Membranous Septum Segmentation Using LVOT Wall Thickness Mapping

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The membranous septum is difficult to segment in 3D image data sets due to its small size and non-planar surface, making manual annotations tedious and costly, and existing methods lack efficient automated segmentation techniques.

Innovation Solution

A device and method that segments the left ventricular outflow tract (LVOT) to determine wall thickness information, maps this information onto the LVOT surface, and uses it to automate the segmentation of the membranous septum, employing techniques like thresholding, independent component analysis, and k-nearest neighbor clustering, with optional model-based segmentation and machine learning for improved accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual annotation methods are used to segment the membranous septum, then segmentation accuracy can be achieved, but the process becomes tedious and costly

Engineering Contradiction:
Improvesegmentation accuracyVSAvoidannotation time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs automated segmentation of the membranous septum by processing 3D image data independently without requiring manual annotation. The circuitry segments the LVOT, determines wall thickness information, and identifies the membranous septum automatically, making the system self-sufficient and eliminating the need for tedious manual work.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system uses wall thickness information as a key parameter to identify and segment the membranous septum. By mapping wall thickness information onto the LVOT surface and using it as a segmentation criterion, the system transforms the segmentation problem into a parameter-based identification task that can be solved automatically.

Inventive Principle:
Principle #35Parameter changes

2Ease of operation

If the membranous septum is segmented in standard planar slice views, then the segmentation process is simplified, but the small and unobtrusive structure becomes difficult to identify

Engineering Contradiction:
Improvesegmentation simplicityVSAvoidstructure visibility
Core Design Contradiction:
Ease of operationVSDifficulty of detecting and measuring

Solution Approach 1:

The system transitions from standard planar slice views to a 3D surface representation of the LVOT. By mapping wall thickness information onto the 3D surface of the segmented LVOT, the system provides a more comprehensive view that makes the small and unobtrusive membranous septum structure visible and identifiable in its spatial context.

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

3Measurement precision

If extensive manual annotations are collected for neural network training, then segmentation accuracy improves, but the cost and complexity increase significantly

Engineering Contradiction:
Improvesegmentation accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system replaces the need for extensive manual annotations and neural network training with a deterministic algorithmic approach. Instead of using machine learning models that require large datasets, the circuitry uses geometric and anatomical relationships (wall thickness information) to automatically segment the membranous septum, substituting computational geometry for statistical learning.

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

Data Source

PatentEP4612647B1Device, method and computer program for segmenting the membranous septum
Publication Date: 2026.03.04 KONINKLIJKE PHILIPS NV
  • EP4612647B1 patent drawingFigure 1
  • EP4612647B1 patent drawingFigure 2~3
  • EP4612647B1 patent drawingFigure 4

AI summary

The present invention relates to a device and method for segmenting the membranous septum. The method comprises segmenting the left ventricular outflow tract, LVOT, of the heart in a 3D image data set; determining wall thickness information indicative of the wall thickness of the septum at different locations of a part of the segmented LVOT that is oriented towards the right heart chambers and right atrium; mapping the determined wall thickness information onto the surface of said part of the segmented LVOT; and segmenting the membranous septum in the 3D image data set based on the mapped wall thickness information.