Medical Image Motion Detection for Resting Phase Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting resting phases in medical imaging, such as MRI, are manual, time-consuming, and prone to errors, especially in cases of varying heart rates or arrhythmia, and lack automation for region-specific detection.
Innovation Solution
A method using deep neural networks for automatic motion detection in medical image-series, involving localization and motion data calculation, which can be implemented in various imaging systems, including MRI, fluoroscopy, ultrasound, and CT, to identify and track targets like coronary arteries and ventricles, reducing the need for manual interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual inspection of CINE image series is used to detect resting phases, then detection accuracy can be achieved, but the process is time-consuming and requires user experience
Solution Approach 1:
The patent replaces the manual mechanical inspection process with an automated computer-based system that uses image analysis algorithms to detect resting phases, eliminating the need for operator intervention while maintaining detection accuracy
Solution Approach 2:
The system enables self-service by automatically analyzing CINE image series to identify resting phases without requiring operator expertise or manual frame-by-frame inspection, making the process independent of user experience
2Measurement precision
If manual detection by medical expert is performed, then region-specific resting phases can be identified, but the workflow is expensive and prone to error
Solution Approach 1:
The patent replaces manual detection by medical experts with an automated computer-based analysis system that objectively identifies region-specific resting phases, eliminating human error and variability while maintaining precise region-specific detection
Solution Approach 2:
The system provides automated feedback through algorithmic analysis of image data, consistently applying the same detection criteria across all cases to eliminate the variability and errors inherent in manual human inspection
3Quantity of substance
If CINE imaging is acquired for resting phase detection, then sufficient image data is obtained, but the additional acquisition time increases total recording time
Solution Approach 1:
The patent makes the CINE imaging serve dual purposes: it provides both the diagnostic image data needed for medical evaluation and the motion information required for resting phase detection, eliminating the need for separate dedicated detection sequences
4Area of stationary object
If whole-heart coverage is needed, then comprehensive imaging is achieved, but the intersecting set of region-specific resting phases reduces available acquisition windows
Solution Approach 1:
The patent merges multiple region-specific resting phase detections into a unified whole-heart analysis, identifying time points where all regions are simultaneously in resting phase, thereby optimizing the acquisition window for comprehensive coverage
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
The invention describes a method for automatic motion detection in medical image-series, comprising the steps: - providing a dataset (D) of a series of images (I1, I2, I3), wherein images (I1, I2, I3) of a similar region of interest are recorded at consecutive points of time, - calculating localization data (LD) of a target (T) by localizing the target (T) in the images (I1, I2, I3) of the dataset (D) and calculating the position of this target (T) in these images (I1, I2, I3), - calculating movement data (MD) of the movement of the target (T) on the basis of temporal adjacent images (I1, I2, I3) based on the localization data (LD). The invention further describes a related system, a related control device and a related medical imaging system.