Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images

Abstract

Computer-aided diagnosis for the reliable and fast detection of coronavirus disease (COVID-19) has become a necessity to prevent the spread of the virus during the pandemic to ease the burden on the healthcare system. Chest X-ray (CXR) imaging has several advantages over other imaging and detection techniques. Numerous works have been reported on COVID-19 detection from a smaller set of original X-ray images. However, the effect of image enhancement and lung segmentation of a large dataset in COVID-19 detection was not reported in the literature. We have compiled a large X-ray dataset (COVQU) consisting of 18,479 CXR images with 8851 normal, 6012 non-COVID lung infections, and 3616 COVID-19 CXR images and their corresponding ground truth lung masks. To the best of our knowledge, this is the largest public COVID positive database and the lung masks. Five different image enhancement techniques: histogram equalization (HE), contrast limited adaptive histogram equalization (CLAHE), image complement, gamma correction, and balance contrast enhancement technique (BCET) were used to investigate the effect of image enhancement techniques on COVID-19 detection. A novel U-Net model was proposed and compared with the standard U-Net model for lung segmentation. Six different pre-trained Convolutional Neural Networks (CNNs) (ResNet18, ResNet50, ResNet101, InceptionV3, DenseNet201, and ChexNet) and a shallow CNN model were investigated on the plain and segmented lung CXR images. The novel U-Net model showed an accuracy, Intersection over Union (IoU), and Dice coefficient of 98.63%, 94.3%, and 96.94%, respectively for lung segmentation. The gamma correction-based enhancement technique outperforms other techniques in detecting COVID-19 from the plain and the segmented lung CXR images. Classification performance from plain CXR images is slightly better than the segmented lung CXR images; however, the reliability of network performance is significantly improved for the segmented lung images, which was observed using the visualization technique. The accuracy, precision, sensitivity, F1-score, and specificity were 95.11 %, 94.55 %, 94.56 %, 94.53 %, and 95.59 % respectively for the segmented lung images. The proposed approach with very reliable and comparable performance will boost the fast and robust COVID-19 detection using chest X-ray images.

An optimized KELM approach for the diagnosis of COVID-19 from 2D-SSA reconstructed CXR Images

“… [26] Ensemble learning + CNN 438 +_+ 333 91.62 X Rahman et al. [28] U-Net+CNN 3616+6012+8851 X 96.29 Shakarami et al. [29] CBIR + AlexNet CNN 400+_+400 99.38 X Proposed Model 2D-SSA + Block GLCM + Grasshopper based KELM 460+3418+1266 100 100 …”

“…To expand the size of the small set of COVID-19 images, one of the promising methods is data augmentation [11] , [13] . Continuous efforts are made employing various machine learning (ML) algorithms where the database of increased number of images are used [21] , [22] , [23] , [24] , [25] , [26] , [27] , [28] , [29] . Chandra et al.…”

“…The same concept is carried out by Rahman et al. [28] while using a 22 layer CNN with a modified version of U-Net segmentation for lung area segmentation from CXR images. Although, most of the aforementioned methods report an accuracy of more than 95%, however, due to the lower number of samples for training the DNNs, the evaluation of the robustness of the proposed models or obtaining a generalized power for clinical setting is dubious [30] .…”

PCXRNet: Condense attention block and Multiconvolution spatial attention block for Pneumonia Chest X-Ray detection

“…(1) Results on COVID-19 Radiography Dataset Rahman et al [43] first used the modified U-Net to segment lung area and then applied a classification network to recognize the COVID-19. This experiment did not use other data enhancement.…”

PCXRNet: Condense attention block and Multiconvolution spatial attention block for Pneumonia Chest X-Ray detection

“…COVID-19 Radiography Database V4: This dataset was created by a team of researchers from Qatar University, the University of Dhaka, etc. [43]. It is currently one of the largest datasets of chest X-ray images of COVID-19.…”