Dehazing Algorithm for Enhancing Fundus Photographs Using Dark Channel and Bright Channel Prior
10.3341/jkos.2024.65.1.44
- Author:
Sehie PARK
1
;
Hyungjin CHUNG
;
Jong Chul YE
;
Kayoung YI
Author Information
1. Department of Ophthalmology, Hallym University College of Medicine, Seoul, Korea
- Publication Type:Original Article
- From:Journal of the Korean Ophthalmological Society
2024;65(1):44-52
- CountryRepublic of Korea
- Language:Korean
-
Abstract:
Purpose:We present a dehazing algorithm using dark channel prior (DCP) and bright channel prior (BCP) to enhance the quality of retinal images obtained through conventional fundus photography.
Methods:A retrospective analysis was conducted on retinal images from patients who visited Gangnam Sacred Heart Hospital between January 2000 and September 2022. These images were captured using a digital fundus camera (KOWA Nonmyd 8S Fundus Camera, KOWA Company, Nagoya, Japan) without pupil dilation. We used two mathematical algorithms: DCP only and DCP and BCP combined. The original, DCP-processed, and DCP & BCP-processed images were compared. Fisher's exact test was used to identify significant quality improvements.
Results:The DCP and the newly proposed DCP plus BCP algorithm effectively eliminated haze and enhanced the contrast of cataract images. Notably, DCP demonstrated limited improvements in fundus photographs from patients with small pupils, whereas the proposed DCP plus BCP method effectively revealed previously obscured retinal details and vessels. However, these methods exhibited limited performance in severe cataracts compared to the clear images obtained after surgery. The quality enhancement with the proposed method was significant in photographs of patients with cataracts (p = 0.032) and small pupils (p < 0.01).
Conclusions:Our algorithm produced clearer images of blood vessels and optic disc structures, while significantly reducing artifacts in fundus images from patients with small pupils or cataracts. The proposed algorithm can provide visually enhanced images, potentially aiding physicians in the diagnosis of retinal diseases in patients with cataracts.
