CEUS Phase Identification Using Sequential Neural Video Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Contrast-enhanced ultrasound (CEUS) imaging is challenging for less experienced doctors due to the difficulty in distinguishing between arterial, portal, and delayed phases, and the long duration of video segments complicates algorithm-assisted diagnosis.
Innovation Solution
An image processing method using a neural network to identify and adjust video streams in CEUS, reducing computation by segmenting and identifying phases sequentially, and generating an electronic report based on these streams.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a neural network is used to identify all three phases (arterial, portal, delayed) in the complete video stream, then the phase identification accuracy is improved, but the computational load increases significantly
Solution Approach 1:
The patent divides the video stream processing into two segments: first identifying the arterial phase video stream, then using it as a reference to identify the delayed phase video stream. This segmentation reduces the computational complexity compared to identifying all three phases simultaneously across the entire video stream.
Solution Approach 2:
The patent performs preliminary identification of the arterial phase video stream before identifying the delayed phase. By establishing the arterial phase as a reference point first, the system simplifies subsequent identification tasks and reduces overall computational requirements.
2Loss of information
If the complete video stream is processed to identify all phases, then comprehensive diagnostic information is obtained, but the processing time increases
Solution Approach 1:
The patent segments the phase identification process into sequential steps focusing on arterial and delayed phases, which provides sufficient diagnostic information for distinguishing normal organs from those with lesions, while avoiding the time cost of processing the entire three-phase video stream.
Solution Approach 2:
The patent extracts and focuses on the most diagnostically critical phases (arterial and delayed phases) rather than processing all three phases equally. This extraction of essential information maintains diagnostic value while reducing processing time.
3Ease of operation
If the video stream is adjusted based on the identified arterial phase, then the identification of subsequent phases is simplified, but the system complexity increases
Solution Approach 1:
The patent uses the identified arterial phase video stream as an intermediary reference to facilitate the identification of the delayed phase video stream. This intermediary approach simplifies the identification process by providing a known reference point, while the complexity is managed through algorithmic processing rather than hardware complexity.
Data Source
AI summary
An image processing method for contrast-enhanced ultrasound imaging, including: acquiring a video stream image relating to a contrast-enhanced ultrasound imaging process, wherein the video stream image includes a plurality of image frames, and the video stream image includes an arterial phase video stream, a portal phase video stream, and a delayed phase video stream; identifying a first video stream in the video stream image by using a neural network, wherein the first video stream includes one of the arterial phase video stream and the delayed phase video stream; based on the identified first video stream, adjusting the video stream image, and identifying a second video stream from the adjusted video stream image by using the neural network; and, based on the identified first video stream and second video stream, determining a third video stream in the video stream image.