OCTA Quality Maps Using Texture Analysis for Objective Scan Review
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing OCTA scans suffer from quality issues that are subjective and time-consuming to assess, making it difficult to determine if a scan is of sufficient quality for diagnosis, and there is no automated method to quantify the quality of flow information.
Innovation Solution
A system and method for generating quantitative quality maps of OCT/OCTA scans by analyzing texture properties at each image location, identifying potential issues, and providing corrective actions to improve scan quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If subjective assessment methods are used to evaluate OCTA scan quality, then flexibility in judgment is maintained, but the process becomes time-consuming and lacks objectivity
Solution Approach 1:
The patent replaces subjective human assessment with an automated image processing system that objectively evaluates OCTA scan quality. The system extracts multiple image quality metrics (signal-to-noise ratio, contrast, brightness, uniformity) and combines them into a comprehensive quality score, eliminating the need for manual review while providing reliable, repeatable assessments.
Solution Approach 2:
The system performs self-assessment of scan quality by automatically analyzing the OCTA images themselves without requiring external human evaluation. The image processing algorithm independently evaluates quality parameters and generates quality maps, allowing the system to serve its own quality control needs efficiently.
2Productivity
If automated quality assessment is implemented, then objectivity and speed are improved, but the complexity of the system increases
Solution Approach 1:
The quality assessment system is divided into separate functional modules: signal-to-noise ratio calculation, contrast analysis, brightness measurement, uniformity evaluation, and quality score aggregation. Each module processes a specific aspect of image quality independently, making the overall complex task manageable through modular components that can be implemented and maintained systematically.
3Reliability
If quality assessment is performed after scan acquisition, then scan production is not interrupted, but low-quality scans cannot be corrected and may be lost
Solution Approach 1:
The system performs quality assessment before finalizing scan acceptance, allowing operators to identify and correct issues while the patient is still positioned and ready for potential re-scanning. The quality maps and metrics are generated in advance to guide decisions about whether additional scans are needed, preventing loss of potentially correctable data.
Solution Approach 2:
The system provides immediate feedback on scan quality through quality maps and numerical scores that are displayed to operators during or after acquisition. This feedback loop enables real-time identification of quality issues and guides decisions about retaking scans, ensuring that only adequately quality-assessed data is used for diagnosis while allowing correction of low-quality acquisitions.
Data Source
Figure 1~3
Figure 2
Figure 4
AI summary
A system, method, and/or device for determinizing a quality measure of OCT structural data and/or OCTA functional data uses a machine learning model trained to provide a single overall quality measure, or a quality map distribution for the OCT/OCTA data based on the generation of multiple features maps extracted from one or more slab views of the OCT/OCTA data. The extracted feature maps may be different texture-type maps, and the machine model is trained to determine the quality measure based on the texture maps.