Machine Learning Architecture for Imaging Protocol Detector

Abstract

A system includes one or more processors coupled to non-transitory memory, and the one or more processors are configured to receive a first image representing at least a portion of a mouth of a user, execute a first machine-learning architecture trained to generate a set of features from the first image, determine, based on the set of features, that the first image satisfies at least one criteria for executing a second machine-learning architecture based on the first image, and generate, based on the first image satisfying the at least one criteria, a prompt indicating feedback for capturing a second image representing at least a second portion of the mouth of the user.

What is claimed is: 
     
         1 . A method comprising:
 receiving, by one or more processors coupled to non-transitory memory, a first image representing at least a first portion of a mouth of a user;   executing, by the one or more processors, a first machine-learning architecture trained to generate a set of features from the first image;   determining, by the one or more processors, based on the set of features, that the first image satisfies at least one criteria for executing a second machine-learning architecture based on the first image; and   generating, by the one or more processors based on the first image satisfying the at least one criteria, a prompt indicating feedback for capturing a second image representing at least a second portion of the mouth of the user.   
     
     
         2 . The method of  claim 1 , wherein determining that the first image satisfies the at least one criteria comprises determining that the first image represents the mouth of the user. 
     
     
         3 . The method of  claim 1 , wherein determining that the first image satisfies the at least one criteria comprises determining that at least one of the first image represents the mouth of the user at a predetermined orientation or the first image represents one or more predetermined teeth of the user. 
     
     
         4 . The method of  claim 1 , wherein determining that the first image satisfies the at least one criteria comprises determining that a composite quality score of the first image satisfies a threshold. 
     
     
         5 . The method of  claim 4 , further comprising:
 executing, by the one or more processors, the first machine-learning architecture to generate a plurality of quality scores, each of the plurality of quality scores representing a quality of a respective region of the first image; and   determining, by the one or more processors, the composite quality score based on the plurality of quality scores.   
     
     
         6 . The method of  claim 1 , wherein the prompt comprises an indication for the user to capture the second image wherein the second image depicts the mouth of the user in a different orientation. 
     
     
         7 . The method of  claim 1 , wherein the prompt comprises an indication for the user to capture the second image wherein the second image depicts additional teeth of the user. 
     
     
         8 . The method of  claim 1 , wherein the prompt comprises an indication for the user to capture the second image wherein the second image depicts the mouth of the user in a different orientation. 
     
     
         9 . The method of  claim 1 , the method further comprising:
 storing, by the one or more processors, the first image in the memory;   automatically capturing and receiving, by the one or more processors, the second image after receiving the first image; and   storing, by the one or more processors, the second image in the memory.   
     
     
         10 . The method of  claim 1 , wherein the first image comprises a plurality of images representing at least the first portion of the mouth of the user. 
     
     
         11 . The method of  claim 1 , further comprising receiving a plurality of initial images in serial representing at least the first portion of the mouth of the user until a specific initial image satisfies the at least one criteria, wherein the first image is the specific initial image. 
     
     
         12 . A system comprising:
 one or more processors coupled to non-transitory memory, the one or more processors configured to: 
 receive a first image representing at least a portion of a mouth of a user; 
 execute a first machine-learning architecture trained to generate a set of features from the first image; 
 determine, based on the set of features, that the first image satisfies at least one criteria for executing a second machine-learning architecture based on the first image; and 
 generate a prompt indicating feedback determined based on the first image satisfying the at least one criteria, the prompt indicating feedback for capturing a second image representing at least a second portion of the mouth of the user. 
   
     
     
         13 . The system of  claim 12 , wherein the one or more processors are further configured to determine that the first image satisfies the at least one criteria by determining that the first image represents the mouth of the user. 
     
     
         14 . The system of  claim 12 , wherein the one or more processors are further configured to determine that the first image satisfies the at least one criteria by determining that at least one of the first image represents the mouth of the user at a predetermined orientation or the first image represents one or more predetermined teeth of the user. 
     
     
         15 . The system of  claim 12 , wherein the one or more processors are further configured to determine that the first image satisfies the at least one criteria by determining that a composite quality score of the first image satisfies a threshold. 
     
     
         16 . The system of  claim 15 , wherein the one or more processors are further configured to:
 execute the first machine-learning architecture to generate a plurality of quality scores, each of the plurality of quality scores representing a quality of a respective region of the first image; and   determine the composite quality score based on the plurality of quality scores.   
     
     
         17 . The system of  claim 12 , wherein the prompt comprises an indication for the user to capture the second image wherein the second image depicts the mouth of the user in a different orientation. 
     
     
         18 . The system of  claim 12 , wherein the prompt comprises an indication for the user to capture the second image wherein the second image depicts additional teeth of the user. 
     
     
         19 . The system of  claim 12 , wherein the prompt comprises an indication for the user to capture the second image wherein the second image depicts the mouth of the user in a different orientation. 
     
     
         20 . The system of  claim 12 , wherein the one or more processors are further configured to:
 store the first image in the memory;   automatically capture and receive the second image after receiving the first image; and   store the second image in the memory.   
     
     
         21 . The method of  claim 12 , wherein the first image comprises a plurality of images representing at least the first portion of the mouth of the user. 
     
     
         22 . The method of  claim 12 , wherein the one or more processors are further configured to receive a plurality of initial images in serial representing at least the first portion of the mouth of the user until a specific initial image satisfies the at least one criteria, wherein the first image is the specific initial image. 
     
     
         23 . A non-transitory memory containing instruction that, when executed by one or more processors, causes the one or more processors to perform operations comprising:
 receiving a first image representing at least a portion of a mouth of a user;   executing a first machine-learning architecture trained to generate a set of features from the first image;   determining, based on the set of features, that the first image satisfies at least one criteria for executing a second machine-learning architecture based on the first image; and   generating, based on the first image satisfying the at least one criteria, a prompt indicating feedback for capturing a second image representing at least a second portion of the mouth of the user.   
     
     
         24 . The non-transitory memory of  claim 23 , the operations further comprising: 
 receiving the second image; and   generating, by the second machine-learning architecture, a 3D model of at least a portion of a dental arch of the user based on at least one of the first image or the second image.   
     
     
         25 . The non-transitory memory of  claim 23 , wherein the first image comprises a plurality of images representing at least the first portion of the mouth of the user. 
     
     
         26 . The non-transitory memory of  claim 23 , the operations further comprising receiving a plurality of initial images in serial representing at least the first portion of the mouth of the user until a specific initial image satisfies the at least one criteria, wherein the first image is the specific initial image.