Tomographic Image 3D Coordinate Derivation Using Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The process of setting three-dimensional coordinates for bounding boxes in three-dimensional medical images, such as CT and MRI images, is computationally intensive and time-consuming.
Innovation Solution
An image processing apparatus and method that utilizes a derivation model trained through machine learning to efficiently derive three-dimensional coordinate information for structures in tomographic images, including the position of the structure within the tomographic plane and outside the plane, using supervised training data to align and integrate coordinate information across multiple images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to set three-dimensional coordinates for bounding boxes in medical images, then measurement precision can be achieved, but processing time becomes excessively long due to large calculation amounts
Solution Approach 1:
The system performs preliminary actions by pre-processing medical images to extract feature information and pre-calculating potential bounding box positions before the actual coordinate setting is needed. This preparation work is done in advance so that when three-dimensional coordinates are required, the system can quickly retrieve and utilize the pre-computed data, significantly reducing processing time while maintaining accuracy
Solution Approach 2:
The invention creates simplified copies or representations of the complex three-dimensional coordinate calculation problem. By generating two-dimensional projections or intermediate representations from the three-dimensional medical images, the system can work with less computationally intensive data structures that still contain the essential spatial information needed to determine accurate bounding box coordinates
2Manufacturing precision
If comprehensive three-dimensional coordinate information is derived for all structures, then manufacturing precision is improved, but device complexity increases due to processing multiple tomographic images
Solution Approach 1:
The system extracts only the essential and relevant information from the complex three-dimensional medical images. By identifying and extracting key feature points, edges, and structural characteristics that are necessary for bounding box definition, the system avoids processing unnecessary data, thereby reducing computational complexity while preserving the precision needed for accurate coordinate determination
Solution Approach 2:
The invention segments the complex task of three-dimensional coordinate derivation into smaller, more manageable sub-tasks. The process is divided into stages such as image preprocessing, feature detection, coordinate calculation, and validation. Each stage handles a specific aspect of the problem independently, making the overall system less complex and easier to implement while maintaining high precision through coordinated execution of these modular components
Data Source
AI summary
An image processing apparatus includes at least one processor, and the processor derives three-dimensional coordinate information that defines a position of a structure in a tomographic plane from a tomographic image including the structure, and that defines a position of an end part of the structure outside the tomographic plane in a direction intersecting the tomographic image.