Angiogram Scoring Using Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Angiography exams face challenges in reducing contrast agent and radiation doses while maintaining image quality, as existing methods struggle to control these doses effectively, leading to potential health risks and reduced image quality.
Innovation Solution
A computer-implemented method using a trained machine-learning algorithm to process angiograms, determining the diagnostic value of frames and adjusting imaging parameters to optimize the acquisition of frames with high diagnostic value, thereby reducing contrast agent and radiation doses and computational costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If the contrast agent dose and/or radiation dose is reduced to minimize health risks, then the safety is improved, but the image quality deteriorates
Solution Approach 1:
The system performs preliminary quality assessment of angiograms using automated criteria during the exam, allowing early identification of diagnostically sufficient images and preventing unnecessary continuation of high-dose acquisition
Solution Approach 2:
The system provides real-time feedback on angiogram quality metrics and diagnostic sufficiency to the operator, enabling dynamic adjustment of acquisition parameters to maintain image quality while minimizing dose
2Manufacturing precision
If the contrast agent dose and/or radiation dose is increased to maintain image quality, then the image quality is improved, but the health risks worsen
Solution Approach 1:
The system replaces manual operator judgment with automated machine-learning-based quality assessment algorithms, providing objective, consistent evaluation of angiogram diagnostic value to optimize dose-quality balance
3Reliability
If multiple angiograms are acquired from multiple angulations to ensure diagnostic coverage, then the diagnostic completeness is improved, but the exam time and computational costs worsen
Solution Approach 1:
The system assesses diagnostic sufficiency of individual angiograms and allows termination of acquisition once sufficient diagnostic information is obtained, avoiding unnecessary acquisition of excessive numbers of angiograms
Solution Approach 2:
The system performs preliminary automated quality assessment to identify angiograms that meet diagnostic criteria, enabling early termination of acquisition protocols and reducing unnecessary processing time
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach allows for precise tailoring of angiogram acquisition to achieve high-quality images with reduced doses, minimizing health risks and computational burdens, and optimizing exam efficiency.
Implementation Method 1
determining, based on the angiogram, a score using a trained machine-learning, ML, algorithm, wherein the score quantifies the diagnostic value of the angiogram
Data Source
AI summary
Techniques for processing one or more frames of an angiogram are disclosed. The processing may take place during or after an angiography exam. The one or more frames of the angiogram are acquired during the angiography exam. The one or more frames are processed to determine, based on at least one pre-defined criterion, whether the angiogram at least comprises one frame with a diagnostic value among the one or more frames. If the angiogram comprises at least one frame with the diagnostic value, based on the angiogram, a score quantifying the diagnostic value of the angiogram is determined using a trained machine-learning (ML) algorithm. Techniques for processing, e.g., ranking/sorting, multiple angiograms associated with an anatomical region of interest of a patient are also provided, by which a respective score for each of the multiple angiograms is determined using the techniques for processing one or more frames of an angiogram.