Estimating measurements of craniofacial structures in dental radiographs

1. A data processing system comprising:

a processor; and

a memory in communication with the processor, the memory comprising executable instructions that, when executed by, the processor, cause the data processing system to perform functions of:

receiving a dental radiographic image that includes an oral structure;

selecting a segmenter and an object detector;

predicting masks and points of the oral structure using the segmenter and the object detector;

providing image metadata comprising the masks and points and the dental radiographic image to a selector;

selecting by the selector at least one measurement method of a set of measurement methods according to the dental radiographic image and the Image metadata;

calculating a sensor pixel to mm (millimeter) ratio using the measurement method; and

calculating a calibrated measurement of the oral structure using the sensor pixel to mm ratio and the image metadata.

2. The data processing system of claim 1 , wherein the instructions further cause the processor to cause the data processing system to perform functions of:

detecting an orientation of the dental radiographic image; and

if the orientation is incorrect, correcting the orientation.

3. The data processing system of claim 1 , the set of measurement methods comprising:

a known sensor measurement method;

an oral structure measurement method;

a 3D surface data measurement method;

a known implant measurement method; and

an implant angle measurement method.

4. The data processing system of claim 1 , wherein the instructions further cause the processor to cause the data processing system to perform functions of:

receiving data from a library, the library comprising at least one of:

an X-ray sensor database;

an Implant database;

a population based anatomical averages database; and

a patient specific database.

5. The data processing system of claim 4 , wherein the instructions further cause the processor to cause the data processing system to perform functions of:

determining a confidence metric of the calibrated measurement; and

adjusting a threshold based on the confidence metric.

6. The data processing system of claim 4 , wherein the Instructions further cause the processor to cause the data processing system to perform functions of:

providing a machine-learning based training mechanism to train the segmenter and the object detector to identify at least one of Individual teeth, restorations, implants, cemento enamel Junction (CEJ) points, and bone points.

7. The data processing system of claim 1 , wherein the instructions further cause the processor to cause the data processing system to perform functions of:

enabling a graphical user interface to display the radiographic image and the calibrated measurement.

8. The data processing system of claim 7 , wherein the Instructions further cause the processor to cause the data processing system to perform functions of:

displaying a plurality of the calibrated measurements according to the threshold.

9. The data processing system of claim 1 , wherein the instructions further cause the processor to cause the data processing system to perform functions of:

determining an Image type of the dental radiographic image; and

based on the image type, selecting the segmenter and the object detector from a set of segmenters and object detectors.

10. A method for providing a calibrated measurement of an oral structure in a dental radiograph image comprising:

receiving a dental radiographic Image that includes the oral structure;

selecting a segmenter and an object detector;

predicting masks and points of the oral structure using the segmenter and the object detector;

providing image metadata comprising the masks and points and the dental radiographic image to a selector;

selecting by the selector at least one measurement method of a set of measurement methods according to the dental radiographic image and the image metadata;

calculating a sensor pixel to mm (millimeter) ratio using the measurement method; and

calculating a calibrated measurement of the oral structure using the sensor pixel to mm ratio and the image metadata.

11. The method of claim 10 further comprising:

detecting an orientation of the dental radiographic image; and

if the orientation is incorrect, correcting the orientation.

12. The method of claim 10 wherein the set of measurement methods further comprises:

a known sensor measurement method;

an oral structure measurement method;

a 3D surface data measurement method;

a known implant measurement method; and

an implant angle measurement method.

13. The method of claim 10 further comprising:

receiving data from a library, wherein the library further comprises at least one of:

an X-ray sensor database;

an implant database;

a population based anatomical averages database; and

a patient specific database.

14. The method of claim 13 further comprising:

determining a confidence metric of the calibrated measurement; and

adjusting a threshold based on the confidence metric.

15. The method of claim 13 further comprising:

providing a machine-learning based training mechanism to train the segmenter and the object detector to identify at least one of individual teeth, restorations, implants, cemento enamel junction (CEJ) points, and bone points.

16. The method of claim 10 further comprising:

enabling a graphical user interface to display the radiographic image and the calibrated measurement.

17. The method of claim 16 further comprising:

displaying a plurality of the calibrated measurements according to the threshold.

18. The method of claim 10 , further comprising:

determining an image type of the dental radiographic image; and

based on the image type, selecting the segmenter and the object detector from a set of segmenters and object detectors.