Computer-implemented detection and processing of oral features

A system for analyzing an input image of a mouth region to determine a disease or condition of the mouth region, the system comprising:

• a trained machine learning system comprising models that are trained using a dataset of training images, the dataset comprising one or both of:
• a dental caries feature and a periodontitis feature, the trained machine learning system further configured to:
• receive one or more images of the mouth region;
• extract image features from the one or more images;
• analyze the extracted image features generate a prediction based on a recognized feature within each of the one or more images;
• and
• generate an oral health score for each of the one or more images corresponding to the recognized feature associated with one or both of:
• the dental caries feature and the periodontitis feature.

A method for analyzing a mouth region to provide information regarding a disease or condition of the mouth region, the method comprising:

• at a trained machine learning system comprising models that are trained using a dataset of training images, wherein the dataset comprises one or both of:
• a dental caries feature and a periodontitis feature:
• receiving one or more images;
• extracting image features from the one or more images;
• analyzing the extracted image features to generate a prediction based on a recognized feature within each of the one or more images;
• and
• generating an oral health score for each of the one or more images corresponding to the recognized feature associated with one or both of the dental caries feature and the periodontitis feature.

A method for training a machine learning system for analyzing an input image to provide information regarding a disease or condition, the method comprising:

• receiving a dataset of training images, the dataset of training images comprising a mouth region having one or both of:
• a dental feature and an oral feature;
• partitioning the dataset into one or more subsets, wherein one subset is used as validation images for each remaining subset of the one or more subsets of training images, to provide one or more trained models;
• receiving a user input image of a user mouth region, wherein the user input image is a 3-channel image;
• converting the 3-channel image into a 1-channel image to provide a greyscale user input image;
• and
• analyzing the user mouth region of the greyscale user input image using the one or more trained models to provide a prediction of a presence or an absence of one or both of:
• the dental feature or the oral feature.