Noninvasive multimodal oral assessment and disease diagnoses apparatus and method
Methods and apparatuses for assessing oral health and automatically providing diagnosis of one or more oral diseases. Described herein are intraoral scanning methods and apparatuses for collecting and analyzing image data and to detect and visualize features within image data that are indicative of oral diseases or conditions, such as gingival inflammation or oral cancer. These methods and apparatuses may be used for identifying and evaluating lesions, redness and inflammation in soft tissue and caries and cracks in the teeth. The methods can include training a machine learning model and using the trained machine learning model to provide a diagnosis of an oral disease or condition based on image data collected using multiple scanning modes of an intraoral scanner.
1. A method, the method comprising:
receiving or accessing scan data collected from an oral scan of a subject's oral cavity, including a dental arch, the scan data including at least three of: three-dimensional (3D) surface data, color image data, near-infrared (NIR) data, and fluorescence imaging data;
identifying one or more features indicative of gingival inflammation in the scan data using a trained machine learning model, wherein the trained machine learning model is trained on image data including at least three of: previous 3D surface data, previous color image data, previous near-infrared (NIR) data, and previous fluorescence imaging data, wherein the data used to train the trained machine learning model is filtered based on a threshold angle between images of the color image data and a threshold distance between the images of the color image data; and
outputting an indication of gingival inflammation based on the one or more features indicative of gingival inflammation.
2. The method of claim 1 , wherein outputting comprises marking the one or more features indicative of gingival inflammation on images or a 3D model of the subject's dental arch on a display.
3. The method of claim 2 , wherein marking the one or more features indicative of gingival inflammation includes highlighting or labeling the one or more features indicative of gingival inflammation.
4. The method of claim 1 , wherein the one or more features indicative of gingival inflammation include one or more measurements of a cementoenamel junction (CEJ) that are sufficiently high to be associated with gum recession.
5. The method of claim 1 wherein the one or more features indicative of gingival inflammation include one or more measurements of the subject's gums that that are sufficiently red to be associated with gingival inflammation.
6. The method of claim 1 , wherein the one or more features indicative of gingival inflammation include one or more measurements of dental pocket depth that are sufficiently high to be associated with gum recession.
7. The method of claim 1 , wherein the one or more features indicative of gingival inflammation include one or more measurements of blood serum concentration sufficiently high to be associated with gingival inflammation.
8. The method of claim 1 , wherein the trained machine learning model is further trained based on X-ray image data, periodontal chart data and visual inspection/tactile data.
9. The method of claim 1 , wherein the trained machine learning model is further trained based on NIR spectroscopy data.
10. The method of claim 1 , further comprising monitoring changes to the one or more features indicative of gingival inflammation over time to determine improvement or worsening of symptoms of gingival inflammation.
11. The method of claim 10 , further comprising updating a diagnosis of gingival inflammation based on the changes to the one or more features indicative of gingival inflammation.
12. The method of claim 10 , further comprising providing a time lapse video showing the changes to the one or more features indicative of gingival inflammation.
13. A method of diagnosing oral cancer or precancer in a subject, the method comprising:
capturing scan data using an intraoral scanner on the subject's oral cavity, wherein the scan data includes three-dimensional (3D) surface data, color image data, near-infrared (NIR) data, and fluorescence imaging data;
identifying one or more cancer or precancer lesions in the 3D surface data of the scan data using a trained machine learning model, wherein the trained machine learning model is trained on image data including includes previous 3D surface data, previous color image data, previous near-infrared (NIR) data, and previous fluorescence imaging data, wherein the data used to train the trained machine learning model is filtered based on a threshold angle between images of the color image data and a threshold distance between the images of the color image data; and
outputting an indication of oral cancer or precancer based on the identified one or more cancer or precancer lesions.
14. The method of claim 13 , wherein capturing the scan data comprises concurringly collecting the 3D surface data, color image data, near-infrared (NIR) data, and fluorescence imaging data.
15. The method of claim 13 , further comprising determining a size and shape of the one or more cancer or precancer lesions.
16. The method of claim 13 , wherein the trained machine learning model is further trained based on X-ray image data, periodontal chart data and visual inspection/tactile data.
17. The method of claim 13 , wherein the trained machine learning model is further trained based on NIR spectroscopy data.
18. The method of claim 13 , wherein the trained machine learning model is further trained based on fluorescence imaging data collected from previous scans of the subject's oral cavity.
19. A system, the system comprising:
one or more processors;
a memory, accessible by the one or more processors and storing computer-program instructions, that, when executed by the one or more processors, perform a computer-implemented method comprising:
receiving or accessing scan data collected from an oral scan of a subject's oral cavity, the scan data including at least three of: three-dimensional (3D) surface data, color image data, near-infrared (NIR) data, and fluorescence imaging data;
identifying one or more features indicative of gingival inflammation in the scan data using a trained machine learning model, wherein the trained machine learning model is trained on image data including at least three of: previous 3D surface data, previous color image data, previous near-infrared (NIR) data, and previous fluorescence imaging data, wherein the data used to train the trained machine learning model is filtered based on a threshold angle between images of the color image data and a threshold distance between the images of the color image data; and
outputting an indication of gingival inflammation gingival inflammation based on the one or more features indicative of gingival inflammation.
20. The system of claim 19 , further comprising a hand-held wand having at least one image sensor and a plurality of light sources, wherein the plurality of light sources is configured to emit light at a visible light range, a florescent light range, and an infrared light range.
21. The system of claim 19 , wherein the computer-implemented method further comprises:
capturing data of at least a portion of the subject's teeth as an intraoral scanner is moved over the subject's teeth, wherein the captured data includes 3D surface data, color image data, near-infrared (NIR) data, and fluorescence imaging data.