IP Library › Granted Patent US 12,251,253
Granted Patent B2
US 12,251,253 · App. 18/481,958 · Granted Mar 18, 2025

Systems and methods for processing of dental images

Inventors: Dmitry Tuzoff (Toronto, CA); Alexey Krasnov (Moscow, RU); Max Kharchenko (Toronto, CA); Lyudmila Tuzova (Toronto, CA)
Assignee: DENTI.AI TECHNOLOGY INC.
A61B6/51A61B6/5217A61B6/563G06T7/0012G06V10/945G06T2200/24G06T2207/20084G06T2207/30036
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 12,251,253
App. No.
18/481,958
Granted
Mar 18, 2025
Kind
B2
Abstract

A computer system implements a neural network to process raw dental images to detect and number teeth and to diagnose pathological, non-pathological, and post-treatment conditions. Detected teeth, corresponding numbers, and any corresponding detected conditions are correlated to the dental image and presented in a graphical user interface comprising the image and a standard, symbolic dental chart associating the tooth number, detected conditions, and regions of the image to teeth represented in the symbolic chart.

Claims (33)

1. A computer-implemented method of generating a dental chart display in a clinical environment, the method comprising:

receiving, by an analysis service computer system from a client computer system in the clinical environment, a two-dimensional dental image comprising a plurality of teeth of a patient, the analysis service computer system comprising at least one processor;

generating, by the at least one processor, responsive data using the dental image, the responsive data comprising a tooth number for one or more detected teeth of the plurality of teeth; image-related data comprising identification of regions in the dental image corresponding to the one or more detected teeth; and at least one detected condition, wherein the at least one detected condition comprises a pathological condition, a non-pathological condition, or a post-treatment condition, wherein generating the responsive data comprises:

detecting, by the at least one processor executing at least one neural network, one or more teeth in the dental image, the detected one or more teeth comprising the one or more detected teeth;

determining for each tooth of the one or more detected teeth, by the at least one processor executing at least one neural network, a tooth number associated with the tooth;

detecting, by the at least one processor executing at least one neural network, at least one condition comprising a pathological condition, a non-pathological condition, or a post-treatment condition; and

transmitting the responsive data to the client computer system for rendering and display of at least some of the responsive data in association with a symbolic dental chart and the dental image in a graphical user interface that visually correlates teeth in the symbolic dental chart with regions identified in the dental image.

2. The computer-implemented method of claim 1 , wherein the plurality of teeth comprised in the dental image includes a pair of overlapping teeth, an impacted tooth, or a tooth with a crown.

3. The computer-implemented method of claim 2 , wherein the detected one or more teeth includes a pair of overlapping teeth, an impacted tooth, or a tooth with a crown.

4. The computer-implemented method of claim 1 , wherein the at least one detected condition is a pathological condition, and the pathological condition comprises a missing tooth, caries, apical periodontitis, and/or a cyst.

5. The computer-implemented method of claim 1 , wherein the at least one detected condition is a non-pathological condition, and the non-pathological condition comprises a restoration, a crown, an implant, a bridge, and/or an endodontic treatment.

6. The computer-implemented method of claim 1 , wherein the at least one detected condition is a post-treatment condition, and the post-treatment condition comprises an overhanging restoration, an endodontic underfilling, and/or an endodontic overfilling.

7. The computer-implemented method of claim 1 , wherein the display of at least some of the responsive data in association with the symbolic dental chart and the dental image in the graphical user interface further visually correlates the at least one detected condition with at least one region identified in the dental image.

8. The computer-implemented method of claim 1 , wherein the display of at least some of the responsive data in association with the symbolic dental chart and the dental image in the graphical user interface further visually correlates the at least one detected condition with at least one tooth in the symbolic dental chart.

9. The computer-implemented method of claim 1 , wherein the dental image comprises a panoramic view radiograph or an intraoral radiograph.

10. The computer-implemented method of claim 1 , wherein detecting the one or more teeth in the dental image comprises segmentation of the dental image.

11. A computer system, comprising:

a network communication subsystem, memory, and at least one processor, the at least one processor being configured to execute instructions to implement:

receiving, from a client computer system in a clinical environment, a two-dimensional dental image comprising a plurality of teeth of a patient, the analysis service computer system comprising at least one processor;

generating, by the at least one processor, responsive data using the dental image, the responsive data comprising a tooth number for one or more detected teeth of the plurality of teeth; image-related data comprising identification of regions in the dental image corresponding to the one or more detected teeth; and at least one detected condition, wherein the at least one detected condition comprises a pathological condition, a non-pathological condition, or a post-treatment condition, wherein generating the responsive data comprises:

detecting, by the at least one processor executing at least one neural network, one or more teeth in the dental image, the detected one or more teeth comprising the one or more detected teeth;

determining for each tooth of the one or more detected teeth, by the at least one processor executing at least one neural network, a tooth number associated with the tooth;

detecting, by the at least one processor executing at least one neural network, at least one condition comprising a pathological condition, a non- pathological condition, or a post-treatment condition; and

transmitting the responsive data to the client computer system for rendering and display of at least some of the responsive data in association with a symbolic dental chart and the dental image in a graphical user interface of a dental chart display that visually correlates teeth in the symbolic dental chart with regions identified in the dental image.

12. The computer system of claim 11 , wherein the plurality of teeth comprised in the dental image includes a pair of overlapping teeth, an impacted tooth, or a tooth with a crown.

13. The computer system of claim 12 , wherein the detected one or more teeth includes a pair of overlapping teeth, an impacted tooth, or a tooth with a crown.

14. The computer system of claim 11 , wherein the at least one detected condition is a pathological condition, and the pathological condition comprises a missing tooth, caries, apical periodontitis, and/or a cyst.

15. The computer system of claim 11 , wherein the at least one detected condition is a non-pathological condition, and the non-pathological condition comprises a restoration, a crown, an implant, a bridge, and/or an endodontic treatment.

16. The computer system of claim 11 , wherein the at least one detected condition is a post-treatment condition, and the post-treatment condition comprises an overhanging restoration, an endodontic underfilling, and/or an endodontic overfilling.

17. The computer system of claim 11 , wherein the display of at least some of the responsive data in association with the symbolic dental chart and the dental image in the graphical user interface further visually correlates the at least one detected condition with at least one region identified in the dental image.

18. The computer system of claim 11 , wherein the display of at least some of the responsive data in association with the symbolic dental chart and the dental image in the graphical user interface further visually correlates the at least one detected condition with at least one tooth in the symbolic dental chart.

19. The computer system of claim 11 , wherein the dental image comprises a panoramic view radiograph or an intraoral radiograph.

20. The computer system of claim 11 , wherein detecting the one or more teeth in the dental image comprises segmentation of the dental image.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 5, 2023
From: TUZOFF, DMITRY; KRASNOV, ALEXEY; KHARCHENKO, MAX; TUZOVA, LYUDMILA
To: DENTI.AI TECHNOLOGY INC.
Reel/Frame 065158/0396 →
Continuity (4)
Continuation 17841300 · Jun 15, 2022
Continuation 16454902 · Jun 27, 2019
Provisional Application 62690844 · Jun 27, 2018
Related Publication 20240041418A1 · Feb 8, 2024
References Cited (137)
US 5839438A · Grattinger et al. · 1998 [cited by applicant]
US 6209095B1 · Anderson et al. · 2001 [cited by applicant]
US 6409504B1 · Jones et al. · 2002 [cited by applicant]
US 6532299B1 · Sachdeva et al. · 2003 [cited by applicant]
US 6736776B2 · Miles · 2004 [cited by applicant]
US 7010153B2 · Zimmermann · 2006 [cited by applicant]
US 7263492B1 · Suresh et al. · 2007 [cited by applicant]
US 7269278B2 · Cong et al. · 2007 [cited by applicant]
US 7391895B2 · Wang et al. · 2008 [cited by applicant]
US 7421398B2 · Kimmel · 2008 [cited by applicant]
US 7472275B2 · Arnouse · 2008 [cited by applicant]
US 7596253B2 · Wong et al. · 2009 [cited by applicant]
US 7602965B2 · Hong et al. · 2009 [cited by applicant]
US 7822621B1 · Chappel · 2010 [cited by applicant]
US 8416984B2 · Liang et al. · 2013 [cited by applicant]
US 8417010B1 · Colby · 2013 [cited by applicant]
US 8463716B2 · Montgomery et al. · 2013 [cited by applicant]
US 8687859B2 · Yan et al. · 2014 [cited by applicant]
US 8737706B2 · Graham et al. · 2014 [cited by applicant]
US 8761493B2 · Chen et al. · 2014 [cited by applicant]
US 8768016B2 · Pan et al. · 2014 [cited by applicant]
US 8929635B2 · Chen et al. · 2015 [cited by applicant]
US 9020236B2 · Wang et al. · 2015 [cited by applicant]
US 9158889B2 · Badawi · 2015 [cited by applicant]
US 9339245B2 · Colby · 2016 [cited by applicant]
US 9477649B1 · Davidson et al. · 2016 [cited by applicant]
US 9710603B2 · Kaminski et al. · 2017 [cited by applicant]
US 9839402B2 · Colby · 2017 [cited by applicant]
US 9886178B2 · Kendall et al. · 2018 [cited by applicant]
US 10043073B2 · Ross et al. · 2018 [cited by applicant]
US 10049457B2 · Abraham et al. · 2018 [cited by applicant]
US 10201318B2 · Tsuji et al. · 2019 [cited by applicant]
US 10410363B2 · Dekel et al. · 2019 [cited by applicant]
US 10426351B2 · Abrams et al. · 2019 [cited by applicant]
US 10722191B2 · Colby · 2020 [cited by applicant]
US 20020178032A1 · Benn et al. · 2002 [cited by applicant]
US 20040038184A1 · Adachi et al. · 2004 [cited by applicant]
US 20050203777A1 · Rosenfeld et al. · 2005 [cited by applicant]
US 20060069591A1 · Razzano · 2006 [cited by applicant]
US 20060147872A1 · Andreiko · 2006 [cited by applicant]
US 20060173985A1 · Moore · 2006 [cited by applicant]
US 20070217648A1 · Muehlbauer · 2007 [cited by applicant]
US 20070294104A1 · Boaz et al. · 2007 [cited by applicant]
US 20090076960A2 · Hamel et al. · 2009 [cited by applicant]
US 20110119088A1 · Gunn · 2011 [cited by applicant]
US 20110153351A1 · Vesper et al. · 2011 [cited by applicant]
US 20120148986A1 · Yan et al. · 2012 [cited by applicant]
US 20130022251A1 · Chen et al. · 2013 [cited by applicant]
US 20130122468A1 · Abrams et al. · 2013 [cited by applicant]
US 20130243276A1 · Souza et al. · 2013 [cited by applicant]
US 20140142984A1 · Wright et al. · 2014 [cited by applicant]
US 20140149128A1 · Getchius · 2014 [cited by applicant]
US 20140278529A1 · Matos · 2014 [cited by applicant]
US 20140314288A1 · Roychowdhury et al. · 2014 [cited by applicant]
US 20140342301A1 · Fleer et al. · 2014 [cited by applicant]
US 20140379361A1 · Mahadkar et al. · 2014 [cited by applicant]
US 20150046181A1 · Adjaoute · 2015 [cited by applicant]
US 20150237106A1 · Golay · 2015 [cited by applicant]
US 20160004811A1 · Somasundaram et al. · 2016 [cited by applicant]
US 20160014288A1 · Ono · 2016 [cited by applicant]
US 20160038092A1 · Golay · 2016 [cited by applicant]
US 20160196389A1 · Moturu et al. · 2016 [cited by applicant]
US 20170053562A1 · Bova et al. · 2017 [cited by applicant]
US 20170083672A1 · Juneau et al. · 2017 [cited by applicant]
US 20170161439A1 · Raduchel et al. · 2017 [cited by applicant]
US 20170367789A1 · Fujiwara · 2017 [cited by examiner]
US 20180033009A1 · Goldman et al. · 2018 [cited by applicant]
US 20180235437A1 · Ozerov et al. · 2018 [cited by applicant]
US 20180122509A1 · Christiansson · 2018 [cited by applicant]
US 20180174367A1 · Marom · 2018 [cited by applicant]
US 20180182039A1 · Wang et al. · 2018 [cited by applicant]
US 20180206940A1 · Kopelan et al. · 2018 [cited by applicant]
US 20180366225A1 · Mansi et al. · 2018 [cited by applicant]
US 20190026598A1 · Salah et al. · 2019 [cited by applicant]
US 20190038367A1 · Ciriello et al. · 2019 [cited by applicant]
US 20190043607A1 · Sears et al. · 2019 [cited by applicant]
US 20190065685A1 · Pickover et al. · 2019 [cited by applicant]
US 20190066835A1 · Lyman et al. · 2019 [cited by applicant]
US 20190110753A1 · Zhang et al. · 2019 [cited by applicant]
US 20190130566A1 · Niemeijmer et al. · 2019 [cited by applicant]
US 20190175314A1 · Lagardere et al. · 2019 [cited by applicant]
US 20190180443A1 · Xue · 2019 [cited by examiner]
US 20190313963A1 · Hillen · 2019 [cited by applicant]
US 20190328489A1 · Capron-Richard · 2019 [cited by examiner]
US 20190333627A1 · Johnson · 2019 [cited by applicant]
US 20190357997A1 · Shi et al. · 2019 [cited by applicant]
US 20200015943A1 · Reynard et al. · 2020 [cited by applicant]
US 20200134823A1 · Emoto et al. · 2020 [cited by applicant]
US 20200138518A1 · Lang · 2020 [cited by applicant]
US 20200305808A1 · Ezhov et al. · 2020 [cited by applicant]
US 20200320685A1 · Anssari Moin et al. · 2020 [cited by applicant]
US 20200381105A1 · Bernard et al. · 2020 [cited by applicant]
US 20210082184A1 · Claessen et al. · 2021 [cited by applicant]
US 20210192726A1 · Bergman · 2021 [cited by examiner]
CN 102598054A · 2012 [cited by applicant]
CN 108389207A · 2018 [cited by applicant]
CN 108463172A · 2018 [cited by applicant]
CN 208172859U · 2018 [cited by applicant]
JP 2005050246A1 · 2005 [cited by applicant]
KR 20050020139A · 2005 [cited by applicant]
WO 2017093563A1 · 2017 [cited by applicant]
WO 2018033762A1 · 2018 [cited by applicant]
Doi K. Computer-aided diagnosis in medical imaging: Historical review, current status and future potential. Comput Med Imaging Graph. 2007; 31(4-5): p. 198-211. [cited by applicant]
Rezaei M, Yang H, Meinel C. Deep Neural Network with 12-norm Unit for Brain Lesions Detection. In International Conference on Neural Information Processing; 2017. p. 798-807. [cited by applicant]
Lin PL, Lai YH, Huang PW. An effective classification and numbering system for dental bitewing radiographs using teeth region and contour information. Pattern Recognit. 2010; 43(4): p. 1380-1392. [cited by applicant]
Hosntalab M, Zoroofi RA, Tehrani-Fard AA, Shirani G. Classification and numbering of teeth in multi-slice CT images using wavelet-Fourier descriptor. Int J Comput Assist Radiol Surg. 2010; 5(3): p. 237-249. [cited by applicant]
Miki Y, Muramatsu C, Hayashi T, Zhou X, Hara T, Katsumata A, et al. Classification of teeth in cone-beam CT using deep convolutional neural network. Comput Biol Med. 2016; 80: p. 24-29. [cited by applicant]
Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In Annual Conference on Neural Information Processing Systems (NIPS); 2012. p. 1097-1105. [cited by applicant]
LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998; 86(11): p. 2278-2323. [cited by applicant]
Huang J, Rathod V, Sun C, Zhu M, Korattikara A, Fathi A, et al. Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Jul. 2017. p… [cited by applicant]
LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015; 521: p. 436-444. [cited by applicant]
Lee H, Park M, Kim J. Cephalometric Landmark Detection in Dental X-ray Images Using Convolutional Neural Networks. In SPIE Medical Imaging; 2017. p. 1-6. [cited by applicant]
Ö. Arik S, Ibragimov B, Xing L. Fully automated quantitative cephalometry using convolutional neural networks. J Med Imaging. 2017; 4(1): p. 014501-014501. [cited by applicant]
Wang CW, Huang CT, Lee JH, Li CH, Chang SW, Siao MJ, et al. A benchmark for comparison of dental radiography analysis algorithms. Med Image Anal. 2016; 31: p. 63-76. [cited by applicant]
Liu J, Wang D, Lu L, Wei Z, Kim L, Turkbey EB, et al. Detection and diagnosis of colitis on computed tomography using deep convolutional neural networks. Med Phys. 2017; 44(9): p. 4630-4642. [cited by applicant]
Ren S, He K, Girshick R, Sun J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans Pattern Anal Mach Intell. 2017; 39: p. 1137-1149. [cited by applicant]
Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations (ICLR); May 2015. [cited by applicant]
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. ImageNet: A large-scale hierarchical image database. In The Conference on Computer Vision and Pattern Recognition (CVPR); 2009. p. 248-255. [cited by applicant]
Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. 2015. Available from: tensorflow.org. [cited by applicant]
Jung A. Image augmentation for machine learning experiments. 2015. Available from: https://imgaug.readthedocs.io/en/latest/. Accessed Nov. 29, 2019, 1 pg. [cited by applicant]
Ahmed, Musheer, “Augmenting Accountability, Security And Fraud Detection In Health Data Sharing Systems”, Georgia Institute Of Technology, May 2016, 148 pgs. [cited by applicant]
Harris, John B., “8 Rules For E-Signature Security”, SIGNiX, 2014, 48 pgs. [cited by applicant]
Reducing Healthcare Fraud In Africa; Genkey Solutions b.v., 2016, 12 pgs. [cited by applicant]
Tian Sukun et al: “Automatic Classification and Segmentation of Teeth on 3D Dental Model Using Hierarchical Deep Learning Networks”, IEEE Access, vol. 7, Jun. 21, 2019. pp. 84817-84828, XP011734278, 001:10.1109/Access.2… [cited by applicant]
Fracaro et al., “The Sensitivity and specificity of Clinical Assessment Compared with Bitewing Radiology for Detection of Occlusal Dentin Caries”, American Academy of Pediatric Dentistry 23:3, Mar. 22, 2001, pp. 204-210. [cited by applicant]
Markowitz et al. “In Vitro Study of the Diagnostic Performance of the Spectra Caries Detention Aid”, The Journal of Clinical Dentistry, 2015,17-22,vol. XXXVI No. 1., 6 pgs. [cited by applicant]
Lee et al. “Diagnosis And Prediction Of Periodontally Compromised Teeth Using a Deep Learning-Based Convolutional Neural Network Algorithm”, Journal of Periodontal & Implant Science, Apr. 23, 2018, pp. 114-123. [cited by applicant]
Lee et al., “Detection And Diagnosis Of Dental Caries Using Deep Learning-Based Convolutional Neural Network Algorithm”, Journal of Dentistry, Jul. 25, 2018, 106-111, 77, 6 pgs. [cited by applicant]
Hwang et al. “An Overview of Deep Learning in the Field of Dentistry”, Image Science in Dentistry, Mar. 25, 2019, 49: 1-7. [cited by applicant]
Murata et al., “Towards a Fully Automated Diagnostic System for Orthodontic Treatment in Dentistry,” IEEE Computer Society, 2017, pp. 1-8, 131h international conference on eScience. [cited by applicant]
Shankeeth et al.,“Automated detection of third molars and mandibular nerve by deep learning” (pp. 1-7), Jun. 21, 2019. [cited by applicant]
S. B. Kotsiantis, “Supervised Machine Learning: A Review of Classification Techniques”, Jul. 16, 2007, Informatica 31 (2007) pp. 249-268. [cited by applicant]
L. C. Rabelo, A. Jones and Y. Yih, “Development of a real-time learning scheduler using reinforcement learning concepts,” 1994, 7 pgs. [cited by applicant]
R. Ho, “Pragmatic Programming Techniques: Characteristics of Machine Learning Model”, Feb. 19, 2012, BlogSpot, 3 pgs. [cited by applicant]
Azmi et al., “Freeman Chain Code Representation in Signature Fraud Detection Based on Nearest Neighbor and ANN Classifiers”, International Journal of Image Processing (IJIP), vol. (8): Issue (6): 2014, pp. 434-454. [cited by applicant]
Calberson et al., “Fraudulent Use of Digital Radiography: Methods to Detect and Protect Digital Radiographs”, 2008, JOE, 34(5), pp. 530-536. [cited by applicant]
Young-Jun Yu: “Machine Learning for Dental Image Analysis”, Nov. 29, 2016, Retrieved from https://arxiv.org/ftp/arxiv/papers/1611/1611.09958.pdf, 24 pgs. [cited by applicant]