CT Image Quality Assessment Using ML Feedback Loop
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computed tomography (CT) image quality is inconsistent across users and scans due to varying acquisition parameter configurations, and existing technologies lack effective feedback mechanisms for optimizing these settings, leading to a trial-and-error process that requires years of experience.
Innovation Solution
A method for an image quality assessment system that uses a trained machine learning model to generate an image quality score for selected medical images, displays the score in a graphical user interface, allows user feedback for adjusting the score, and retraining the model to improve image quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual configuration of acquisition parameters is used, then user control over image settings is maintained, but image quality consistency deteriorates due to varying user experience and trial-and-error processes
Solution Approach 1:
The system automatically evaluates image quality and provides feedback without requiring manual user intervention. The AI model self-adjusts acquisition parameters based on image quality assessment, eliminating the need for users to have extensive experience or perform trial-and-error configurations.
Solution Approach 2:
The system implements a closed-loop feedback mechanism where image quality is automatically assessed and the results are used to adjust acquisition parameters. This feedback loop enables continuous optimization of image quality without requiring manual user input or interpretation.
2Manufacturing precision
If extensive user experience is required for optimal parameter configuration, then image quality can be improved through expert knowledge, but the time and training required increases significantly
Solution Approach 1:
The patent replaces the mechanical system of human expertise and manual adjustment with an AI-based automated system. The machine learning model substitutes for years of user experience and trial-and-error processes, providing expert-level image quality optimization without requiring user training or experience.
3Productivity
If automated AI techniques are implemented, then productivity and automation level increase, but the complexity of the system increases
Solution Approach 1:
The patent introduces an AI model as an intermediary between the acquisition parameters and image quality assessment. This intermediary automatically processes the complex relationships between multiple parameters and image quality metrics, simplifying the overall system operation while maintaining high automation levels.
Data Source
AI summary
Methods and systems are provided for automatically generating an image quality score for a computed tomography (CT) image within an image quality assessment system. In one example, a method for an image quality assessment system comprises receiving a selection of a medical image from a user of the image quality assessment system; generating an image quality score for the selected medical image, the image quality score generated using a trained machine learning (ML) model; displaying the selected medical image and the image quality score in a graphical user interface (GUI) on a display device of the image quality assessment system; receiving an adjusted image quality score of the medical image from the user via the GUI; and using the adjusted image quality score to retrain the ML model.