Virtual clinical imaging trial platform
Define image quality requirements for reliable diagnosis
“Survey Monkey meets virtual clinical imaging trials for radiology.”
X-ray optimisation means producing diagnostic quality images at the lowest possible dose. Use LesionSim to quantify the image quality required for a reliable diagnosis on your journey to optimisation.
Conduct clinical imaging trials quickly and rigorously
Load your test images, add lesions, modify the image noise and resolution characteristics, create a scoring schedule and invite your radiologists to join the survey.
LesionSim creates a virtual imaging trial that simulates and scores radiologist detection performance under different conditions. The results feed back into the MyXrayDose web service to identify which imaging procedures may be falling short of the expected performance, so you can find the contributing factors and potential solutions.
About MyXrayDose
Determining imaging requirements through simulation
The purpose of a medical x-ray is to visualise structures and pathologies for diagnosis, yet radiology professionals have not had rigorous methods for deciding whether their clinical images are adequate for a particular diagnostic task.
Our vision lacks specificity when assessing image quality attributes such as noise, and their likely impact on our ability to see the subtle features needed for diagnosis. To address this we developed LesionSim, an application and web service for simulating realistic pathologies on clinical images and running web-based detection accuracy surveys.
The simulated pathologies are typically designed to represent the “edge case”: the smallest, lowest-contrast version of a specific pathology you expect to see.
Combining the quantitative image quality metrics with observers’ responses to the simulations gives you what you need to set image quality benchmarks for consistent detection of a minimum edge-case pathology across a fleet of imaging equipment.
Benefits
- Quantify diagnostic accuracy and minimise diagnosis-related patient errors and harm
- Reduce healthcare costs to the patient and health system from diagnostic errors
- Answer the question: is our image quality adequate for the task?
- Avoid the cost, time, ethical complexity and potential harm of running imaging trials on patients
- Engage radiology staff in managing and setting the quality of the core business
Features
- Arbitrary lesion simulation
- Lesions generated mathematically, hand-crafted or copied from a real image
- Unlimited scoring questions
- Answer with scoring sliders, yes/no, picklists or measurement tools
- Study designer interface
- Lock studies when the design is complete
- Variable noise simulation
- Variable resolution simulation
- Locked or adjustable window and level settings
- Image anonymisation
- Predefined pseudorandom image order to minimise observer bias
- Hidden measurement values to minimise observer measurement bias
Collaborate across your organisation
LesionSim runs from a central server, so you can set up a single virtual imaging trial and invite participants from multiple locations within your organisation.
Works with MyXrayDose
Close the loop on image quality
LesionSim defines the image quality requirement. MyXrayDose monitors it across every system in your fleet and reports where protocols fall short, so your team can optimise them and measure again.
Explore MyXrayDoseRun your first virtual imaging trial
Talk to us about setting up LesionSim for your radiology team.