Dynamic MRI Reconstruction Using Adaptive Image Quality Metrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Dynamic MRI reconstruction faces challenges in achieving optimal temporal resolution that balances image quality and temporal information, as existing methods often require empirical testing and may not generalize well across different anatomical areas or applications, and conventional compressed sensing techniques struggle to determine suitable undersampling factors and reconstruction algorithms.
Innovation Solution
An automated method for dynamic MRI reconstruction that uses image quality metrics to iteratively adjust temporal resolution and reconstruction parameters, allowing for flexible selection of temporal resolution and optimal image quality, enabling reconstruction without a fixed temporal resolution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If compressed sensing is used to accelerate MRI scans by undersampling data, then imaging time is reduced and temporal resolution is improved, but spatial resolution deteriorates and image quality becomes noisy or grainy
Solution Approach 1:
The patent employs iterative feedback mechanisms where reconstructed images are evaluated against quality metrics, and the reconstruction parameters are adjusted in subsequent iterations to improve image quality while maintaining acceleration benefits
Solution Approach 2:
The system dynamically adjusts multiple parameters including undersampling factor, regularization strength, and iteration count based on the specific imaging scenario and desired quality levels, allowing optimization for different anatomical regions and clinical applications
2Manufacturing precision
If empirical testing is performed to determine optimal sampling strategy and reconstruction parameters, then image quality may be improved for specific cases, but the process becomes time-consuming and does not generalize well to different anatomical areas or applications
Solution Approach 1:
The reconstruction algorithm automatically selects optimal parameters and adjusts reconstruction settings based on intrinsic properties of the acquired data, eliminating the need for manual empirical testing and making the system adaptable to different anatomical regions and applications without additional complexity
Solution Approach 2:
The patent develops a universal reconstruction framework that can handle various imaging scenarios (different anatomical regions, contrast agents, temporal resolutions) through a single adaptive algorithm, rather than requiring separate optimized parameters for each case
3Manufacturing precision
If a fixed temporal resolution is chosen to maintain image quality, then diagnostic accuracy is improved, but rapid dynamics may be overlooked and the temporal resolution cannot be optimized for different applications
Solution Approach 1:
The system transitions from static fixed temporal resolution to dynamic adaptive temporal resolution, where the temporal sampling rate is automatically adjusted based on the detected speed of physiological processes in the specific imaging scenario, allowing optimization for both slow and rapid dynamics
Data Source
AI summary
Systems and methods are provided for performing automated reconstruction of a dynamic MRI dataset that is acquired without a fixed temporal resolution. On one or more image quality metrics (IQMs) are obtained by processing a subset of the acquired dataset. In one example implementation, at each stage of an iterative process, one or more IQMs of the image subset is computed, and the parameters controlling the reconstruction and/or the strategy for data combination are adjusted to provide an improved or optimal image reconstruction. Once the IQM of the image subset satisfies acceptance criteria based on an estimate of the overall temporal fidelity of the reconstruction, the full reconstruction can be performed, and the estimate of the overall temporal fidelity can be reported based on the IQM at the final iteration.