Automatic Crown Shape Generation Using 3D Dentition Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to accurately and automatically generate a digital representation of a crown shape for a missing tooth in a dentition based solely on 3D maxillofacial data without relying on abutments or additional information, requiring large annotated datasets and specific pose information.
Innovation Solution
A method and system using a digital crown shape model with optimization parameters, iteratively minimizing a loss function based on 3D spatial constraints and user input, employing deep neural networks like DeepSDF for generating and refining crown shapes, and utilizing 3D spatial constraints from neighboring teeth to optimize the crown shape.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If existing deep learning models are used to generate crown shapes, then automation is improved, but the models rely on abutments and screw fixation information that cannot be extracted from standard dentition models
Solution Approach 1:
The patent extracts and removes the dependency on abutment and screw fixation information from the crown shape generation process. By formulating the optimization problem to work exclusively with 3D maxillofacial data and dentition geometry, the solution eliminates the need for these additional data sources, enabling true automation from standard scans alone.
Solution Approach 2:
The patent introduces an intermediary optimization framework that bridges the gap between available 3D maxillofacial data and the desired crown shape. This framework uses spatial constraints and iterative optimization as intermediaries to generate accurate crown shapes without requiring direct abutment or screw fixation inputs.
2Measurement precision
If large annotated 3D maxillofacial datasets are used for training, then model accuracy is improved, but data requirements and training complexity increase
Solution Approach 1:
The patent enables the system to generate accurate crown shapes through self-service optimization using the existing 3D maxillofacial data structure. The optimization framework automatically derives spatial constraints and crown parameters from the input data itself, eliminating the need for external large-scale annotated training datasets while maintaining high accuracy.
3Manufacturing precision
If iterative optimization is performed to minimize loss function, then crown shape precision is improved, but computational time increases
Solution Approach 1:
The patent performs preliminary actions by pre-defining spatial constraints and initial crown parameters from the 3D maxillofacial data before the iterative optimization begins. This preliminary setup reduces the search space and guides the optimization process, enabling faster convergence to precise crown shapes with fewer iterations.
Solution Approach 2:
The patent implements a feedback mechanism through the loss function that continuously evaluates crown shape accuracy against spatial constraints and anatomical requirements. This feedback guides the iterative optimization process efficiently, allowing the system to converge to precise solutions while minimizing unnecessary computational iterations through informed adjustments.
Data Source
AI summary
Methods and systems for automatic generation of a crown shape for a dentition comprise segmenting 3D maxillofacial data into a set of 3D dental objects; determining/receiving a position of a tooth determining 3D spatial constraints for the target crown shape using the set of 3D dental objects; determining an initial pose based for the target crown shape based on 3D dental object(s) of the set of 3D dental objects; and, optimizing parameter(s) associated with a digital crown shape model to determine the target crown shape, including determining a trial crown shape using the digital crown shape model and the parameter(s), computing a loss value for the trial crown shape based on the 3D spatial constraints and the initial pose; and, if the loss value does not meet one or more optimization conditions modifying the parameter(s) to determine a further trial crown shape and to compute a further loss value.