Automated Arterial Input Function Estimation in DCE-MRI
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining arterial input function (AIF) in dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) are manual and subjective, leading to reproducibility issues and instability in blood flow maps, particularly in cerebral blood flow (CBF) measurements.
Innovation Solution
An automated method using a fast-AP clustering algorithm to process concentration time curves, involving mask design, intravascular contrast agent concentration calculation, area filtering, peak value determination, dissimilarity calculation, and clustering to accurately estimate AIF without user interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual AIF determination procedures are used, then operator flexibility is maintained, but reproducibility and measurement precision deteriorate due to subjective judgments
Solution Approach 1:
The system performs automatic AIF determination through self-service mechanisms including automated curve selection, clustering analysis, and quality control checks. The algorithm independently identifies arterial input function curves from concentration-time curves without requiring operator intervention, thereby improving reproducibility while maintaining accuracy through objective mathematical criteria
Solution Approach 2:
The patent replaces manual operator judgment with an automated computational system that uses clustering algorithms and mathematical optimization to determine AIF. This substitution of mechanical/manual processes with automated computational methods eliminates subjective variability while preserving the essential function of AIF determination
2Extent of automation
If K-means cluster analysis is used for automatic AIF selection, then automation is achieved, but clustering stability and reliability worsen due to sensitivity to initialization
Solution Approach 1:
The patent modifies the clustering approach by changing the initialization parameters and using multiple random initializations to select the optimal clustering result. This parameter change strategy addresses the sensitivity to initialization by systematically exploring different starting conditions and selecting the most stable solution, thereby improving reliability while maintaining automation
Solution Approach 2:
The system incorporates feedback mechanisms through iterative clustering where the results of one clustering attempt inform subsequent attempts. By evaluating clustering stability metrics and using feedback from previous iterations to adjust initialization parameters, the system achieves more reliable and stable clustering results while remaining fully automated
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The method provides a stable and reproducible estimation of AIF, reducing the impact of operator variability and improving the accuracy of blood flow measurements in DCE-MRI, applicable to various tissues and organs.
Implementation Method 1
calculating a concentration of intravascular contrast agent Cp(t) by ΔR2* represents transverse relaxation at time t
Data Source
AI summary
Disclosed are methods, systems and apparatuses for detection of arterial input function (AIF) in MRI, specially DCE MR images, comprising automatic selection of AIF based on affinity propagation (AP) clustering method.