Cardiac MRI Respiratory Phase Classification for Motion-Corrected Imaging

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional cardiac MRI techniques require breath holds and electrocardiogram synchronization, which are challenging for patients with arrhythmias, chronic respiratory diseases, or unconsciousness, leading to image distortions due to respiratory motion and prolonged exam discomfort.

Innovation Solution

A system that classifies cardiac cycles as occurring during inspiration or expiration using principal component analysis (PCA) to segregate cardiac images, allowing real-time MRI acquisition without breath holds, reducing respiratory motion by monitoring breathing retrospectively through post-processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If breath holds and electrocardiogram synchronization are used in conventional cardiac MRI, then image quality is improved, but patient compliance deteriorates and exam duration increases

Engineering Contradiction:
Improveimage qualityVSAvoidpatient compliance
Core Design Contradiction:
Manufacturing precisionVSEase of operation

Solution Approach 1:

The patent applies segmentation by separating cardiac cycles into distinct respiratory phases (inspiration and expiration) using principal component analysis. This allows independent processing and selection of cardiac cycles from stable respiratory phases, achieving high image quality without requiring patient breath-hold compliance.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes the parameter of respiratory motion management from active breath-holding control to passive retrospective classification based on respiratory phase detection. By monitoring respiratory motion parameters and categorizing cardiac cycles accordingly, the system eliminates the need for patient cooperation while maintaining image quality.

Inventive Principle:
Principle #35Parameter changes

2Object-affected harmful factors

If breath holds are required for cardiac MRI, then respiratory motion is reduced, but exam duration and patient discomfort increase

Engineering Contradiction:
Improverespiratory motionVSAvoidexam duration
Core Design Contradiction:
Object-affected harmful factorsVSLoss of time

Solution Approach 1:

The patent performs preliminary action by retrospectively analyzing and classifying cardiac cycles according to respiratory phase after data acquisition. This preliminary classification enables selective use of high-quality cardiac cycles from stable respiratory phases without requiring prospective breath-hold instructions, reducing both respiratory motion and exam duration.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system applies self-service by automatically detecting respiratory phases and categorizing cardiac cycles without requiring patient participation or breath-hold compliance. The respiratory motion monitoring and classification occur autonomously through post-processing, eliminating the need for patient cooperation while reducing respiratory motion artifacts.

Inventive Principle:
Principle #25Self-service

3Ease of operation

If real-time MRI acquisition without breath holds is performed, then patient compliance is improved, but respiratory motion in images increases

Engineering Contradiction:
Improvepatient complianceVSAvoidimage quality
Core Design Contradiction:
Ease of operationVSManufacturing precision

Solution Approach 1:

The patent extracts high-quality cardiac cycles from the complete dataset by identifying and selecting only those cycles that occur during stable respiratory phases (inspiration or expiration). This extraction process removes the harmful effect of respiratory motion while maintaining patient compliance with free-breathing protocols, as only the most stable cardiac cycles are used for image reconstruction.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent converts the harmful effect of respiratory motion into a beneficial classification mechanism. By using respiratory phase detection to categorize cardiac cycles, the system transforms what would normally be a source of artifact into a useful parameter for selecting optimal images, thereby maintaining image quality without requiring breath-hold compliance.

Inventive Principle:
Principle #22Blessing in disguise (Convert harm into benefit)

4Quantity of substance

If cardiac cycles from all respiratory phases are used, then data completeness is improved, but image clarity deteriorates due to respiratory motion

Engineering Contradiction:
Improvedata completenessVSAvoidimage clarity
Core Design Contradiction:
Quantity of substanceVSManufacturing precision

Solution Approach 1:

The patent applies partial action by selecting only the most suitable cardiac cycles from stable respiratory phases rather than using all available data. This selective approach sacrifices some data quantity but significantly improves image clarity by excluding cycles contaminated with respiratory motion, achieving optimal balance between data completeness and image quality.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS12524844B2Real-time cardiac magnetic resonance (MR) by respiratory phase
Publication Date: 2026.01.13 THE CURATORS OF THE UNIVERSITY OF MISSOURI
  • US12524844B2 patent drawing
  • US12524844B2 patent drawing
  • US12524844B2 patent drawing

AI summary

Systems, methods, and media are provided for image correction of magnetic resonance images (MRIs). Operations include capturing image data using a medical imaging system, and identifying respiratory principal components and cardiac principal components from the image data. The operations also include classifying the cardiac principal components based on whether the cardiac principal components are associated with expiration events or inspiration events of the respiratory principal components, and generating corrected cardiac images using the classified cardiac principal components.