CEUS Frame Filtering for Out-of-Plane Motion Artifacts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing contrast enhanced ultrasound (CEUS) imaging systems face challenges with motion artifacts due to patient movement, resulting in out-of-plane images that burden memory and clinician review time, as they are stored and transmitted without effective filtering.
Innovation Solution
A system that generates time-intensity-curves for ultrasound images, identifies and removes out-of-plane frames based on criteria, and displays an optimized set of frames using a pre-trained model like a Siamese Network with Triplet Loss, ensuring only in-plane frames are stored and reviewed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all acquired CEUS frames are stored and transmitted for review, then complete diagnostic data is preserved, but memory and bandwidth resources are excessively consumed
Solution Approach 1:
The system extracts and removes out-of-plane frames from the acquired CEUS sequence using a trained neural network model. Only in-plane frames that meet quality criteria are retained for storage and transmission, eliminating unnecessary data while preserving diagnostically valuable information.
Solution Approach 2:
The system changes the parameter of frame selection from including all frames to selectively including only in-plane frames based on quality assessment. This parameter change in data selection criteria reduces the quantity of stored and transmitted data while maintaining diagnostic reliability.
2Reliability
If all acquired CEUS frames are transmitted to the clinician, then no diagnostic information is lost, but review time is significantly increased
Solution Approach 1:
The system extracts and removes out-of-plane frames that would require clinician review time but provide no diagnostic value. This extraction process reduces the number of frames the clinician must review while ensuring all diagnostically relevant in-plane frames are retained.
Solution Approach 2:
The system performs self-service by automatically identifying and filtering out-of-plane frames using the trained neural network. This automated quality control reduces the burden on the clinician, who only needs to review the pre-filtered set of high-quality in-plane frames.
3Manufacturing precision
If motion compensation is applied during CEUS acquisition, then respiratory motion impact is reduced, but out-of-plane images still occur and burden resources
Solution Approach 1:
The system converts the harmful effect of motion-induced out-of-plane frames into a benefit by using the trained neural network to identify and remove these frames. Rather than trying to prevent all motion artifacts, the system leverages AI to distinguish between useful and useless frames, transforming the problem into a solution.
Solution Approach 2:
The system extracts and removes the remaining out-of-plane frames that persist despite motion compensation techniques. This post-processing extraction complements the motion compensation during acquisition, further reducing storage and transmission burden while maintaining image quality.
Data Source
AI summary
A system for providing contrast enhanced ultrasound (CEUS) images is described. The CEUS system includes an ultrasound probe adapted to provide the ultrasound images; a processor configured to determine out-of-plane frames of the ultrasound images, and remove the out-of-plane frames from the ultrasound images based on a criterion to provide an optimized set of frames; and a display in communication with the processor and configured to display the optimized set of frames.