3D Eye Imaging Segmentation for Transparent Vitreous Visualization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods face difficulties in visualizing and evaluating dynamic structures within the eye, such as the vitreous, due to its transparent and gelatinous nature, making it challenging to diagnose medical conditions like diabetic retinopathy and myopia in vivo.
Innovation Solution
A medical diagnostic apparatus that uses three-dimensional data from the eye, segmented using multiple algorithms trained on two-dimensional data from different planes, to generate metrics for evaluating medical conditions by producing a segmented three-dimensional data set and skeletonization, allowing for improved visualization and analysis of eye structures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If conventional imaging methods are used to view eye structures, then the imaging process is simple, but the ability to visualize transparent gelatinous structures like the vitreous is insufficient
Solution Approach 1:
The patent transitions from conventional two-dimensional imaging to three-dimensional volumetric imaging of the eye. By acquiring OCT data in three dimensions and performing volumetric segmentation, the system enables comprehensive visualization of transparent gelatinous structures like the vitreous that cannot be adequately captured in 2D slices alone
Solution Approach 2:
The patent applies pseudo-color mapping to segmented three-dimensional eye structures to enhance visual differentiation. Different tissue types and structural elements are assigned distinct color codes, making transparent and gelatinous structures visually distinguishable and easier to evaluate
2Measurement precision
If multiple segmentation algorithms are used to segment three-dimensional eye data, then the diagnostic accuracy is improved, but the processing complexity increases
Solution Approach 1:
The patent divides the three-dimensional eye data into multiple two-dimensional planar datasets (axial, coronal, and sagittal planes). Each plane is processed by dedicated segmentation algorithms trained on plane-specific data, and the results are integrated to form a comprehensive three-dimensional segmentation. This approach improves diagnostic accuracy by capturing structural features that may be missed in single-plane analysis
Solution Approach 2:
The patent develops a unified multi-plane segmentation framework where algorithms trained on different planes (axial, coronal, sagittal) work together to segment the complete three-dimensional eye structure. This multi-functional approach allows a single system to handle various imaging planes and orientations, improving robustness and accuracy without requiring separate specialized systems for each plane
3Manufacturing precision
If three-dimensional data is segmented into multiple planes using separate algorithms, then the structural detail is enhanced, but the computational time increases
Solution Approach 1:
The patent performs preliminary segmentation on individual two-dimensional planes (axial, coronal, sagittal) before integrating them into the final three-dimensional structure. By pre-processing each plane separately with optimized algorithms trained on plane-specific characteristics, the system achieves detailed structural segmentation while managing computational complexity through divide-and-conquer strategy
Data Source
AI summary
A medical diagnostic apparatus includes a receiver circuit that receives three-dimensional data of an eye, and processing circuitry configured to segment the three-dimensional data into regions that include a target structural element and regions that do not include the target structural element to produce a segmented three-dimensional data set. The segmenting is performed using a plurality of segmentation algorithms. Each of the plurality of segmentation algorithms is trained separately on different two-dimensional data extracted from the three-dimensional data. The processing circuitry is further configured to generate at least one metric from the segmented three-dimensional data set, and evaluate a medical condition based on the at least one metric.