Training method and system for oral-cavity-imaging-and-modeling equipment

Patent metadata

Field	Value
Publication number	US-10504386-B2
Application number	US-201614993798-A
Country	US
Kind code	B2
Filing date	Jan 12, 2016
Priority date	Jan 27, 2015
Publication date	Dec 10, 2019
Grant date	Dec 10, 2019

Abstract

The current document is directed to methods and systems that provide semi-automated and automated training to technicians who use oral-cavity-imaging-and-modeling systems to accurately and efficiently generate three-dimensional models of patients' teeth and underlying tissues. The training methods and systems are implemented either as subsystems within oral-cavity-imaging-and-modeling systems or as separate system in electronic communication oral-cavity-imaging-and-modeling systems. The training methods and systems use an already generated, digital, three-dimensional model of a portion of the oral cavity of a particular patient or of a physical model of a portion of an oral cavity to compute a temporal, translational, and rotational trajectory of an oral-cavity-imaging-and-modeling endoscope, or wand, during a training scan. The temporal, translational, and rotational trajectory is used for a variety of different types of instruction and instructional feedback to facilitate training of technicians.

First claim

The invention claimed is:

1. An automated training system that monitors a training scan to display training information, the automated training system comprising:
one or more processors;
one or more memories that are accessed by the one or more processors;
a display device; and
computer instructions, stored in one or more of the one or more memories that, when executed by the automated training system, control the automated training system to:
display a training user interface on the display device,
continuously capture images of multiple surfaces of a three-dimensional, solid object from a wand that illuminates the one or more surfaces and receives reflected and scattered light from the one or more illuminated surfaces as the wand is moved along a trajectory to scan the one or more surfaces during the training scan,
compute and store, in one or more of the one or more memories, an ordered set of spatial positions and orientations of the wand by matching images of the captured images to projections of a previously created three-dimensional digital model of the solid object wherein the ordered set of spatial positions and orientations of the wand comprises a plurality of vector points and vector point includes: three spatial coordinates, three orientation coordinates, and an indication of the time at which an image was captured from which the spatial coordinates and orientation coordinates were calculated, and
wherein, for each vector point, the three spatial coordinates and three orientation coordinates are computed by:
searching the previously created three-dimensional digital model of the solid object for a projection of a portion of the previously created three-dimensional digital model of the solid object that best matches with the captured image and determining a translation and rotation of the captured image, relative to the previously created 3 D digital model of the solid object, that places the captured image in a position corresponding to the projection; and
computing coordinates of the spatial positions and orientations of the wand from the determined translation and rotation,

compute and display, within the training user interface on the display device, information regarding the accuracy and efficiency of the training scan from the stored ordered set of spatial positions and orientations of the wand.

2. The automated training system of claim 1 wherein the solid object is teeth and tissues within the oral cavity of a patient.

3. The automated training system of claim 1 wherein the solid object is a three-dimensional model of teeth and tissues.

4. The automated training system of claim 1 further comprising:
designating, as normal-scan images, those images captured during the training scan that would have been captured during a normal, non-training scan in which the wand follows a trajectory equivalent to the trajectory of the training scan; and
computing, during or after the training scan, a training-scan-generated three-dimensional digital model of the solid object.

5. The automated training system of claim 4 wherein the information regarding the accuracy and efficiency of the training scan includes one or more of:
indications of the translational velocity of the wand;
indications of the rotational velocity of the wand;
indications of the elapsed time of the scan;
indications of the accuracy of the training-scan-generated three-dimensional digital model of the solid object;
indications of the degree of coverage of the normal-scan images with respect to the surface of the previously created three-dimensional digital model of the solid object;
indications of the spatial trajectory of the wand during the training scan;
indications of the points, in the spatial trajectory of the wand during the training scan, at which normal-scan images were captured;
indications of the similarity of the spatial trajectory of the wand during the training scan to an acceptable-trajectory envelope within which normal-scan images can be captured and used to construct an accurate three-dimensional digital model of the solid object; and
indications of the similarity of the spatial trajectory of the wand during the training scan to an optimal trajectory envelope within which normal-scan images can be captured and used to construct an accurate three-dimensional digital model of the solid object.

6. The automated training system of claim 1 wherein the user interface is additionally displayed on the display of a remote computer system.

7. The automated training system of claim 1 wherein a trainee interacting with the automated training system communicates with a user of the remote computer system by voice and inputs to one or more input devices.

8. The automated training system of claim 1 wherein a captured image is one of:
a two-dimensional photographic image; and
a three-dimensional surface image.

9. A method controlled by computer instructions executed in an automated training system having one or more processors, one or more memories that are accessed by the one or more processors, and a display device, the method comprising:
continuously capturing images of multiple surfaces of a three-dimensional, solid object from a wand that illuminates the one or more surfaces and receives reflected and scattered light from the one or more illuminated surfaces as the wand is moved along a trajectory to scan the one or more surfaces during a training scan; and
computing and storing, in one or more of the one or more memories, an ordered set of spatial positions and orientations of the wand by matching the captured images to projections of a previously created three-dimensional digital model of the solid object,
wherein computing the ordered set of spatial positions and orientation of the wand further includes, for each captured image:
searching the previously created three-dimensional digital model of the solid object for a projection of a portion of the previously created three-dimensional digital model of the solid object that best matches with the captured image and determining a translation and rotation of the captured image, relative to the previously created 3 D digital model of the solid object, that places the captured image in a position corresponding to the projection; and
computing coordinates of the spatial positions and orientations of the wand from the determined translation and rotation,

further wherein the ordered set of spatial positions and orientations of the wand includes a plurality of vector points and each vector point comprises:
three spatial coordinates;
three orientation coordinates; and
an indication of the time at which the image was captured from which the spatial coordinates and orientation coordinates were calculated.

10. The method of claim 9 further comprising;
designating, as normal-scan images, those images captured during the training scan that would have been captured during a normal, non-training scan in which the wand follows a trajectory equivalent to the trajectory of the training scan; and
computing, during or after the training scan, a training-scan-generated three-dimensional digital model of the solid object.

11. An method of claim 10 further comprising:
computing and displaying, on the display device, information regarding the accuracy and efficiency of the training scan from the stored ordered set of spatial positions and orientations of the wand.

12. An method of claim 11 wherein the information regarding the accuracy and efficiency of the training scan includes one or more of:
indications of the translational velocity of the wand;
indications of the rotational velocity of the wand;
indicat

Assignees

• Align Technology Inc

Inventors

• Levin Adi
• Furst Gilad

Classifications

• G06T1/0007

  Image acquisition · CPC title

• G09B23/283 Primary

  for dentistry or oral hygiene (G09B23/286 takes precedence) · CPC title

• A61C9/0053

  Optical means or methods, e.g. scanning the teeth by a laser or light beam · CPC title

• G06F3/0481

  based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance · CPC title

• G06T2200/24

  involving graphical user interfaces [GUIs] · CPC title