Deep Learning Dental Arch Analysis for Aligner Separation Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current orthodontic treatments require patients to transmit dental arch images to orthodontists for analysis, which is inefficient and lacks automation.
Innovation Solution
A method utilizing deep learning devices, preferably neural networks, to analyze dental arch images by creating a learning base of historical images, training the network, and determining tooth and image attributes, with an enrichment method to automatically update the learning base using patient-acquired images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual analysis by orthodontist is used, then analysis accuracy is maintained, but productivity is low and time consumption is high
Solution Approach 1:
The system enables self-service through automated deep learning analysis that processes dental images without requiring orthodontist intervention for routine assessments. The neural network independently performs tooth detection, attribute extraction, and change detection, allowing the system to serve itself for common analysis tasks while maintaining clinical accuracy.
Solution Approach 2:
The patent replaces the mechanical manual analysis process with an automated deep learning system. The neural network substitutes the orthodontist's visual inspection and manual measurement processes, using computational algorithms to detect teeth, extract attributes, and identify changes between images, thereby dramatically increasing productivity and reducing time loss.
2Extent of automation
If deep learning device is implemented, then productivity and automation are improved, but device complexity increases
Solution Approach 1:
The deep learning device is designed with multi-functionality to handle various analysis tasks within a single unified system. The same neural network infrastructure performs tooth detection, attribute extraction (shape, position, color), and change detection across different image types, reducing the need for multiple specialized systems and managing complexity through functional integration.
Solution Approach 2:
The system performs preliminary actions by pre-training the neural network on large datasets of historical dental images before deployment. This preliminary training phase establishes the model's capabilities in advance, allowing the deployed system to automatically process new images without requiring complex real-time adjustments or manual configuration, thereby managing operational complexity.
3Measurement precision
If learning base is enriched with patient images, then measurement precision is improved, but loss of information increases due to privacy concerns
Solution Approach 1:
The system extracts only the essential visual features and attributes needed for dental analysis from patient images, separating these diagnostic elements from personally identifiable information. The neural network processes and extracts tooth-level attributes (shape, position, color) while the system architecture enables storing and analyzing this extracted data without retaining complete original images that would contain sensitive patient information.
Solution Approach 2:
The system creates processed copies of dental images that contain extracted tooth attributes and analysis results rather than storing original patient photographs. These derivative copies retain the diagnostic information needed for training and analysis while removing or obscuring personally identifiable features, allowing learning base enrichment while protecting patient privacy.
Data Source
AI summary
A method for assessing the shape of an orthodontic aligner, said method comprising the following steps:a″) acquisition of at least one image at least partially representing the aligner in a service position in which it is worn by a patient, called “analysis image”;b″) analysis of the analysis image by means of a deep learning device, preferably a neural network, trained by means of a learning base, so as to determine a value for at least one tooth attribute of an “analysis tooth zone” representing, at least partially, a tooth on said analysis image, the tooth attribute relating to a separation between the tooth represented by the analysis tooth zone, and the aligner represented on the analysis image, and/orfor an image attribute of the analysis image, the image attribute relating to a separation between at least one tooth represented on the analysis image, and the aligner represented on said analysis image.