Automated Medical Image Segmentation for Non-Planar Cardiac Valves
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual segmentation of non-planar surfaces in medical images, such as the cardiac valve, is cumbersome, prone to errors, and inconsistent due to reliance on user input, especially in three- or four-dimensional data sets, leading to potential loss of spatial context and incorrect contour detection.
Innovation Solution
An automated method that detects the surface boundary of non-planar surfaces using landmarks and distance information to generate a corrected model surface, which is then divided into subsurfaces for precise visualization, utilizing techniques like surface-rendering and volume-rendering to align and correct the model surface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual segmentation is performed by users, then the segmentation can be performed on non-planar surfaces, but the process is cumbersome and time-consuming
Solution Approach 1:
The system performs automatic segmentation using algorithms that detect surface boundaries and generate model surfaces independently, eliminating the need for manual user input and making the system self-sufficient in the segmentation process
Solution Approach 2:
The patent replaces manual mechanical contouring operations with automated image processing algorithms and computational geometry methods, substituting human manual work with computational processes
2Measurement precision
If manual segmentation is performed, then the user can detect contours, but errors may occur in contour detection
Solution Approach 1:
The system uses feedback mechanisms where the automatically detected model surface is continuously refined by comparing it with the original image data and adjusting the segmentation until optimal accuracy is achieved, ensuring consistent and error-free results
3Ease of operation
If processing is done slice by slice on two-dimensional images, then the segmentation can be performed, but spatial context is lost and contouring becomes inconsistent
Solution Approach 1:
The patent transitions from processing two-dimensional slices to three-dimensional volume-based processing, allowing the system to maintain spatial context and generate consistent contours by considering the entire volumetric data set simultaneously
4Productivity
If manual segmentation is performed, then the process can be completed, but results vary depending on the user
Solution Approach 1:
The automated segmentation system provides a universal algorithm that produces consistent results regardless of who operates it, making the segmentation process independent of individual user skills or interpretations and ensuring standardized outcomes
Data Source
AI summary
The present invention relates to a method and device for automatical segmentation of medical images of a non-planar surface of an object, in particular of a heart valve, including detecting a surface boundary which delimits the non-planar surface of the object, creating a model surface, which is spanned between the surface boundary, correcting the model surface by means of distance information containing information about the distance between the model surface and the non-planar surface of the object, until a corrected model surface is generated, and depicting the corrected model surface, where the correction of the model surface is preferably carried out by means of three- or four-dimensional image data sets, by orienting the three-dimensional volume-rendering of the object essentially perpendicular to the model surface, so that the information about the distance between the model surface and the non-planar surface of the object can be evaluated, until the corrected model surface has been produced.