Dental image analysis and treatment planning using an artificial intelligence engine
A trained artificial intelligence engine analyzes a subject's dental images and dental survey results to determine whether the subject has an apparent dental condition. The artificial intelligence engine is trained using manually-classified dental images and model survey results. The trained artificial intelligence engine can annotate the subject's dental images to indicate landmark structures and the location of the apparent dental condition. In addition, the trained artificial intelligence engine can generate a confidence score that indicates the likelihood that the subject has the apparent dental condition.
1. A non-transitory computer-readable medium storing instructions that, when executed by a computer having a hardware-based processor, cause the computer to:
store a subject's dental images in a memory of the computer;
automatically determine an apparent dental condition in the subject by analyzing the subject's dental images with an artificial neural network stored in the memory, the artificial neural network trained using manually-diagnosed dental images from other subjects;
generate at least one output signal that represents the apparent dental condition; and
generate a graphical output a representation of the apparent dental condition with respect to one of said dental images;
wherein the instructions further cause the computer to store dental survey responses of the subject in the memory of the computer; and
automatically determine the apparent dental condition in the subject by analyzing the dental images and the dental survey responses with the artificial neural network, the artificial neural network trained using the manually-diagnosed dental images from other subjects and a plurality of model dental survey response sets.
2. The non-transitory computer-readable medium of claim 1 , wherein the instructions further cause the computer to determine a likelihood that the subject has the apparent dental condition, wherein the at least one output signal includes the likelihood.
3. The non-transitory computer-readable medium of claim 2 , wherein the likelihood is quantitative.
4. The non-transitory computer-readable medium of claim 2 , wherein the instructions further cause the computer to determine the likelihood based on a fit of the subject's dental images to the manually-diagnosed dental images used to train the artificial neural network.
5. The non-transitory computer-readable medium of claim 1 , wherein the instructions further cause the computer to graphically annotate on the graphical output depicting said one of the subject's dental images to indicate which of the subject's teeth has the dental condition.
6. The non-transitory computer-readable medium of claim 5 , wherein the instructions further cause the computer to graphically annotate the at least one of the subject's dental images to indicate a landmark structure in the subject's mouth.
7. The non-transitory computer-readable medium of claim 1 , wherein the model dental survey response sets include hypothetical dental survey response sets from hypothetical patients.
8. The non-transitory computer-readable medium of claim 1 , wherein the instructions further cause the computer to generate a dental information output signal that corresponds to dental information regarding the apparent dental condition.
9. The non-transitory computer-readable medium of claim 1 , wherein the instructions further cause the computer to generate a dental cost estimate output signal that corresponds to a cost estimate for treating the apparent dental condition.