A New Deep Learning Pipeline to Detect Covid-19 on Chest X-Ray Images using Local Binary Pattern, Dual Tree Complex Wavelet Transform and Convolutional Neural Networks

Abstract

At the end of 2019, a new type of virus, belonging to the coronaviridae family has emerged and it is considered that the virus in question is of zootonic origin. The virus that emerged in China first affected this country and then spread worldwide. Pneumonia develops due to Covid-19 virus in patients having severe disease symptoms. Many literature studies have been carried out in the process where the effects of the disease-induced pneumonia in lungs have been demonstrated with the help of chest X-ray imaging. In this study, which aims at early diagnosis of Covid-19 disease by using X-Ray images, the deep-learning approach, which is a state-of-the-art artificial intelligence method, was used and automatic classification of images was performed using Convolutional Neural Networks (CNN). In the first training-test data set used in the study, there were a total of 230 abnormal and 80 normal X-Ray images, while in the second training-test data set there were 476 X-Ray images, of which 150 abnormal and 326 normal. Thus, classification results have been provided for two data sets, containing predominantly abnormal images and predominantly normal images respectively. In the study, a 23-layer CNN architecture was developed. Within the scope of the study, results were obtained by using chest X-Ray images directly in training-test procedures and the sub-band images obtained by applying Dual Tree Complex Wavelet Transform (DT-CWT) to the above-mentioned images. The same experiments were repeated using images obtained by applying Local Binary Pattern (LBP) to the chest X-Ray images. Within the scope of the study, a new result generation algorithm having been put forward additionally, it was ensured that the experimental results were combined and the success of the study was improved. In the experiments carried out in the study, the trainings were carried out using the k-fold cross validation method. Here the k value was chosen 23. Considering the highest results of the tests performed in the study, values of sensitivity, specificity, accuracy and AUC for the first training-test data set were calculated to be 1, 1, 0,9913 and 0,9996; while for the second data set of training-test, they were 1, 0,9969, 0,9958 and 0,9996 respectively. Considering the average highest results of the experiments performed within the scope of the study, the values of sensitivity, specificity, accuracy and AUC for the first training-test data set were 0,9933, 0,9725, 0,9843 and 0,9988; while for the second training-test data set, they were 0,9813, 0,9908, 0,9857 and 0,9983 respectively.

COVID-19 Detection from Chest X-ray Images Using Feature Fusion and Deep Learning

“…However, the study by Loye et al [ 35 ] found a higher accuracy (100%) than this study. This could be due to a much lower number of images (69 COVID-19 and 79 normal images) used in their dataset for testing the system’s performance [ 59 ].…”

“…In this study, despite taking some preventative measures to avoid bias, such as using relatively large data set (3111 non-COVID and 1979 COVID-19 images) without huge data imbalanced, preprocessing of images (e.g., removing text labels) to remove dataset-dependent features, extracting features by two techniques and feature fusion and testing with a set of data different from the training set, still, the trained model would not be completely free from the learning bias. Yasar et al compiled results for the COVID-19 detection by recent studies using the X-ray images and found that seven out of sixteen (44%) studies used k-fold validation [ 59 ]. This represented that k-fold was a popular validation technique.…”

Robotics and artificial intelligence in healthcare during COVID-19 pandemic: A systematic review

“…As transfer learning from these models gave acceptable results, the authors suggested that the existing models for diagnosing should be explored with more attention before developing a completely new architecture with different deep learning techniques for COVID-19 detection. In [46] , the authors had developed a deep learning pipeline with local binary pattern, dual tree complex wavelet transform and convolutional neural networks for COVID-19 detection using chest X-ray images. Gupta et al.…”

COVID-19 deep classification network based on convolution and deconvolution local enhancement

“…This technique can analyze the lung tissue structure and lesion morphology of suspected COVID-19 patients. In this paper, the deep convolution neural network based on a lung CT image is used to judge the suspected COVID-19 patients [ 57 , 58 ].…”