Ophthalmic Image Processing Device for Multi-Tissue Abnormality Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ophthalmic image processing methods struggle to provide a comprehensive view of structural abnormalities in ophthalmic images, making it difficult for users to accurately determine the extent and distribution of abnormalities across multiple tissues.
Innovation Solution
An ophthalmic image processing device and method that acquires ophthalmic images of a subject eye, uses a machine learning algorithm to generate probability distributions for identifying multiple tissues, and creates simultaneous side-by-side displays of structural abnormality degree maps for each tissue, allowing for a clearer visualization of abnormality distribution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single structural abnormality degree map is generated for the entire tissue, then the presence or absence of abnormality can be recognized, but the whole picture of structural abnormality cannot be recognized
Solution Approach 1:
The patent divides the tissue into multiple specific layers or boundaries (e.g., different retinal layers in OCT images) and generates separate structural abnormality degree maps for each layer. This segmentation allows the system to preserve detailed abnormality distribution information across different tissue depths while maintaining overall abnormality detection capability.
2Loss of information
If multiple structural abnormality degree maps are generated for different tissues, then comprehensive abnormality information is provided, but the complexity of the processing system increases
Solution Approach 1:
The patent employs a universal processing framework that can handle multiple tissue layers through the same basic workflow: acquiring ophthalmic images, generating probability distributions using machine learning, calculating structural abnormality degrees, and creating visual maps. This multi-functional approach allows the system to process different tissue layers consistently without requiring separate complex processing pipelines for each layer.
3Loss of information
If separate structural abnormality degree maps are generated for each tissue layer, then the whole picture of structural abnormality can be recognized, but the ease of operation decreases
Solution Approach 1:
The patent enhances the visualization of multiple tissue layer maps by introducing additional dimensional representations. This may include displaying maps in a stacked three-dimensional arrangement, using color-coded legends, or providing depth indicators that help users intuitively understand the spatial relationships between abnormalities in different tissue layers, thereby improving ease of interpretation.
Data Source
AI summary
An ophthalmic image processing device processes an ophthalmic image of a subject eye. The ophthalmic image processing device includes a controller which acquires an ophthalmic image including a tomographic image of a plurality of tomographic planes in a subject eye, acquires a probability distribution for identifying two or more tissues included in a plurality of tissues in the tomographic image, by inputting the ophthalmic image into a mathematical model trained with using a machine learning algorithm, generates a structural abnormality degree map showing a two-dimensional distribution of a degree of abnormality of a structure in the tissue, for each of the two or more tissues, based on the probability distribution, and simultaneously displays two or more structural abnormality degree maps generated for each of the two or more tissues side by side on a display device.