Combined Morphological and Perivascular Marker Assessment in Atherosclerosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for diagnosing atherosclerosis, particularly in aging populations, are limited and often result in suboptimal treatment decisions due to insufficient analysis of the vessel wall, leading to misclassification of risk levels and inability to assess drug response effectively.
Innovation Solution
A system utilizing a processor and non-transient storage medium with a hierarchical analytics framework and machine learned algorithms to segment medical imaging data, delineate perivascular adipose tissue, and quantify biological properties, including calcified regions and lipid-rich necrotic core thickness, to improve diagnostic accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current imaging methods are used to assess atherosclerosis, then luminal stenosis can be measured, but the vessel wall composition and perivascular tissue cannot be accurately distinguished
Solution Approach 1:
The patent applies segmentation by dividing the vascular structure into distinct components: lumen, vessel wall, and perivascular tissue. The system segments medical imaging data to delineate the outer wall boundary and identify perivascular adipose tissue, enabling precise measurement of each component's properties without requiring overly complex imaging hardware.
Solution Approach 2:
The patent introduces machine learned algorithms as an intermediary between the imaging data and clinical interpretation. These algorithms process the imaging data to extract meaningful features about vessel wall composition and perivascular tissue characteristics, bridging the gap between raw imaging data and diagnostic information without requiring more complex imaging devices.
2Measurement precision
If high-resolution imaging techniques are used to improve diagnostic accuracy, then more detailed vessel wall information can be obtained, but data complexity increases making interpretation difficult
Solution Approach 1:
The patent extracts specific diagnostic features from the complex high-resolution imaging data using machine learned algorithms. The system identifies and extracts key characteristics such as cap thickness, lipid-rich necrotic core presence, and perivascular adipose tissue properties, separating the essential diagnostic information from the overwhelming raw data.
Solution Approach 2:
The patent replaces manual radiologist interpretation with machine learned algorithms that automatically analyze the imaging data. This substitution of mechanical human analysis with computational algorithms reduces the difficulty of interpreting complex high-resolution imaging data while maintaining or improving measurement precision.
3Ease of operation
If traditional luminal stenosis assessment is used, then simple measurements can be obtained, but diagnostic accuracy for atherosclerosis risk is insufficient
Solution Approach 1:
The patent merges the simple luminal stenosis measurement with additional vessel wall and perivascular tissue analysis. The system combines multiple measurement dimensions (lumen area, wall thickness, tissue composition) into a unified assessment framework, maintaining operational simplicity while significantly improving diagnostic accuracy for atherosclerosis risk stratification.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system including a hierarchical analytics framework that can utilize a first set of machine learned algorithms to identify and quantify a set of biological properties utilizing medical imaging data is provided. System can segment the medical imaging data based on the quantified biological properties to delineate existence of perivascular adipose tissue. The system can also segment the medical imaging data based on the quantified biological properties to determine a lumen boundary and/or determine a cap thickness based on a minimum distance between the lumen boundary and LRNC regions.