Patient Worklist Sorting via CAD Metrics in Radiology
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Radiologists in high-throughput environments face challenges with complex user interfaces and inadequate control over patient worklists in radiology review workstations, which can impact review rate and diagnosis quality.
Innovation Solution
A system and method for managing patient worklists in radiology environments, utilizing CAD-computed metrics to sort and prioritize medical imaging cases, with a graphical user interface for easy customization of sorting criteria, including CAD markers, suspiciousness, and anatomical complexity metrics, providing radiologists with greater insight and control over their workflow.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If additional image information and decision support tools are provided to the radiologist, then detection and diagnosis quality is improved, but user interface complexity and radiologist workload increase
Solution Approach 1:
The patent segments the worklist management function from the overall imaging system, creating a dedicated worklist manager component that handles sorting and prioritization independently. This segmentation allows the complex decision support information to be organized through specialized algorithms (CAD-computed metrics) without overwhelming the radiologist with raw data, thus improving detection quality while managing interface complexity.
Solution Approach 2:
The patent introduces an intermediary layer (the worklist manager with CAD-computed metrics) between the imaging system and the radiologist. This intermediary processes and prioritizes image information before presentation, filtering and organizing data according to clinically relevant metrics. This mediator reduces the cognitive load on the radiologist while maintaining access to comprehensive decision support information.
2Reliability
If more technology and decision support information are provided, then diagnostic capability is enhanced, but radiologist review rate decreases
Solution Approach 1:
The patent applies preliminary action by pre-computing CAD metrics and pre-sorting cases in the worklist before the radiologist begins review. Cases are prioritized in advance based on CAD-computed metrics such as suspiciousness scores and anatomical complexity, so the radiologist receives cases in optimal review order. This preliminary organization enhances diagnostic quality while maintaining review rate by eliminating the need for radiologists to manually prioritize cases during review.
Solution Approach 2:
The patent changes the parameter of case presentation from unsorted or简单地 chronological order to sorting based on multiple CAD-computed parameters simultaneously (suspiciousness, complexity, throughput). This multi-parameter sorting approach optimizes the balance between diagnostic quality and review efficiency by dynamically adjusting case priority based on computed metrics rather than static ordering.
3Ease of operation
If patient worklists are customized with multiple sorting criteria, then radiologist control and insight are improved, but system complexity and training requirements increase
Solution Approach 1:
The patent implements dynamic worklist sorting where the sorting criteria and priorities can be adjusted in real-time based on radiologist preferences and clinical context. The system allows radiologists to dynamically modify sorting parameters (e.g., emphasizing suspiciousness vs. throughput) without requiring system reconfiguration. This dynamic approach enhances radiologist control while managing system complexity through adaptive algorithms that respond to user input rather than requiring complex preset configurations.
Solution Approach 2:
The patent incorporates feedback mechanisms where the worklist manager continuously monitors radiologist interactions and adjusts sorting based on observed preferences and clinical outcomes. The system provides feedback to radiologists about how sorting criteria affect their workflow, enabling them to refine their preferences. This feedback loop improves ease of operation by adapting to individual radiologist needs while keeping system complexity manageable through iterative learning rather than complex predefined rules.
Data Source
AI summary
Managing a patient worklist in a radiology environment is described, the patient worklist identifying a plurality of medical imaging cases to be reviewed at a radiology review workstation. For each case, a set of CAD-computed metrics is received, the CAD-computed metrics being derived from an operation of a CAD processing algorithm on that case. According to a preferred embodiment, the cases in the patient worklist are sorted according to at least one of the CAD-computed metrics. The reviewing radiologist is provided with greater insight into, and control over, patient workflow at the radiology review workstation. Also described is a graphical user interface for easy user customization of the case sorting criteria. Examples of case sorting criteria include a number of CAD markers per case metric, a maximum suspiciousness metric, and an anatomical complexity metric.