Tooth decay diagnostics using artificial intelligence
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12440149-B2
Publication Date
2025-10-14
Expiration Date
Abstract
A device is disclosed for diagnosing a dental condition. The device captures image data representative of a tooth of a patient based on data obtained from a hardware device that scans the tooth. The device inputs the image data into a first supervised machine learning model, and receives, as output from the first supervised machine learning model, a plurality of biomarkers, each biomarker corresponding to a different location of the tooth. The device inputs the plurality of biomarkers into a second supervised machine learning model, and receives, as output from the second supervised machine learning model, a diagnosis of a dental condition.
Core Innovation
The disclosure describes non-X-ray dental-condition screening using Deep Penetration Optical Coherence Tomography (DPOCT) data and intensity maps, optionally combined with color images of a tooth. A first supervised machine learning model detects changes in intensity between regions and produces location-specific biomarkers. A second supervised machine learning model receives the biomarkers and produces a diagnosis of a dental condition.
The disclosed approach supports autonomous, point-of-care screening and is stated to improve access. Historical biomarkers and changes in intensity may also inform diagnosis. The supplied partial content does not include the background section; therefore, the problem identified in that section is not explicitly described in patent. The disclosed claim forms include a method, a computer-readable medium, and a system.
Claims Coverage
There are three independent claims corresponding to three inventive features: claim 1 covers a method, claim 5 covers a non-transitory computer-readable medium, and claim 9 covers a system. The three claims share the same principal image-processing and diagnosis approach, expressed in different claim forms.
Method for diagnosing a dental condition
Independent claim 1 captures tooth image data comprising DPOCT data and an intensity map reflective of optical properties. A first supervised machine learning model uses the intensity map and a color image to produce biomarkers for different tooth locations, with its output excluding color data from the color image. A second supervised machine learning model receives the biomarkers and outputs a diagnosis. Dependent claims also cover historical biomarkers, intensity differences, and multiple biomarker-associated diagnoses.
Computer-readable medium with diagnostic instructions
Independent claim 5 covers a non-transitory computer-readable medium with instructions that cause processors to perform the claimed image capture, biomarker generation, and diagnosis operations. The operations use DPOCT intensity-map data and a color image, generate location-specific biomarkers with a first supervised machine learning model, and provide them to a second supervised machine learning model. Dependent claims add historical biomarkers, intensity differences, and multiple diagnoses associated with different biomarkers.
System for diagnosing a dental condition
Independent claim 9 covers memory containing diagnostic instructions and processors that execute the claimed operations. The system uses DPOCT data and an intensity map with a color image to generate location-specific biomarkers through a first supervised machine learning model, then uses a second supervised machine learning model to produce a diagnosis. Dependent claims cover using historical biomarkers and intensity differences as diagnostic inputs.
The independent claims cover the same DPOCT-based, two-model diagnostic approach as a method, computer-readable medium, and system. The dependent claims further address historical biomarkers, comparisons of intensity, and—in the method and medium claim families—multiple diagnoses associated with different biomarkers.
Stated Advantages
The disclosure highlights autonomous, point-of-care screening.
The disclosure states that the approach improves access.
Documented Applications
Non-X-ray screening and diagnosis of dental conditions using tooth image data.
Point-of-care dental-condition screening.
Interested in licensing this patent?