Methods and systems for employing artificial intelligence in automated orthodontic diagnosis and treatment planning

• US 9,152,767 B2
• Filed: 09/18/2014
• Issued: 10/06/2015
• Est. Priority Date: 03/17/2010
• Status: Active Grant

• Current Assignee: ClearCorrect Holdings LLC (ClearCorrect Incorporated)
• Original Assignee: ClearCorrect Holdings LLC (ClearCorrect Incorporated)
• Inventors: Mah, James
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): Smith, Paulinho E
• Application Number:
  US14/490,344
• Publication Number:
  US 20150006465A1
• Time in Patent Office: 383 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/0088 for oral or dental tissue
• CPC Class Codes: A61B 5/4547 Evaluating teeth
• CPC Class Codes: A61B 5/4552 Evaluating soft tissue within the mouth, e.g. gums or tongue
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7475 User input or interface means, e.g. keyboard, pointing device, joystick
• CPC Class Codes: A61C 19/05 for determining occlusion
• CPC Class Codes: A61C 7/002 Orthodontic computer assisted systems
• CPC Class Codes: G06F 16/24 Querying
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A method for treating an orthodontic condition can include receiving patient data, such as through a website, accessing a database having information derived from patient treatments, generating a model of an orthodontic condition defining one or more anatomic features of a set of teeth, identifying a diagnosis of an orthodontic condition and identifying a treatment regimen for the diagnosis. A method can include tagging an anatomic feature with an electronic identifier and automatically generating a tooth setup. A system can include a server and a database, which can include information relating to patient treatments, and a website for receiving patient data. A system can include an electronic model representing anatomic features of a patient'"'"'s teeth and an application adapted to identify a diagnosis and a treatment regimen for an orthodontic condition, which can include executing artificial intelligence and/or other algorithms.

Claims

1. A method for diagnosing and identifying a treatment for an orthodontic condition, comprising:

receiving patient data regarding the orthodontic condition onto a server;

accessing a database that comprises or has access to information derived from patient treatments, the information derived from patient treatments including an electronically stored data set for each patient treatment, wherein each data set includes data that represents at least one of (a) a location and position of one or more teeth subject of a corresponding patient treatment and (b) a previously diagnosed orthodontic condition for the corresponding patient treatment;

generating an electronic treatment model of the orthodontic condition by defining coordinates that represent at least two anatomic features of a set of teeth; and

executing one or more algorithms that cause a processor to;

compare the coordinates to at least a portion of the information derived from patient treatments;

identify a best fit data set that represents a statistical or prioritized best fit for the coordinates;

identify at least one diagnosis of the orthodontic condition by prioritizing at least a portion of the data from a plurality of the data sets and outputting one or more of (a) a diagnosis, (b) the diagnosis along with a probability value representing a likelihood the diagnosis is accurate, and (c) a plurality of diagnoses along with a plurality of probability values, wherein each of the plurality of probability values represents a likelihood that a corresponding one of the plurality of diagnoses is accurate; and

identify at least one treatment regimen for the at least one diagnosis by prioritizing at least a portion of the data from a plurality of the data sets and outputting one or more of (a) a treatment regimen, (b) the treatment regimen along with a probability value representing a likelihood the treatment regimen is accurate, and (c) a plurality of treatment regimens along with a plurality of probability values, wherein each of the plurality of probability values represents a likelihood that a corresponding one of the plurality of treatment regimens is accurate, the at least one treatment regimen for the at least one diagnosis including at least one of a treatment approach, a corrective appliance and a combination thereof.

2. The method of claim 1, further comprising tagging one or more of the at least two anatomic features with an electronic identifier, the electronic identifier being at least one of an identifier generated by an algorithm, an identifier defined by a user and a combination thereof.

3. The method of claim 1, further comprising wherein the at least two anatomic features are selected from the group consisting of incisal edges, cusp tips, occlusal fossa, points of maximum crown convexity, marginal ridges, interproximal contact points, interocclusal contact points, interdental papilla heights, marginal gingival lines, zones of attached gingiva and a combination thereof.

4. The method of claim 1, further comprising aligning the at least two anatomic features.

5. The method of claim 1, further comprising aligning the at least two anatomic features based on a pattern representing a target orthodontic condition, wherein the target orthodontic condition is at least one of an ideal condition, an acceptable condition based on a consensus of previously successful patient treatments and a combination thereof.

6. The method of claim 1, further comprising aligning the at least two anatomic features along a curve.

7. The method of claim 1, further comprising aligning the at least two anatomic features along a spline.

8. The method of claim 1, further comprising aligning the at least two anatomic features relative to one or more additional anatomic features defined in the model.

9. The method of claim 1, wherein a first of the at least two anatomic features is on a first arch and a second of the at least two anatomic features is on a second arch, the method further comprising aligning the first anatomic feature on the first arch relative to the second anatomic feature on the second arch.

10. The method of claim 1, further comprising receiving patient data on the server through a website.

11. The method of claim 1, further comprising wherein the database comprises or has access to patient treatment information derived from at least one of textbooks, scientific literature, results derived from ongoing patient treatments, results derived from completed patient treatments and a combination thereof.

19. The method of claim 1, further comprising outputting a malocclusion classification for the orthodontic condition along with a probability value representing a likelihood the identified malocclusion classification is accurate.

20. The method of claim 1, further comprising outputting a list of potential treatment regimens along with a plurality of probability values, wherein each of the plurality of probability values represents a relative likelihood that a corresponding one of the potential treatment regimens will be effective to reorient one or more teeth of the set of teeth represented in the electronic treatment model, and wherein the potential treatment regimens include at least one of interproximal tooth reduction, tooth extraction, tooth restoration and a combination thereof.

21. The method of claim 1, wherein the information derived from patient treatments includes data representing treatment time for one or more patient treatments and the method further comprises outputting at least one of an estimated treatment time and an average treatment time for the at least one treatment regimen.

22. The method of claim 1, wherein the at least one diagnosis is the same as a prior diagnosis for a patient treatment corresponding to the best fit data set.

23. The method of claim 1, wherein the at least one treatment regimen is the same as a prior treatment regimen for a patient treatment corresponding to the best fit data set.

12. A system for diagnosing and identifying a treatment for an orthodontic condition, comprising:

a server having a processor and configured to receive patient data;

a database that comprises or has access to information derived from patient treatments, the information derived from patient treatments including an electronically stored data set for each patient treatment, wherein each data set includes data that represents at least one of (a) a location and position of one or more teeth subject of a corresponding patient treatment and (b) a previously diagnosed orthodontic condition for the corresponding patient treatment;

an electronic treatment model of the orthodontic condition that defines coordinates that represent at least two anatomic features of a set of teeth; and

at least one computer program housed within or accessible by the server that, when executed by the processor causes the processor to;

compare the coordinates to at least a portion of the information derived from patient treatments;

identify a best fit data set that represents a statistical or prioritized best fit for the coordinates;

identify at least one diagnosis of the orthodontic condition by prioritizing at least a portion of the data from a plurality of the data sets and outputting one or more of (a) a diagnosis, (b) the diagnosis along with a probability value representing a likelihood the diagnosis is accurate, and (c) a plurality of diagnoses along with a plurality of probability values, wherein each of the plurality of probability values represents a likelihood that a corresponding one of the plurality of diagnoses is accurate; and

identify at least one treatment regimen for the at least one diagnosis by prioritizing at least a portion of the data from a plurality of the data sets and outputting one or more of (a) a treatment regimen, (b) the treatment regimen along with a probability value representing a likelihood the treatment regimen is accurate, and (c) a plurality of treatment regimens along with a plurality of probability values, wherein each of the plurality of probability values represents a likelihood that a corresponding one of the plurality of treatment regimens is accurate, wherein the at least one treatment regimen for the at least one diagnosis includes at least one of a treatment approach, a corrective appliance and a combination thereof.

13. The system of claim 12, further comprising wherein the at least two anatomic features are each defined by an electronic identifier that is at least one of an identifier generated by an algorithm, an identifier defined by a user and a combination thereof.

14. The system of claim 12, further comprising wherein the at least two anatomic features are selected from the group consisting of incisal edges, cusp tips, occlusal fossa, points of maximum crown convexity, marginal ridges, interproximal contact points, interocclusal contact points, interdental papilla heights, marginal gingival lines, zones of attached gingiva and a combination thereof.

15. The system of claim 12, further comprising wherein the at least one computer program is configured to align the at least two anatomic features at least one of relative to one another, based on a pattern representing a target orthodontic condition, along a curve, along a spline, relative to one or more additional anatomic features defined in the model, and a combination thereof.

16. The system of claim 12, further comprising a website and wherein the server is configured to receive patient data through the website.

17. The system of claim 12, further comprising wherein the database comprises or has access to patient treatment information derived from at least one of textbooks, scientific literature, results derived from ongoing patient treatments, results derived from completed patient treatments and a combination thereof.

18. A non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, cause the processor to perform a method comprising:

receiving patient data regarding an orthodontic condition onto a server;

accessing a database that comprises or has access to information derived from patient treatments, the information derived from patient treatments including an electronically stored data set for each patient treatment, wherein each data set includes data that represents at least one of (a) a location and position of one or more teeth subject of a corresponding patient treatment and (b) a previously diagnosed orthodontic condition for the corresponding patient treatment;

generating an electronic treatment model of the orthodontic condition by defining coordinates that represent at least two anatomic features of a set of teeth;

comparing the coordinates to at least a portion of the information derived from patient treatments;

identifying a best fit data set that represents a statistical or prioritized best fit for the coordinates;

identifying at least one diagnosis of the orthodontic condition by prioritizing at least a portion of the data from a plurality of the data sets and outputting one or more of (a) a diagnosis, (b) the diagnosis along with a probability value representing a likelihood the diagnosis is accurate, and (c) a plurality of diagnoses along with a plurality of probability values, wherein each of the plurality of probability values represents a likelihood that a corresponding one of the plurality of diagnoses is accurate; and

identifying at least one treatment regimen for the at least one diagnosis by prioritizing at least a portion of the data from a plurality of the data sets and outputting one or more of (a) a treatment regimen, (b) the treatment regimen along with a probability value representing a likelihood the treatment regimen is accurate, and (c) a plurality of treatment regimens along with a plurality of probability values, wherein each of the plurality of probability values represents a likelihood that a corresponding one of the plurality of treatment regimens is accurate, the at least one treatment regimen for the at least one diagnosis including at least one of a treatment approach, a corrective appliance and a combination thereof.