System and method for ranking bacterial activity leading to tooth and gum disease

1. A system for the optical measurement of pH, comprising:

a light emitter to emit an excitation light;

a detector configured to receive, in response to the excitation light, florescence light produced by a pH-sensitive compound when the pH-sensitive compound contacts one or more surfaces of individual teeth; and

a controller coupled to the detector and the light emitter, wherein the controller includes logic that when executed by the controller, causes the system to perform operations including:

emitting the excitation light from the light emitter;

performing a series of measurements over a period of time, each measurement included in the series of measurements measuring an intensity of the florescence light emitted from the pH-sensitive compound when the pH-sensitive compound contacts the one or more surfaces of the individual teeth;

correlating the intensity of the florescence light to a pH proximate to the one or more surfaces of the individual teeth for the series of measurements to determine at least one of a resting pH, a minimum pH, or a pH recovery rate proximate to the one or more surfaces of the individual teeth; and

determining, based on at least one of the intensity of the florescence light the resting pH, the minimum pH, or the pH recovery rate, one or more locations on the individual teeth likely to develop demineralization.

2. The system of claim 1 , wherein the one or more locations on the individual teeth likely to develop demineralization have a lower pH than other locations on the individual teeth.

3. The system of claim 1 , wherein a combination of the resting pH, the minimum pH, and the pH recovery rate is utilized to determine the one or more locations on the individual teeth likely to develop demineralization.

4. The system of claim 1 , wherein a combination of parameters including at least the resting pH, the minimum pH, and the pH recovery rate is provided to a machine learning algorithm that classifies caries to determine the one or more locations on the individual teeth likely to develop demineralization, and wherein the machine learning algorithm includes at least one of linear regression, multi-class classification, or a deep neural network.

5. The system of claim 1 , wherein the controller further includes logic that when executed by the controller, causes the system to perform operations including:

mapping the one or more locations on a model of the individual teeth.

6. The system of claim 5 , further comprising an image sensor coupled to the controller, wherein the controller further includes logic that when executed by the controller, causes the system to perform operations including:

capturing images of the individual teeth with the image sensor to generate the model; and

mapping the intensity of the florescence light emitted from the individual teeth onto the images of the individual teeth.

7. The system of claim 5 , wherein the image sensor is included in the detector, and wherein a filter blocks a portion of the excitation light from reaching the detector.

8. The system of claim 1 , wherein the excitation light includes 405 nm wavelength light, and wherein the florescence light includes at least one of 620 nm wavelength light or 635 nm wavelength light, and wherein the detector includes a spectrometer or two detectors, wherein the two detectors include a first detector to detect the 620 nm wavelength light and a second detector to detect the 635 nm wavelength light.

9. The system of claim 1 , wherein the light emitter, the detector, and the controller are disposed in a housing, and wherein the system further includes a solution reservoir disposed within the housing and positioned to spray a sugar solution on the individual teeth.

10. The system of claim 1 , wherein the pH-sensitive compound includes at least one of porphyrins or dye molecules.

11. The system of claim 1 , wherein the performing the series of measurements over the period of time includes:

monitoring the one or more locations of the individual teeth likely to develop demineralization over the period of time;

repeatedly measuring the intensity of the florescence light over the period of time to determine a change in local pH of hot spots corresponding to the one or more locations of the individual teeth of the individual teeth; and

determining, based on the change in the local pH of the hot spots, whether the one or more locations of the individual teeth are likely to develop demineralization.

12. The system of claim 1 , wherein the excitation light output by the light emitter has a spot size smaller than the individual teeth.

13. A method for optical detection of pH, comprising:

emitting an excitation light from a light emitter;

detecting, with a detector in response to the excitation light, florescence light produced by a pH-sensitive compound when the pH-sensitive compound contacts one or more surfaces of individual teeth;

performing a series of measurements over a period of time, each measurement included in the series of measurements measuring, using a controller coupled to the detector and the light emitter, an intensity of the florescence light emitted from the pH-sensitive compound when the pH-sensitive compound contacts the one or more surfaces of the individual teeth;

correlating the intensity of the florescence light to a pH proximate to the one or more surfaces of the individual teeth for the series of measurements to determine at least one of a resting pH, a minimum pH, or a pH recovery rate proximate to the one or more surfaces of the individual teeth; and

determining, based on at least one of the intensity of the florescence light, the resting pH, the minimum pH, or the pH recovery rate, one or more locations on the individual teeth likely to develop demineralization.

14. The method of claim 13 , wherein a combination of parameters including at least the resting pH, the minimum pH, and the pH recovery rate is provided to a machine learning algorithm that classifies caries to determine the one or more locations on the individual teeth likely to develop demineralization, wherein the machine learning algorithm includes at least one of linear regression, multi-class classification, or a deep neural network.

15. The method of claim 13 , wherein a combination of the resting pH, the minimum pH, and the pH recovery rate is utilized to determine the one or more locations on the individual teeth likely to develop demineralization.

16. The method of claim 13 , further comprising administering a sugar solution to a mouth of a patient prior to detecting the florescence light.

17. The method of claim 13 , wherein the pH-sensitive compound includes at least one of porphyrins or dye molecules.

18. The method of claim 13 , further comprising mapping the intensity of the florescence light emitted from the one or more surfaces to a model of the individual teeth; and

capturing images of the individual teeth to generate the model using an image sensor coupled to the controller.

19. The method of claim 18 , wherein images of the individual teeth include a 3D reconstruction of the individual teeth.

20. The method of claim 13 , further comprising filtering the excitation light from the florescence light prior to receiving the florescence light with the detector.

21. The method of claim 13 , wherein emitting the excitation light from the light emitter is in response to a patient pressing a button on a housing, wherein the housing includes the light emitter, the detector, and the controller.

22. The method of claim 13 , wherein the one or more locations on the individual teeth likely to develop demineralization have a lower pH than other locations on the individual teeth.

23. The method of claim 13 , wherein measuring the intensity of the florescence light includes at least one of an intensity ratio based measurement or a lifetime based measurement.