Automatic Inversion Time Selection for FIDDLE MRI
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge in Late Gadolinium Enhancement (LGE) MRI is to accurately delineate diseased from normal tissue, particularly when diseased tissue adjacent to the cardiac cavity or vasculature is hidden due to poor contrast between hyperenhanced tissue and bright blood-pool, and determining the optimal inversion time (TI) for Flow-Independent Dark-blood Delayed Enhancement (FIDDLE) techniques is difficult.
Innovation Solution
A method and system for automatically calculating the optimal inversion time (TI) for FIDDLE by acquiring MR data, segmenting phase sensitive FIDDLE images into myocardial wall and blood pool compartments, calculating signals for normal myocardium and blood, grouping these signals with their respective TI values into recovery curves, determining the crossing TI from the intersection of these curves, and calculating the optimal TI from the crossing TI.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If FIDDLE technique is used to suppress blood-pool signal and enhance tissue contrast, then the visibility of diseased tissue is improved, but the optimal inversion time (TI) becomes difficult to determine
Solution Approach 1:
The patent performs preliminary actions by acquiring multiple FIDDLE images at different TI values before determining the optimal TI. This preliminary data collection enables subsequent automated analysis to identify the optimal TI without requiring manual trial-and-error acquisition, thus resolving the difficulty in optimal TI determination while maintaining high tissue contrast accuracy
Solution Approach 2:
The patent implements feedback mechanisms by automatically analyzing the signal intensity patterns across multiple TI values and using this information to determine the optimal TI. The system monitors signal recovery curves of both normal myocardium and blood pool, comparing them to identify the TI that maximizes tissue contrast while minimizing blood signal, thereby autonomously resolving the optimal TI selection problem
2Measurement precision
If multiple FIDDLE images with different TI values are acquired for optimal TI determination, then the accuracy of tissue contrast is improved, but the acquisition time and data processing complexity increase
Solution Approach 1:
The patent segments the analysis process into distinct functional components: (1) automatic segmentation of myocardial wall and blood pool compartments using reference images, (2) extraction of signal intensity values from segmented regions, (3) construction of signal recovery curves, and (4) automated optimal TI determination. This segmentation enables efficient processing of multiple TI images by handling each component independently, reducing overall processing time while maintaining high accuracy
Solution Approach 2:
The patent uses reference images (non-inversion images) as copies or templates to guide the segmentation process. These reference images serve as templates for automatically identifying myocardial and blood pool regions across all TI images, eliminating the need for manual segmentation of each image. This copying approach significantly reduces processing time while ensuring consistent and accurate region identification
3Ease of operation
If automated TI determination is implemented, then the ease of operation is improved, but the device complexity and processing requirements increase
Solution Approach 1:
The patent implements self-service by enabling the system to automatically determine optimal TI values without requiring operator intervention. The automated algorithm processes multiple FIDDLE images, segments anatomical structures, extracts signal intensities, and identifies optimal TI parameters independently. This self-service capability eliminates manual TI selection complexity while the structured processing approach keeps system complexity manageable through modular design
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
This approach enables accurate and automatic determination of the optimal TI for FIDDLE, improving tissue contrast and enhancing the visibility of diseased tissue, thereby facilitating more reliable diagnostic imaging.
Implementation Method 1
Late gadolinium enhancement (LGE) is a T1-weighted magnetic resonance imaging (MRI) acquisition technique
Implementation Method 2
T1-weighting is achieved by an inversion recovery (IR) pulse and a data acquisition (DA) timed to this pulse so that the recovery curve of normal, i.e., viable, healthy myocardium passes through the zero-magnetization point
Implementation Method 3
LGE MRI relies on the administration of a T1-shortening contrast agent, typically a chelate of gadolinium, which selectively accumulates in the dead myocardial cells and areas of myocardial scar
Data Source
AI summary
Systems and methods for automatically selecting an optimal inversion time for Flow-Independent Dark-blood Delayed Enhancement (FIDDLE). Deep learning is used to train a neural network to perform myocardium segmentation on REF images associated with FIDDLE images. A separate neural network is trained to find the intersection of the recovery curves of normal myocardium and blood pool. The intersection is used to determine the optimal inversion time.