RBAD: A Dataset and Benchmark for Retinal Vessels Branching Angle Detection

TL;DR

This paper introduces RBAD, a new dataset and benchmark for detecting retinal vessel branching angles, featuring a novel self-configured image processing method and an open-source annotation tool to improve accuracy and efficiency in ophthalmic diagnosis.

Contribution

The paper presents a novel self-configured image processing technique for retinal branching angle detection, along with an open-source dataset and benchmark for improved analysis.

Findings

High accuracy in angle detection across various conditions

Robustness of the method demonstrated through benchmark comparison

Enhanced efficiency over previous approaches

Abstract

Detecting retinal image analysis, particularly the geometrical features of branching points, plays an essential role in diagnosing eye diseases. However, existing methods used for this purpose often are coarse-level and lack fine-grained analysis for efficient annotation. To mitigate these issues, this paper proposes a novel method for detecting retinal branching angles using a self-configured image processing technique. Additionally, we offer an open-source annotation tool and a benchmark dataset comprising 40 images annotated with retinal branching angles. Our methodology for retinal branching angle detection and calculation is detailed, followed by a benchmark analysis comparing our method with previous approaches. The results indicate that our method is robust under various conditions with high accuracy and efficiency, which offers a valuable instrument for ophthalmic research and clinical applications.