Exploring the Impact of Preprocessing Techniques on Retinal Blood Vessel Segmentation Using a Study Group Learning Scheme

The segmentation of retinal vessels in retinal images is vital for automated diagnosis of retinal diseases. This is a challenging task because it requires accurate manual labeling of the vessels by expert clinicians and the detection of tiny vessels is difficult due to limited samples, low contrast, and noise. In this study, we explore the use of preprocessing techniques such as contrast-limited adaptive histogram equalization (CLAHE), grad-cam analysis and min-max contrast stretching to improve the performance of a study-group learning (SGL) segmentation model. We evaluate the impact of these preprocessing techniques on the accuracy, sensitivity, specificity, AUC, IoU, and Dice scores using four publicly available datasets, DRIVE, CHASE, HRF and IOSTAR. Our findings indicate that the utilization of the Min-Max technique resulted in a notable enhancement in the accuracy of both the DRIVE and CHASE datasets, with an approximate increase of 3% and 2% respectively. Conversely, the impact of the CLAHE method was discernible solely in the DRIVE dataset, demonstrating an improvement in accuracy of 1%. In addition, our results demonstrated superior accuracy performance for both the DRIVE and CHASE datasets compared to the findings of the reviewed studies. The GitHub repo for this project is available at Link.

I. Introduction

Any abnormality in the retina or ocular condition, such as glaucoma or diabetic retinopathy, can impair a person’s vision. Glaucoma is the second leading cause of irreversible vision loss worldwide, after cataracts [1]. Approximately 12% of all cases of blindness worldwide can be attributed to retinal abnormalities. The structure of retinal blood vessels is critical for the diagnosis of such abnormalities. The identification and localization of retinal vessels enable the differentiation of the diverse vasculature structure of the retina from the background of the fundus image. This allows clinicians to interpret potentially problematic retinal anatomical structures such as abnormal lesions, macula, and optic disc [2–4]. Even the color of the retina changes throughout life and can be used as a biomarker for a variety of diseases, including diabetes and stroke prediction [2–4].