Dynamic Mitral Valve Annulus Analysis from Volumetric Image Sequences
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current pre-operative analysis methods for mitral valve replacement and repair, such as transcatheter mitral valve replacement (TMVR), rely on static 3D segmentation of the mitral annulus at limited phases of the cardiac cycle, failing to capture dynamic changes essential for accurate device selection and therapy planning, leading to potential errors in valve function preservation.
Innovation Solution
A method and system for dynamic analysis of the mitral valve annulus using a sequence of volumetric image frames, involving object identification, contour segmentation, propagation, and dynamic parameter calculation across multiple heart phases, enabling accurate geometric and deformation analysis of the mitral valve annulus.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If static 3D segmentation of the mitral annulus is performed at limited phases of the cardiac cycle, then the analysis process is simpler and faster, but dynamic changes of the mitral valve are not captured accurately
Solution Approach 1:
The patent applies dynamics by transitioning from static segmentation at limited phases to dynamic segmentation across multiple phases of the cardiac cycle. The system performs automated segmentation at multiple time points (e.g., end-diastole, end-systole, and intermediate phases) to capture the temporal evolution of mitral annulus geometry, enabling accurate measurement of dynamic changes in annular dimensions, shape, and motion patterns.
Solution Approach 2:
The patent implements preliminary action through pre-processing steps that prepare the volumetric image data before segmentation. This includes image registration to align multiple phases, noise filtering to enhance structural visibility, and automated detection of key anatomical landmarks. These preliminary actions reduce the complexity of subsequent segmentation operations and improve overall measurement accuracy.
2Measurement precision
If manual 3D segmentation is performed by clinicians, then anatomical accuracy can be achieved, but the process is extremely time-consuming and prone to errors
Solution Approach 1:
The patent implements self-service through automated segmentation algorithms that perform the segmentation task without requiring manual clinician intervention. The system automatically identifies mitral annulus structures, segments the annulus across multiple cardiac phases, and computes geometric parameters. This self-service approach maintains anatomical accuracy through validated algorithms while dramatically reducing processing time and eliminating human error associated with manual tracing.
Solution Approach 2:
The patent replaces the mechanical manual tracing process with computational algorithms. Instead of clinicians manually placing points and drawing contours, the system uses image processing techniques including thresholding, edge detection, and region-growing algorithms to automatically segment the mitral annulus. This substitution maintains measurement accuracy while improving productivity by processing multiple phases rapidly.
3Loss of information
If multiple heart phases are analyzed to capture dynamic changes, then complete overview of mitral valve is obtained, but the segmentation process becomes more time-consuming and error-prone
Solution Approach 1:
The patent applies segmentation by dividing the cardiac cycle into discrete phases (e.g., early diastole, late diastole, early systole, late systole) and performing automated segmentation at each phase independently. This allows complete capture of dynamic changes across the cardiac cycle while managing complexity through systematic phase-by-phase processing. The segmented data from multiple phases are then integrated to provide comprehensive information about mitral valve dynamics.
Solution Approach 2:
The patent implements continuity of useful action by processing multiple cardiac phases in a continuous automated workflow. Once the segmentation parameters are established for one phase, the system automatically applies and adapts these parameters across subsequent phases without requiring re-initialization or manual intervention. This continuous processing maintains information completeness while minimizing total analysis time.
Data Source
AI summary
Devices, systems, computer program products and computer implemented methods are provided for dynamically assessing a moving object from a sequence of consecutive volumetric image frames of such object, which images are timely separated by a certain time interval, by:identifying in at least one image of the sequence the object of interest;segmenting the object to identify object contour;propagating the object contour as identified to other images of the sequence; andperforming dynamic analysis of the object based on the object contour as propagated.