Wide-Area Angiogram Synthesis via Feature Point Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional OCTA can only perform imaging for a relatively narrow area of the eye fundus, limiting the construction of angiograms over a wide area.
Innovation Solution
An ophthalmological device equipped with a memory to store angiograms, processors for detecting and identifying feature points, transforming angiograms based on feature point groups, and composing transformed angiograms to cover a wider area.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If conventional OCTA imaging is used, then imaging can be performed with current technology, but the imaging area is limited to a relatively narrow area
Solution Approach 1:
The patent divides the wide-area fundus imaging task into multiple narrow-area OCTA images that are captured separately and then synthesized through image processing. The fundus is imaged in multiple regions, each with its own angiogram, and these are subsequently combined to form a comprehensive wide-area angiogram.
Solution Approach 2:
The patent transitions from two-dimensional narrow-area imaging to wide-area imaging by introducing spatial synthesis through coordinate transformation and image composition. Multiple 2D angiograms are transformed and combined in a coordinate system to create a comprehensive wide-area view, effectively expanding the imaging coverage.
2Area of stationary object
If multiple angiograms are captured to cover wide area, then imaging coverage is improved, but position matching and composition complexity increases
Solution Approach 1:
The patent introduces feature points as intermediary elements that facilitate the matching and alignment of multiple angiograms. These feature points serve as reference markers that enable automatic position matching between different captured images, simplifying the composition process.
Solution Approach 2:
The patent applies coordinate transformation to change the spatial parameters of individual angiograms, transforming them into a unified coordinate system. This parameter transformation enables seamless composition of multiple images while maintaining accurate spatial relationships.
3Measurement precision
If feature point matching is performed for position alignment, then imaging precision is improved, but processing time increases
Solution Approach 1:
The patent performs feature point detection and grouping as preliminary actions before the actual image composition. By pre-identifying and organizing feature points into groups that correspond to the same fundus locations, the system prepares the data structure needed for efficient position matching and reduces processing time during composition.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An ophthalmological device in an embodiment comprises a storage unit, a detection unit, a specification unit, a deformation unit and a compositing unit. The storage unit stores a plurality of angiograms obtained by applying optical coherence tomography to the fundus of an eye being examined. The detection unit detects feature points from each of the plurality of angiograms. The specification unit specifies a plurality of feature points groups, each of said groups corresponding to the same site on the fundus, from the plurality of feature points detected by the detection unit from among the plurality of angiograms. The deformation unit deforms at least some of the plurality of angiograms on the basis of the plurality of feature point groups specified by the specification unit. The compositing unit combines two or more angiograms from among the plurality of angiograms, at least some of which were deformed by the deformation unit, on the basis of the plurality of feature point groups.