Automatic generation of dental restorations using machine learning

A method for training an artificial intelligence model for generating dental preparations, the method comprising:

• receiving a first dataset comprising digital three-dimensional representations of mouths in which a tooth is missing and is partially replaced with a dental preparation;
• and
• repeating for each of the digital three-dimensional representations of mouths of the first dataset:
• positioning one or more boundaries on one or more teeth;
• for each boundary, removing a corresponding tooth;
• and
• for each boundary, replacing the corresponding tooth with a new dental preparation;
• until quality metrics are satisfied and exit parameters are reached.

A crown generation system configured for generating a three-dimensional crown surface for replacing a missing tooth using an artificial intelligence model;

• the system comprising:
• a storage module for storing digital three-dimensional representation of mouths;
• a processor module having an artificial intelligence model configured to:
• for each of the digital three-dimensional representations of mouths, detect the missing tooth;
• select a tooth model of the missing tooth;
• and
• morph the tooth model into a crown shape using the digital three-dimensional representation of the mouth and the artificial intelligence model, thereby generating the three-dimensional crown surface;
• and
• wherein morphing the tooth model is performed taking into account one or more of a dental preparation, margin line, occlusion, a gap between the dental preparation and adjacent and opposing teeth;
• and
• a memory module for storing the three-dimensional crown surface;
• wherein the artificial intelligence model is trained by:
• receiving a first dataset comprising digital three-dimensional representations of mouths in which a three-dimensional-represented tooth is missing and is partially replaced with a three-dimensional-represented dental preparation;
• and
• repeating for each of the digital three-dimensional representations of mouths of the first dataset;
• positioning one or more boundaries on one or more teeth;
• for each boundary, removing a corresponding tooth;
• and
• for each boundary, replacing the corresponding tooth with a new dental preparation;
• until quality metrics are satisfied and exit parameters are reached.