3D Dental Image Inference for Root Structure Without CBCT
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing dental imaging methods, such as physical impressions and intra-oral scans, fail to provide detailed information about the internal volumetric structures of teeth and surrounding oral cavity, while CBCT scans, though capable, have lower resolution and health and cost concerns.
Innovation Solution
A machine learning inference model is trained using co-registered three-dimensional image data to map from surface representations of intra-oral tissue to generate a full three-dimensional representation of internal structures, including teeth roots and surrounding tissues, without the need for CBCT scans.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If CBCT scans are used to obtain internal volumetric structures, then information about root structure and internal tissue is improved, but measurement precision and patient safety deteriorate due to lower resolution and X-ray exposure
Solution Approach 1:
The patent introduces an inference model trained on co-registered surface representation and CBCT data as an intermediary. This model predicts internal volumetric structures from surface representations, eliminating the need for direct CBCT scanning while providing high-resolution predictions that match or exceed actual CBCT resolution.
Solution Approach 2:
The patent creates a virtual copy of the internal volumetric structures by training the inference model on CBCT data during development. Once trained, the model generates predicted CBCT-like images from surface representations, providing a non-ionizing copy of the internal structures that maintains high resolution without requiring actual X-ray exposure.
2Loss of information
If CBCT scans are used to obtain internal volumetric structures, then information about root structure is improved, but health safety and cost worsen due to X-ray exposure and expense
Solution Approach 1:
The inference model serves as an intermediary that translates surface representation data into predicted internal structures, replacing the harmful CBCT scanning process with a computational approach that requires no ionizing radiation exposure to the patient.
Solution Approach 2:
The patent replaces the expensive, resource-intensive CBCT scanning process with a computationally efficient inference model that has already been trained on CBCT data. The model provides a low-cost alternative that eliminates recurring exposure costs and reduces dependency on expensive imaging equipment for routine treatment planning.
3Ease of operation
If physical impressions or intra-oral scans are used, then ease of operation is improved, but loss of information worsens as they only provide surface information
Solution Approach 1:
The patent transforms two-dimensional surface representation data into three-dimensional internal volumetric structure predictions through the inference model. This dimensional transformation allows the system to maintain the simplicity of surface scanning while gaining access to internal structural information that was previously only obtainable through CBCT.
Solution Approach 2:
The inference model acts as an intermediary computational layer that bridges surface representations and internal structures. It takes easily obtained surface data as input and generates predicted internal volumetric information, combining the advantages of both simple imaging and comprehensive structural information.
Data Source
AI summary
Creation and/or use of an inference model that maps between a three-dimensional image data of an intra-oral tissue structure, e.g. shape and size of teeth roots, and a three-dimensional representation of an exposed surface of dental features of the intra-oral tissue structure, e.g. teeth crowns. One method disclosed for image processing, using an inference model, includes a computer-readable surface representation of an individual's intra-oral tissue to provide a full three-dimensional representation of the intra-oral tissue. Also proposed is a method for creating the inference model.