Contrast Enhancement of RGB Retinal Fundus Images for Improved Segmentation of Blood Vessels Using Convolutional Neural Networks

Retinal fundus images are non-invasively acquired and faced with low contrast, noise, and uneven illumination. The low-contrast problem makes objects in the retinal fundus image indistinguishable and the segmentation of blood vessels very challenging. Retinal blood vessels are significant because of their diagnostic importance in ophthalmologic diseases. This paper proposes improved retinal fundus images for optimal segmentation of blood vessels using convolutional neural networks (CNNs). This study explores some robust contrast enhancement tools on the RGB and the green channel of the retinal fundus images. The improved images undergo quality evaluation using mean square error (MSE), peak signal to noise ratio (PSNR), Similar Structure Index Matrix (SSIM), histogram, correlation, and intersection distance measures for histogram comparison before segmentation in the CNN-based model. The simulation results analysis reveals that the improved RGB quality outperforms the improved green channel. This revelation implies that the choice of RGB to the green channel for contrast enhancement is adequate and effectively improves the quality of the fundus images. This improved contrast will, in turn, boost the predictive accuracy of the CNN-based model during the segmentation process. The evaluation of the proposed method on the DRIVE dataset achieves an accuracy of 94.47, sensitivity of 70.92, specificity of 98.20, and AUC (ROC) of 97.56.

Automated summary

This paper proposes an improved method for optimal segmentation of blood vessels in retinal fundus images using convolutional neural networks (CNNs). By enhancing the contrast of the RGB and green channel, the improved images are evaluated for quality using various measures. The results show that the improved RGB quality outperforms the improved green channel, indicating that using RGB for contrast enhancement effectively improves the image quality. The proposed method achieves an accuracy of 94.47%, sensitivity of 70.92%, specificity of 98.20%, and AUC (ROC) of 97.56% on the DRIVE dataset.