Intraoral Margin-Line Recognition for Automatic Target Tooth Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing dental CAD/CAM systems require manual user selection of prosthesis target teeth, which is inefficient and time-consuming.

Innovation Solution

A method and apparatus that automatically recognize and select a prosthesis target tooth from intraoral images using a margin line, eliminating the need for manual user selection by employing a data processing apparatus with a processor to analyze and generate prosthesis models based on margin lines.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual user selection is used to identify prosthesis target teeth, then the user can control the selection process, but the process becomes inefficient and time-consuming

Engineering Contradiction:

Improveprosthesis design efficiencyVSAvoidtime for tooth selection

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system automatically identifies and selects prosthesis target teeth using deep neural networks and margin lines without requiring manual user intervention. The computer vision algorithm processes intraoral images, extracts margin lines, and automatically determines target teeth, allowing the system to serve itself rather than requiring continuous user input for tooth selection.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual mechanical selection process is replaced with an automated computational system using deep neural networks and image processing algorithms. The system substitutes human visual inspection and manual selection with automated AI-based tooth identification, thereby eliminating time loss and improving productivity.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If automated tooth recognition is implemented, then productivity increases, but the complexity of the data processing system increases

Engineering Contradiction:

Improveprosthesis design efficiencyVSAvoiddata processing system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The complex automated tooth recognition task is segmented into distinct processing stages: (1) loading intraoral images, (2) extracting margin lines using deep neural networks, (3) processing margin lines to identify target teeth, and (4) generating prosthesis models. This segmentation allows each stage to be optimized independently and simplifies the overall system architecture while maintaining high productivity.

Inventive Principle:

Principle #1Segmentation

3Ease of operation

If manual tooth selection is required, then the user can verify accuracy, but the ease of operation decreases

Engineering Contradiction:

Improveuser convenienceVSAvoidtime for tooth selection

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system provides visual feedback by displaying the automatically identified prosthesis target teeth and generated prosthesis models. Users can review the automated selection results and verify accuracy, and the system allows for necessary adjustments. This feedback mechanism maintains ease of operation while eliminating time loss, as users only need to review rather than manually select teeth.

Inventive Principle:

Principle #23Feedback

Data Source

PatentEP4400074B1Method for processing intraoral image and data processing device

Publication Date: 2025.12.24 MEDIT CORP

Figure 1
Figure 2
Figure 3

AI summary

A method and apparatus for processing an intraoral image are disclosed. The method of processing an intraoral image includes obtaining a first intraoral image including pre-preparation tooth data and a second intraoral image including preparation tooth data, obtaining a margin line based on the preparation tooth data, and automatically recognizing and selecting a prosthesis target tooth from at least one of the first intraoral image and the second intraoral image based on the margin line.