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

Abstract

Currently, COVID-19 is considered to be the most dangerous and deadly disease for the human body caused by the novel coronavirus. In December 2019, the coronavirus spread rapidly around the world, thought to be originated from Wuhan in China and is responsible for a large number of deaths. Earlier detection of the COVID-19 through accurate diagnosis, particularly for the cases with no obvious symptoms, may decrease the patient’s death rate. Chest X-ray images are primarily used for the diagnosis of this disease. This research has proposed a machine vision approach to detect COVID-19 from the chest X-ray images. The features extracted by the histogram-oriented gradient (HOG) and convolutional neural network (CNN) from X-ray images were fused to develop the classification model through training by CNN (VGGNet). Modified anisotropic diffusion filtering (MADF) technique was employed for better edge preservation and reduced noise from the images. A watershed segmentation algorithm was used in order to mark the significant fracture region in the input X-ray images. The testing stage considered generalized data for performance evaluation of the model. Cross-validation analysis revealed that a 5-fold strategy could successfully impair the overfitting problem. This proposed feature fusion using the deep learning technique assured a satisfactory performance in terms of identifying COVID-19 compared to the immediate, relevant works with a testing accuracy of 99.49%, specificity of 95.7% and sensitivity of 93.65%. When compared to other classification techniques, such as ANN, KNN, and SVM, the CNN technique used in this study showed better classification performance. K-fold cross-validation demonstrated that the proposed feature fusion technique (98.36%) provided higher accuracy than the individual feature extraction methods, such as HOG (87.34%) or CNN (93.64%).

Willing or Hesitant? A Socioeconomic Study on the Potential Acceptance of COVID-19 Vaccine in Japan

“…As of 18 March 2021—a year after the WHO categorized the COVID-19 outbreak as a pandemic, there were 120,915,219 cumulative cases and 2,674,078 total deaths [ 1 ]. The number of infected cases is believed to be underreported because of asymptomatic infection, hesitancy to get tested, and lack of alternative testing procedures [ 2 , 3 , 4 , 5 ]. The pandemic disrupted many aspects of human activity, leading to worldwide economic challenges including increased unemployment, income, food, and housing insecurity, and intimate partner violence [ 6 , 7 , 8 ].…”

Medical Images Encryption Based on Adaptive-Robust Multi-Mode Synchronization of Chen Hyper-Chaotic Systems

“…For future work, the proposed method can be utilized to encrypt EEG signals of epileptic seizures [ 67 , 68 ], attention deficit hyperactivity disorder (ADHD) [ 69 , 70 ], schizophrenia [ 71 , 72 ], and multiple sclerosis [ 73 ]. Additionally, the technique presented in this study can be adopted to encrypt MRI [ 74 , 75 ], X-ray [ 76 ], mammography [ 77 , 78 ], and other medical data [ 79 , 80 , 81 , 82 , 83 , 84 ].…”

COVID-19 Biomarkers and Advanced Sensing Technologies for Point-of-Care (POC) Diagnosis

“…X-ray stands for Energetic High-Frequency Electromagnetic Radiation. An electromagnetic beam passes through the body and body tissues and bones absorb or block the beam at different densities [176]. This creates a shadow that is picked up by a sensor.…”