AI Targeting System for CT Scan Parameter Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current medical imaging technologies face challenges in accurately measuring small lung nodules due to degraded bias and precision performance, increased complexity in CT scanner settings, and suboptimal image acquisition parameters, which hinder effective detection and characterization of abnormalities.
Innovation Solution
A system and method utilizing an AI targeting and image optimization system that analyzes medical images to determine targeted scan parameters for improved visualization and quantitative measurement of abnormalities, incorporating model-based and deep learning AI methods, simulation engines, and clinical guidance to optimize image acquisition and reconstruction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If CT scanners use highest resolution acquisition parameters (thin slices with small spacing), then image quality and measurement precision improve, but the number of CT images increases significantly, extending radiologist review time
Solution Approach 1:
The patent segments the image processing task by introducing an AI system that automatically detects abnormalities and generates measurement reports, separating the measurement function from radiologist review. This allows high-resolution imaging to be used without proportionally increasing radiologist time investment, as the AI handles the time-consuming measurement and analysis tasks.
Solution Approach 2:
The patent introduces an AI-based measurement and analysis system as an intermediary between image acquisition and radiologist review. This intermediary automatically processes high-resolution images, performs measurements, and generates preliminary reports, reducing the time radiologists need to spend reviewing individual images while maintaining measurement precision.
2Adaptability or versatility
If CT scanners use multiple acquisition parameters and complex capabilities, then imaging versatility improves, but predicting impact on image quality and measurement performance becomes difficult
Solution Approach 1:
The patent implements feedback mechanisms where the AI system analyzes the actual image quality and measurement performance resulting from different acquisition parameters. This feedback loop allows the system to learn which parameter combinations produce optimal results for specific clinical tasks, enabling predictable control over image quality and measurement accuracy despite the complexity of multiple acquisition parameters.
Solution Approach 2:
The patent systematically varies acquisition parameters and uses AI to evaluate their impact on measurement performance. By changing parameters in a controlled manner and measuring the effects, the system establishes relationships between scanner settings and outcomes, making the impact of complex parameters predictable through data-driven insights rather than theoretical prediction alone.
3Reliability
If CT images are acquired for radiologist subjective viewing, then diagnostic capability improves, but quantitative measurement quality degrades
Solution Approach 1:
The patent makes the imaging system multi-functional by acquiring images that simultaneously serve both diagnostic viewing and quantitative measurement purposes. The AI system analyzes the acquired images to determine whether they meet the quality criteria for both radiologist review and automated measurement, eliminating the need for separate acquisition protocols for each purpose.
Solution Approach 2:
The patent performs preliminary analysis of acquired images using AI to assess their suitability for quantitative measurement before radiologist review. This preliminary action identifies images that may require re-acquisition with optimized parameters, ensuring that quantitative measurement quality is addressed early in the workflow rather than discovered later when it would be too late to correct.
Data Source
AI summary
The present invention discloses a system and method for obtaining quality image data and measurements from a medical imaging device. The system comprises a medical scanner configured to obtain image of a patient. The system further comprises an artificial intelligence (AI) targeting and image optimization system configured to receive and analyze the image with any combination of model-based methods and AI methods to find one or more target areas of abnormalities. The AI targeting and image optimization system is configured to analyze one or more target areas of abnormality of the image to determine a set of targeted scan parameters for the medical scanner for visualizing and automatically quantitatively measuring the abnormality. The AI targeting and image optimization system is configured to provide information including a target image acquisition parameters to a user to perform an additional targeted image acquisition or image reconstruction.