Retinal OCT Segmentation Confidence Map Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Optical Coherence Tomography (OCT) data processing lacks a method to accurately and automatically generate a confidence map for retinal layer segmentation, making it difficult to interpret and reliable retinal layer thickness measurements.
Innovation Solution
A computer-implemented method that processes retinal layer segmentation data to generate a segmentation confidence map by calculating confidence indicators for each voxel based on probability values, allowing for the identification of reliable classifications and spatial distribution of confidence in retinal layer classifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If retinal layer segmentation is performed automatically using algorithms, then productivity is improved, but reliability deteriorates due to lack of confidence assessment
Solution Approach 1:
The patent implements feedback by calculating confidence indicators from the probability values generated by the segmentation algorithm and using these to assess and validate the reliability of segmentation results, allowing the system to self-evaluate its own performance
Solution Approach 2:
The patent introduces confidence indicators as an intermediary between the segmentation algorithm output and the final interpretation, providing a mediating layer that assesses the quality of segmentation before clinical use
2Measurement precision
If probability values are generated for each voxel, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent extracts only the necessary confidence information from the probability values using simple operations like finding the maximum probability and calculating the difference between top probabilities, avoiding complex processing while maintaining precision
Solution Approach 2:
The patent transforms the raw probability values into simplified confidence indicators through parameter transformation, converting complex probability distributions into interpretable confidence scores
Data Source
AI summary
A method of generating a segmentation confidence map by processing classification values each indicating a respective classification of a respective voxel of a retinal C-scan into a respective retinal layer class of a predefined set of retinal layer classes, the method comprising: generating, for each voxel, a respective confidence value which indicates a level of confidence in the classification of the voxel; for a retinal layer class of the predefined set, identifying a subset of the voxels such that the classification value generated for each voxel indicates a classification of the voxel into the retinal layer class; calculating, for each A-scan having voxels in the identified subset, a respective average of the confidence indicator values generated for the voxels; and using the calculated averages to generate the map, which indicates a spatial distribution of a level of confidence in the classification of the voxels.