A Novel Hybrid Dehazing and Illumination based Approach for Preprocessing, Enhancement and Segmentation of Lung Images using Deep Learning

Abstract

Abstract Medical images are affected by various complications such as noise and deficient contrast. To increase the quality of an image, it is highly important to increase the contrast and eliminate noise. In the field of image processing, image enhancement is one of the essential methods for recovering the visual aspects of an image. However segmentation of the medical images such as brain MRI and lungs CT scans properly is difficult. In this article, a novel hybrid method is proposed for the enhancement and segmentation of lung images. The suggested article includes two steps. In the 1st step, lung images were enhanced. During enhancement, images were gone through many steps such as de-hazing, complementing, channel stretching, course illumination, and image fusion by principal component analysis (PCA). In the second step, the modified U-Net model was applied to segment the images. We evaluated the entropy of input and output images, mean square error (MSE), peak signal-to-noise ratio (PSNR), gradient magnitude similarity deviation (GMSD), and multi-scale contrast similarity deviation (MCSD) after the enhancement process. During segmentation we used both original and enhanced images and calculated the segmentation accuracy. We found that the Dice-coefficient was 0.9695 for the original images and 0.9797 for the enhanced images.