3D Oral Prosthesis Classification Using AI Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for classifying prosthesis types from three-dimensional oral data are inefficient and prone to misclassification, requiring lengthy manual analysis and lacking objective accuracy.
Innovation Solution
An automated method using deep learning techniques, including layer-wise relevance propagation (LRP), to extract features from three-dimensional oral data and classify prosthesis types using two artificial intelligence neural networks, aligning and combining data to generate feature data for accurate classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual analysis is used to classify prosthesis types from three-dimensional oral data, then the analysis can be performed with simple equipment, but the process is lengthy and prone to misclassification
Solution Approach 1:
The patent replaces manual mechanical analysis with an automated deep learning system using two AI neural networks. The first network extracts features from 3D oral data, and the second network classifies prosthesis types based on these features, eliminating human intervention and significantly reducing analysis time while improving classification accuracy through automated processing.
Solution Approach 2:
The system enables self-service classification by training the AI neural networks to automatically extract features and classify prosthesis types without human assistance. The networks learn from training data and independently perform classification tasks, making the system autonomous and eliminating dependency on manual analysis.
2Reliability
If deep learning with two AI neural networks is used to automate classification, then classification accuracy is improved, but the device complexity increases
Solution Approach 1:
The patent divides the classification system into two separate AI neural networks with distinct functions: the first network specializes in feature extraction from 3D oral data, while the second network specializes in classification. This segmentation allows each network to be optimized for its specific task, improving overall accuracy while making the complex system more manageable through functional decomposition.
Solution Approach 2:
The first AI neural network acts as an intermediary between the raw 3D oral data and the second classification network. It processes the input data and generates feature representations that serve as intermediate outputs, enabling the second network to focus solely on classification without directly processing raw complex data.
3Measurement precision
If feature extraction using AI neural network is implemented, then misclassification risk is reduced, but the computational requirements and processing complexity increase
Solution Approach 1:
The first AI neural network performs preliminary feature extraction before the classification process. By pre-processing the 3D oral data to extract relevant features and generate heatmaps highlighting important regions, the system prepares optimized input for the classification network, improving accuracy while reducing the computational burden on the second network during actual classification.
Data Source
AI summary
An automated method for classifying a prosthesis type from a three dimensional oral data includes aligning a three dimensional oral data including tooth, extracting a feature for determining the prosthesis type to be used for the tooth from the three dimensional oral data which is aligned, combining the three dimensional oral data which is aligned with a feature data including the feature, and classifying the prosthesis type to be used for the tooth based on the three dimensional oral data which is aligned and the feature data.