Experimental Science
Evaluation of low-quality fundus image enhancement based on cycle-constraint adversarial network
Xueting Zhou, Weihua Yang, Xiao Hua, Qijing You, Jing Sun, Jianxin Shen, Cheng Wan
Published 2021-09-10
Cite as Chin J Exp Ophthalmol, 2021, 39(9): 769-775. DOI: 10.3760/cma.j.cn115989-20201028-00718
Abstract
ObjectiveTo propose and evaluate the cycle-constraint adversarial network (CycleGAN) for enhancing the low-quality fundus images such as the blurred, underexposed and overexposed etc.
MethodsA dataset including 700 high-quality and 700 low-quality fundus images selected from the EyePACS dataset was used to train the image enhancement network in this study.The selected images were cropped and uniformly scaled to 512×512 pixels.Two generative models and two discriminative models were used to establish CycleGAN.The generative model generated matching high/low-quality images according to the input low/high-quality fundus images, and the discriminative model determined whether the image was original or generated.The algorithm proposed in this study was compared with three image enhancement algorithms of contrast limited adaptive histogram equalization (CLAHE), dynamic histogram equalization (DHE), and multi-scale retinex with color restoration (MSRCR) to perform qualitative visual assessment with clarity, BRISQUE, hue and saturation as quantitative indicators.The original and enhanced images were applied to the diabetic retinopathy (DR) diagnostic network to diagnose, and the accuracy and specificity were compared.
ResultsCycleGAN achieved the optimal results on enhancing the three types of low-quality fundus images including the blurred, underexposed and overexposed.The enhanced fundus images were of high contrast, rich colors, and with clear optic disc and blood vessel structures.The clarity of the images enhanced by CycleGAN was second only to the CLAHE algorithm.The BRISQUE quality score of the images enhanced by CycleGAN was 0.571, which was 10.2%, 7.3%, and 10.0% higher than that of CLAHE, DHE and MSRCR algorithms, respectively.CycleGAN achieved 103.03 in hue and 123.24 in saturation, both higher than those of the other three algorithms.CycleGAN took only 35 seconds to enhance 100 images, only slower than CLAHE.The images enhanced by CycleGAN achieved accuracy of 96.75% and specificity of 99.60% in DR diagnosis, which were higher than those of oringinal images.
ConclusionsCycleGAN can effectively enhance low-quality blurry, underexposed and overexposed fundus images and improve the accuracy of computer-aided DR diagnostic network.The enhanced fundus image is helpful for doctors to carry out pathological analysis and may have great application value in clinical diagnosis of ophthalmology.
Key words:
Deep learning; Image enhancement; Cycle-constraint adversarial network; Fundus image
Contributor Information
Xueting Zhou
College of Electronic Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
Weihua Yang
The Laboratory of Artificial Intelligence and Bigdata in Ophthalmology, The Affiliated Eye Hospital of Nanjing Medical University, Nanjing 210001, China
Xiao Hua
Nanjing Star-mile Technology Co., Ltd, Nanjing 210046, China
Qijing You
College of Electronic Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
Jing Sun
College of Electronic Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
Jianxin Shen
College of Electronic Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
Cheng Wan
College of Electronic Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
