Introduction

Few studies have explored MultiColor™ imaging (MCI) in evaluating retinal vascular diseases, particularly branch retinal vein occlusion (BRVO). This study aimed to compare the identification of retinal vessel whitening in BRVO using MCI by scanning confocal laser versus conventional white-flash color fundus photography (CFP).

Methods

Paired images of consecutive patients diagnosed with BRVO who underwent same-day MCI and CFP were reviewed. Visualization of vessel whitening on MCI and CFP was graded and scored using a scale by two masked graders. A longitudinal analysis of the vessel grading score was performed to evaluate the vessel whitening detection by MCI. A correlation analysis was conducted between vessel whitening on MCI and the measured area of retinal ischemia on fluorescein angiography to evaluate the MCI performance.

Results

Forty-four eyes of 41 patients (mean age 69 ± 14 years; 61% female) were analyzed. MCI demonstrated superior vessel whitening visibility score than CFP (p < 0.001). Longitudinal analysis showed no significant changes in vessel whitening visibility scores over a mean follow-up time of 430 ± 648 days (p = 0.655). There was a significantly positive correlation between the grading score of vessels whitening by MCI and the area of ischemia by fluorescein angiography (r2 = 0.15; p = 0.036).

Conclusion

MCI appears to provide a superior detection of whitening BRVO compared to CFP, serving as a rapid and non-invasive correlate of retinal ischemia.

Purpose

The purpose of this study was to evaluate the ability to align two types of retinal images taken on different platforms; color fundus (CF) photographs and infrared scanning laser ophthalmoscope (IR SLO) images using mathematical warping and artificial intelligence (AI).

Methods

We collected 109 matched pairs of CF and IR SLO images. An AI algorithm utilizing two separate networks was developed. A style transfer network (STN) was used to segment vessel structures. A registration network was used to align the segmented images to each. Neither network used a ground truth dataset. A conventional image warping algorithm was used as a control. Software displayed image pairs as a 5 × 5 checkerboard grid composed of alternating subimages. This technique permitted vessel alignment determination by human observers and 5 masked graders evaluated alignment by the AI and conventional warping in 25 fields for each image.

Results

Our new AI method was superior to conventional warping at generating vessel alignment as judged by masked human graders (P < 0.0001). The average number of good/excellent matches increased from 90.5% to 94.4% with AI method.

Conclusions

AI permitted a more accurate overlay of CF and IR SLO images than conventional mathematical warping. This is a first step toward developing an AI that could allow overlay of all types of fundus images by utilizing vascular landmarks.

Translational relevance

The ability to align and overlay imaging data from multiple instruments and manufacturers will permit better analysis of this complex data helping understand disease and predict treatment.