Cardiac Imaging Artifact Reduction via ECG-Gated Cycle Segmentation

Solution Overview

Problem

Medical imaging technologies, such as CT and MRI, face challenges in producing high-quality cardiac images due to motion blur caused by heartbeats, leading to pulsatile artifacts that hinder accurate disease diagnosis.

Innovation Solution

A method and system that utilize electrocardiogram (ECG) data to iteratively reconstruct cardiac images by identifying and adjusting scan data based on cardiac cycles, employing machine-learned identification models to detect and correct pulsatile artifacts, ensuring the absence of artifacts in the final image.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If scan data is collected during heartbeats to capture cardiac images, then image coverage and diagnostic information are improved, but motion blur causes pulsatile artifacts that degrade image quality

Engineering Contradiction:

Improvecardiac image informationVSAvoidimage quality

Core Design Contradiction:

Loss of informationVSManufacturing precision

Solution Approach 1:

The patent segments the cardiac imaging process into multiple cardiac cycles, dividing scan data into different time periods (first time period and second time period) corresponding to different phases of the cardiac cycle. This segmentation allows selective reconstruction of images from specific cardiac phases, isolating the stationary phase to avoid motion blur while capturing comprehensive cardiac information across multiple cycles.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary classification of scan data into different time periods before image reconstruction. By pre-identifying and separating data from the stationary time period (first time period) versus moving time period (second time period), the system prepares organized datasets that can be reconstructed without motion artifacts, ensuring high image quality from the outset.

Inventive Principle:

Principle #10Preliminary action

2Manufacturing precision

If iterative reconstruction is performed to eliminate pulsatile artifacts, then image quality is improved, but processing time and computational complexity increase

Engineering Contradiction:

Improveimage qualityVSAvoidprocessing time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary classification of scan data into different time periods before image reconstruction. By pre-identifying and separating data from the stationary time period (first time period) versus moving time period (second time period), the system prepares organized datasets that can be reconstructed without motion artifacts, ensuring high image quality from the outset.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent extracts and removes data from the second time period (moving phase with motion blur) and excludes it from the final image reconstruction. By taking out only the necessary data from the first time period (stationary phase), the system eliminates the need for complex iterative artifact removal while achieving artifact-free images.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS11989804B2Systems and methods for medical imaging

Publication Date: 2024.05.21 SHANGHAI UNITED IMAGING HEALTHCARE

AI summary

The present disclosure relates to a method for analyzing an R-wave of an electrocardiogram (ECG) signal. The method includes obtaining an original ECG signal of a subject; filtering the original ECG signal; determining whether to trigger a search gate based on the filtered ECG signal, wherein the search gate is an instruction for detecting an R-wave on the original ECG signal; and detecting the R-wave on the original ECG signal in response to a determination of triggering the search gate.