Related Experiment Video
Updated: Jul 14, 2026
11:45
Generation and 3-Dimensional Quantitation of Arterial Lesions in Mice Using Optical Projection Tomography
Published on: May 26, 2015
Using an Image Fusion Methodology to Improve Efficiency and Traceability of Posterior Pole Vessel Analysis by
Sasapin G Prakalapakorn1, Laura A Vickers1, Rolando Estrada2
1Deptartment of Ophthalmology, Duke University, Durham, NC 27710, USA.
The Open Ophthalmology Journal
|August 2, 2017
Summary
Image fusion using robust mosaicing improves the speed and accuracy of analyzing retinal blood vessels in retinopathy of prematurity (ROP) using ROPtool. This enhancement aids in the objective diagnosis of plus disease, a critical step in ROP treatment decisions.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computational Biology
Background:
- Diagnosis of plus disease in retinopathy of prematurity (ROP) is subjective and crucial for treatment decisions.
- Semi-automated programs like ROPtool quantify vascular changes but require high-quality images.
- Many indirect ophthalmoscopy images lack sufficient quality for accurate ROPtool analysis.
Purpose of the Study:
- To evaluate if robust mosaicing, an image fusion technique, can enhance posterior pole vessel analysis efficiency and traceability by ROPtool.
- To assess the impact of image enhancement on the objectivity of ROP diagnosis.
Main Methods:
- Retrospective review of video indirect ophthalmoscopy images from ROP examinations.
- Creation of enhanced mosaic images using robust mosaicing from video data.
- Comparison of ROPtool analysis time and vessel tracing capability between enhanced and unenhanced images.
Main Results:
- ROPtool analysis was significantly faster with enhanced mosaic images (125s) compared to unenhanced still images (152s; p=0.02).
- Retinal vessel tracing was more successful in enhanced images, covering more quadrants (92% vs. 74%; p=0.16) and overall (97% vs. 87%; p=0.07).
Conclusions:
- Retinal image enhancement via robust mosaicing improves ROPtool's efficiency and vessel analysis capabilities.
- This methodology represents a significant advancement in automating the grading of posterior pole disease in ROP.
