Medical Image Registration for Automated Marker Transfer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing AI-based tools for automating medical image measurements are limited to specific organs and anomalies, requiring tedious tool selection and failing to create relationships between findings across patient studies, making radiological measurements time-consuming.
Innovation Solution
A framework for processing medical images that overlays markers from reference images onto target images using registration techniques, including rigid, affine, and non-rigid methods, with neural networks and edge detection algorithms to automate measurement transfer and adjustment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If radiologists manually place markers and lines on images to compute distances and angles, then measurement accuracy is maintained, but processing time increases significantly
Solution Approach 1:
The system enables automatic self-measurement by using registration algorithms to automatically transfer markers and compute measurements without radiologist intervention. The system serves itself by automating the entire measurement process from marker placement to distance/angle calculation.
Solution Approach 2:
The patent replaces the manual mechanical process of placing markers and measuring distances with automated computational algorithms. Registration algorithms automatically align images and compute measurements, substituting human manual operations with digital processing.
2Loss of time
If AI-based tools are used to automate measurements, then processing time is reduced, but the tools are limited to specific organs and anomalies requiring tedious tool selection
Solution Approach 1:
The system provides a universal measurement framework that works across multiple organs and anomaly types through a single integrated platform. The registration and measurement algorithms are designed to be broadly applicable, eliminating the need to select different specialized tools for different anatomical structures.
Solution Approach 2:
The patent segments the measurement process into independent modular components: image registration, marker transfer, and measurement calculation. This segmentation allows each component to be optimized independently and enables the system to handle diverse organs and anomalies through the same modular framework.
3Extent of automation
If existing AI tools are used for measurements, then automation is achieved, but they fail to create relationships between findings of multiple studies across patient history
Solution Approach 1:
The system performs preliminary registration and marker transfer actions automatically before the radiologist performs any manual measurements. By pre-aligning multiple studies and transferring markers across time points, the system prepares the data structure that enables relationship analysis between longitudinal findings.
Solution Approach 2:
The patent merges multiple separate studies into a unified coordinated framework by registering them to a common reference space. This combining of studies allows the system to create relationships between findings across different time points and modalities, preserving longitudinal information that would otherwise be lost.
Data Source
AI summary
A framework for processing medical images. The framework may include receiving a target medical image, a reference medical image and at least one marker associated with a location in the reference medical image. A corresponding location of the at least one marker is determined in the target medical image. The target medical image is overlaid with the at least one marker at the determined corresponding location to provide an overlaid image. Display data is generated to cause a display device to display the overlaid image.