Medical Image Reconstruction QoS Adjustment Under Resource Load
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In clinical radiology, reconstruction parameters for medical images are statically defined, neglecting factors that affect the quality of the diagnostic reporting workflow, such as turnaround time, which varies across different scenarios and resource availability, leading to inefficient image reconstruction and delivery.
Innovation Solution
A system and method that dynamically adjust image reconstruction parameters based on current resource load and availability to meet predefined quality of service (QoS) specifications, including negotiable and non-negotiable parameters, to optimize turnaround time and resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If reconstruction parameters are defined statically (e.g., in exam cards), then the image quality and reconstruction process are simplified and standardized, but the system cannot adapt to varying resource availability and workflow requirements, leading to inefficient image delivery
Solution Approach 1:
The patent transforms static reconstruction parameters into dynamic parameters that can be automatically adjusted based on current system load and resource availability. The parameter adjustment mechanism monitors resource status and modifies parameters such as matrix size, slice thickness, and reconstruction filter in real-time, enabling the system to adapt to varying workflow requirements without manual intervention.
Solution Approach 2:
The system changes reconstruction parameters dynamically based on monitored resource availability and workflow priorities. By adjusting parameters like image matrix size, slice thickness, and reconstruction algorithms according to current system capacity, the system optimizes both image quality and delivery speed without requiring complex manual reconfiguration.
2Loss of time
If high-quality reconstruction parameters are used consistently, then image quality is maintained at optimal levels, but the system cannot meet varying turnaround time requirements in different clinical scenarios
Solution Approach 1:
The patent implements dynamic parameter adjustment where reconstruction quality parameters are automatically modified based on current system load and clinical priority. During high-demand periods or emergency situations, the system reduces processing time by adjusting parameters while maintaining acceptable quality levels, whereas during low-load periods, optimal quality parameters are applied.
Solution Approach 2:
The system dynamically changes reconstruction parameters such as matrix size, slice thickness, and reconstruction filter strength based on workflow requirements and resource availability. This allows the system to balance image quality with turnaround time by selecting appropriate parameter sets for different clinical scenarios without manual intervention.
3Productivity
If reconstruction parameters are optimized for speed, then turnaround time is reduced, but image quality may deteriorate, affecting diagnostic accuracy
Solution Approach 1:
The patent employs dynamic parameter optimization where the system automatically adjusts reconstruction parameters based on current resource availability and workflow priorities. During periods of high resource availability, the system uses quality-optimized parameters; during constrained periods, it switches to speed-optimized parameters, maintaining both productivity and acceptable image quality through continuous adaptation.
Solution Approach 2:
The system dynamically modifies reconstruction parameters to balance speed and quality based on monitored resource status. By changing parameters such as reconstruction algorithm complexity, matrix size, and processing resolution according to current system capacity, the system achieves high productivity during resource-rich periods while maintaining diagnostic quality when resources are available.
4Productivity
If the system continuously monitors and adjusts parameters based on load, then resource utilization efficiency is improved, but the system complexity and computational overhead increase
Solution Approach 1:
The patent implements a self-service mechanism where the system automatically monitors its own resource status and adjusts parameters without external intervention. The load monitoring component tracks system capacity and the parameter adjustment mechanism automatically selects appropriate parameters, eliminating the need for manual configuration or complex external control systems while maintaining high resource utilization efficiency.
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
System (FS) for facilitating delivery of a medical data-based service (S), deliverable by cooperable resources (Rj). The system comprises an input interface (IN) for receiving a request for such a service at a pre-defined quality of service, QoS, the said QoS specifiable by a specification (Q) that specifies parameters. A load establisher (LE) establishes a current load of the resources (Rj). A QoS adjuster (QA) adjusts, based on the established load, one or more parameters, so that the QoS as per the other parameter is met.