4D MR Flow Valve Tracking for Accurate Cardiac Flow Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for analyzing blood flow in cardiac valves using 2D phase-contrast MRI are prone to errors due to operator dependency, out-of-plane motion, and require additional datasets, making them time-consuming and unreliable for accurate diagnosis.

Innovation Solution

A computer-implemented method utilizing 4D MR Flow data for automatic detection and tracking of cardiac valves without additional datasets, employing machine learning and template matching to determine feature locations and perform quantitative flow analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If 2D phase-contrast MRI is used for flow analysis, then flow quantification can be performed, but operator dependency and out-of-plane motion cause measurement errors

Engineering Contradiction:
Improveflow measurement accuracyVSAvoiddiagnosis reliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent transitions from 2D static plane analysis to 4D dynamic volumetric analysis by acquiring flow data across the entire heart volume over time. This dimensional expansion eliminates out-of-plane motion errors and operator dependency in plane positioning, as the analysis adapts to actual valve positions in three-dimensional space throughout the cardiac cycle.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent implements dynamic adaptation of analysis planes to track moving cardiac valves throughout the cardiac cycle. Instead of using fixed static planes, the system continuously adjusts the analysis planes to follow valve motion, transforming the static 2D approach into a dynamic 4D approach that maintains measurement accuracy despite heart movement.

Inventive Principle:
Principle #15Dynamics

2Measurement precision

If additional datasets are acquired for valve tracking, then flow analysis accuracy improves, but examination time increases

Engineering Contradiction:
Improvevalve location accuracyVSAvoidexamination time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent combines flow acquisition and anatomical tracking into a single integrated 4D MR Flow dataset. By encoding velocity information in all three spatial directions simultaneously during one acquisition, the system eliminates the need for separate tracking datasets while maintaining both flow quantification and valve localization accuracy.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The 4D MR Flow acquisition serves multiple functions simultaneously: it provides flow velocity measurements, defines valve positions through velocity maxima, and enables dynamic plane adaptation. This multi-functional approach replaces multiple separate acquisitions with a single universal dataset that accomplishes all objectives.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Ease of operation

If manual plane positioning is performed, then flow analysis can be conducted, but operator expertise is required and errors occur regularly

Engineering Contradiction:
Improveplane positioning simplicityVSAvoiddiagnosis reliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system performs automatic valve localization and dynamic plane adaptation without operator intervention. The algorithm independently identifies valve positions by detecting velocity maxima in the 4D dataset and automatically adjusts analysis planes throughout the cardiac cycle, eliminating operator dependency and associated errors.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces manual operator positioning with automated computational algorithms. Instead of relying on human expertise to position planes, the system uses computer-based image processing and velocity field analysis to automatically define and track valve positions, substituting mechanical/manual operations with automated digital processing.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach reduces operator interaction, minimizes alignment issues, and provides accurate, efficient blood flow analysis with minimal user intervention, enabling reliable diagnosis of cardiovascular conditions.

Implementation Method 1

flow sensitive Magnetic Resonance (MR) imaging

Methodology Applied
Scientific EffectMagnetic Resonance: Magnetic Field

Implementation Method 2

two-dimensional (2D) phase-contrast Magnetic Resonance Imaging (MRI) planes

Methodology Applied
Scientific EffectPhase-contrast MRI: Interference

Implementation Method 3

Time resolved three-dimensional phase contrast MRI

Methodology Applied
Scientific EffectMagnetic Resonance: Magnetic Field

Implementation Method 4

three-directional velocity information are acquired for each voxel within a three-dimensional (3D) isotropic volume over time

Methodology Applied
Scientific EffectPhase-contrast imaging: Interference

Data Source

PatentEP4224418B1Flow analysis in 4d mr image data
Publication Date: 2026.03.25 PIE MEDICAL IMAGING
  • EP4224418B1 patent drawingFigure 1
  • EP4224418B1 patent drawingFigure 2
  • EP4224418B1 patent drawingFigure 3

AI summary

A method for performing flow analysis in a target volume of a moving organ having a long axis, such as the heart, from 4D MR Flow volumetric image data set of such organ, wherein such data set comprises structural information and three-directional velocity information of the target volume over time, the devices, program products and methods comprising, under control of one or more computer systems configured with specific executable instructions: a) deriving from the 4D MR Flow volumetric image data set at least one derived image data set related to the long axis of the moving organ, for example, by using a multi planar reconstruction; b) determining at least one feature of interest in the 4D MR Flow volumetric image data set or in said derived image data set. The feature of interest may be determined, for example, by receiving input from a user or by performing automatic detection steps on the 4D MR Flow volumetric image data set; c) tracking the feature of interest within the 4D MR Flow volumetric image data set or in the derived image data set; d) determining the spatial orientation over time of a plane containing the feature of interest in the 4D MR Flow volumetric image data set; e) performing quantitative flow analysis using velocity information on the plane as determined in step d). A corresponding device and computer program are also disclosed.