convolutional Neural Networks”, ACM Transactions on Graphics, Dec. 2015, pp. 1-12, vol. 35, No. 1, Article 3. [cited by applicant]
Hermosilla et al. “Monte Carlo Convolution for Learning on Non-Uniformly Shaped Point Clouds”, ACM Transactions on Graphics, Nov. 2018, 12 pages, vol. 37, No. 6, Article 235. [cited by applicant]
Hou et al. “3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans”, Computer Vision and Pattern Recognition (CPR), Apr. 29, 2019, 14 pages. [cited by applicant]
Huang et al. “Edge-Aware Point Set Resampling”, ACM Transactions on Graphics, 2013, pp. 1-12, vol. 32, No. 1, Article 9. [cited by applicant]
Johari et al. “Detection of Vertical Root Fractures in Intact and Endodontically Treated Premolar Teeth by Designing a Probabilistic Neural Network: An ex vivo Study”, Dentomaxillofacial Radiology, Feb. 2017, vol. 46, N… [cited by applicant]
Ku et al. “Joint 3D Proposal Generation and Object Detection from View Aggregation”, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Jul. 12, 2018, pp. 1-8. [cited by applicant]
Le T. and Duan Y. “PointGrid: A Deep Network for 3D Shape Understanding”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 18-23, 2018, pp. 9204-9214. [cited by applicant]
Li et al. “SO-Net: Self-Organizing Network for Point Cloud Analysis”, Eye In-Painting with Exemplar Generative Adversarial Networks, Jun. 2018, pp. 9397-9406. [cited by applicant]
Liu, C. and Furukawa, Y. “MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation”, Computer Vision and Pattern Recognition (CPR), Feb. 12, 2019, 4 pages. [cited by applicant]
Qi et al. “Frustum PointNets for 3D Object Detection from RGB-D Data”, Computer Vision and Pattern Recognition (CPR), Apr. 13, 2018, 15 pages. [cited by applicant]
Qi et al. “PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space”, Conference on Neural Information Processing Systems (NIPS), Jun. 2017, 14 pages. [cited by applicant]
Ravanbakhsh et al. “Deep Learning With Sets and Point Clouds”, Feb. 24, 2017, 12 pages, retrieved online from https://arxiv.org/abs/1611.04500. [cited by applicant]
Silva et al. “Automatic Segmenting Teeth in X-Ray Images: Trends, A Novel Data Set, Benchmarking and Future Perspectives”, Feb. 9, 2018, 33 pages, retrieved online from https://arxiv.org/pdf/1802.03086.pdf. [cited by applicant]
Skrodzki et al. “Directional Density Measure to Intrinsically Estimate and Counteract Non-Uniformity in Point Clouds”, Computer Aided Geometric Design, Aug. 2018, pp. 73-89, vol. 64. [cited by applicant]
Shaoqing et al. “Mask R-CNN”, Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2961-2969. [cited by applicant]
Tian, S. “Automatic Classification and Segmentation of Teeth on 3D Dental Model Using Hierarchical Deep Learning Networks” IEEE Journals & Magazine, Jun. 21, 2019, pp. 84817-84828. [cited by applicant]
Wang et al. “SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation”, CVF Conference on Computer Vision and Pattern Recognition, Nov. 23, 2017, 13 pages. [cited by applicant]
Wu et al. “3D ShapeNets: A Deep Representation for Volumetric Shapes”, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1912-1920. [cited by applicant]
Xu et al. “SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters”, Computer Vision—EECV, 2018, 16 pages. [cited by applicant]
Yi et al. “GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, 13 pages. [cited by applicant]
Zhou et al. “A Method for Tooth Model Reconstruction Based on Integration of Multimodal Images”, Journal of Healthcare Engineering, Jun. 20, 2018, vol. 8, pp. 1-8. [cited by applicant]
Non-published U.S. Appl. No. 17/415,465, filed Jun. 17, 2021. [cited by applicant]
Non-published U.S. Appl. No. 17/626,744, filed Jan. 12, 2022. [cited by applicant]
Atzmon et al. “Point Convolutional Neural Networks by Extension Operators”, Mar. 27, 2018, 14 pages, arXiv:1803.10091v1 [cs.CV]. [cited by applicant]
Office Action in corresponding Japanese application Ser. No. 2021-510643 dated Oct. 2, 2023. [cited by applicant]
Hamida et al. “Deep Learning for Semantic Segmentation of Remote Sensing Images with Rich Spectral Content”, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2017, pp. 2569-2572. [cited by applicant]
Kamnitsas et al. “Efficient Multi-scale 3D CNN With Fully Connected CRF for Accurate Brain Lesion Segmentation”, Medical Image Analysis, 2017, pp. 61-78, vol. 36. [cited by applicant]
Cited By (2)
US 12,465,456 US 12,482,052