A Superpixel-Based Algorithm for Detecting Optical Density Changes in Choroidal Optical Coherence Tomography Images of Diabetic Patients

TL;DR

This paper introduces a new image-processing algorithm to detect changes in eye scans of diabetic patients, revealing potential biomarkers for early vascular damage.

Contribution

A novel superpixel-based algorithm is proposed to analyze OCT images for detecting choroidal vascular changes in diabetes.

Findings

Significant differences in choroidal area and optical density were found between diabetic and healthy eyes.

The algorithm identified new biomarkers for early vascular damage in diabetic patients.

Abstract

Background: This study explored the diagnostic potential of image-processing analysis in optical coherence tomography (OCT) images to detect systemic vascular changes in individuals with systemic diseases. Methods: Ocular OCT images from two cohorts diabetic patients and healthy control subjects were analyzed. A novel Superpixel Segmentation (SpS) algorithm was used to process these images and extract optical image density information from ocular vascular tissue. The algorithm was applied to isolate the choroid layer for analysis of its optical properties. The procedure was performed by separate examiners, and both inter- and intra-observer repeatability were assessed. Choroidal area (CA) and choroidal optical image density (COID) metrics were used to assess structural changes in the vascular tissue and predict alterations in the choroidal parameters. Results: A total of 110 diabetic patient eye images and 92 healthy control images were processed. The results showed significant differences in CA and COID between diabetic and healthy eyes, indicating that these parameters could serve as valuable biomarkers for early vascular damage. Conclusions: The use of the SpS algorithm on OCT B-scan images allows for the identification of new parameters linked to ocular vascular damage. These findings suggest that digital image-processing techniques can reveal differences in vascular tissue, offering potential new indicators of pathology.

Figures