Annular Structure Representation in Medical Imaging

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Manual detection of annular structures in medical imaging is time-consuming and often inaccurate, necessitating a more efficient and accurate method for reconstructing these structures from three-dimensional image data.

Innovation Solution

A method involving the detection of at least two landmark points on an annular structure, determination of a plane oriented perpendicular to the line connecting these points, and identification of a third landmark point within this plane, using machine learning algorithms such as deep reinforcement learning and 2D/3D neural networks to generate a representation of the annular structure.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual detection methods are used to identify annular structures, then diagnostic accuracy can be maintained through expert analysis, but the process becomes time-consuming and inefficient

Engineering Contradiction:
Improvedetection accuracyVSAvoiddetection time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical detection methods with an automated computer-based system that uses machine learning algorithms and geometric modeling to detect annular structures. The system automatically identifies landmark points, determines planes, and generates representations without requiring manual expert analysis, thereby maintaining accuracy while dramatically reducing detection time.

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

Solution Approach 2:

The system enables self-service detection by using automated algorithms to identify annular structures without human intervention. The computer-based system performs landmark detection, plane determination, and representation generation autonomously, allowing the detection process to serve itself without requiring time-consuming manual expert analysis.

Inventive Principle:
Principle #25Self-service

2Measurement precision

If complex machine learning algorithms are applied to detect landmark points, then detection accuracy improves, but computational resources and processing time increase

Engineering Contradiction:
Improvelandmark detection accuracyVSAvoidcomputational resource consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent segments the detection process into distinct stages: landmark point detection, plane determination, and representation generation. By dividing the complex task into manageable segments, the system can apply appropriate algorithms to each stage, optimizing computational resource usage while maintaining high detection accuracy at each step.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by first detecting landmark points and determining planes before generating the final annular structure representation. This preliminary detection and planning phase allows the system to prepare data structures and geometric models in advance, reducing the computational burden during the final representation generation stage.

Inventive Principle:
Principle #10Preliminary action

3Loss of information

If three-dimensional image data is processed to generate annular structure representations, then diagnostic information quality improves, but data processing complexity and resource requirements increase

Engineering Contradiction:
Improvediagnostic information qualityVSAvoiddata processing complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent extracts essential geometric features from complex three-dimensional image data to create simplified annular structure representations. By taking out only the critical landmark points and geometric relationships needed for diagnosis, the system maintains high diagnostic information quality while reducing data processing complexity and resource requirements.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system transforms three-dimensional image data into two-dimensional plane representations and geometric models. By changing the dimensionality of the data representation, the system preserves essential diagnostic information while simplifying the data structure, making it easier to process and analyze without requiring excessive computational resources.

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

Data Source

PatentEP3869458B1Annular structure representation
Publication Date: 2024.12.25 SIEMENS HEALTHINEERS AG
  • EP3869458B1 patent drawingFigure 1
  • EP3869458B1 patent drawingFigure 2~3
  • EP3869458B1 patent drawingFigure 4~5

AI summary

A method, apparatus and computer readable storage medium for constructing a representation of an annular structure associated with an anatomical object. The method comprising receiving three-dimensional image data of the anatomical object; and detecting at least a first landmark point and a second landmark point on the annular structure. A plane positioned between the first landmark point and the second landmark point, and oriented in accordance with a predefined angular relationship to a line connecting the first landmark point and the second landmark point is determined. A third landmark point on the annular structure which lies in the plane is also detected and the representation of the annular structure is generated using at least the first landmark point, the second landmark point, and the third landmark point. The representation is then outputted.