DCNN-FuzzyWOA: Artificial Intelligence Solution for Automatic Detection of COVID-19 Using X-Ray Images

Abstract

Artificial intelligence (AI) techniques have been considered effective technologies in diagnosing and breaking the transmission chain of COVID-19 disease. Recent research uses the deep convolution neural network (DCNN) as the discoverer or classifier of COVID-19 X-ray images. The most challenging part of neural networks is the subject of their training. Descent-based (GDB) algorithms have long been used to train fullymconnected layer (FCL) at DCNN. Despite the ability of GDBs to run and converge quickly in some applications, their disadvantage is the manual adjustment of many parameters. Therefore, it is not easy to parallelize them with graphics processing units (GPUs). Therefore, in this paper, the whale optimization algorithm (WOA) evolved by a fuzzy system called FuzzyWOA is proposed for DCNN training. With accurate and appropriate tuning of WOA’s control parameters, the fuzzy system defines the boundary between the exploration and extraction phases in the search space. It causes the development and upgrade of WOA. To evaluate the performance and capability of the proposed DCNN-FuzzyWOA model, a publicly available database called COVID-Xray-5k is used. DCNN-PSO, DCNN-GA, and LeNet-5 benchmark models are used for fair comparisons. Comparative parameters include accuracy, processing time, standard deviation (STD), curves of ROC and precision-recall, and F1-Score. The results showed that the FuzzyWOA training algorithm with 20 epochs was able to achieve 100% accuracy, at a processing time of 880.44 s with an F1-Score equal to 100%. Structurally, the i-6c-2s-12c-2s model achieved better results than the i-8c-2s-16c-2s model. However, the results of using FuzzyWOA for both models have been very encouraging compared to particle swarm optimization, genetic algorithm, and LeNet-5 methods.

Detection of Covid-19 Using AI Application

“…Helical CT is used because it is faster, produces better quality 3D images of the internal organs, and may also detect small abnormalities better. Computed tomography imaging is highly sensitive in detecting early disease, assessing the abnormalities, progression of the disease, etc [9].…”

Improved Latin hypercube sampling initialization-based whale optimization algorithm for COVID-19 X-ray multi-threshold image segmentation

“…Haque et al reviewed the fundamentals of deep learning methods and their implementation in various medical applications 60 . Furthermore, several approaches have been developed for COVID-19 diagnosis using medical imaging: IP-based SCA evolved deep convolutional neural networks for chest CT scans 61 , improved deep convolutional neural networks using the chimp optimization algorithm for X-ray images 62 , automatic COVID-19 diagnosis from chest X-ray images using a deep trigonometric convolutional neural network 63 , and real-time COVID-19 diagnosis from X-ray images using deep CNN and extreme learning machines stabilized by the chimp optimization algorithm 64 . However, deep learning-based image segmentation methods tend to have disadvantages such as high time complexity, inability to perform real-time segmentation, coarse utilization of global contextual information, and unfavorable application to 3D image segmentation 65 , 66 .…”

Predicting survival of Iranian COVID-19 patients infected by various variants including omicron from CT Scan images and clinical data using deep neural networks

“…Some of the introduced models can also calculate the percentage of infected regions of the lungs [13] . Another group of studies has focused on diagnosing COVID-19 from chest X-ray images to be utilized as a screening stage [10] , [20] , [21] , [22] , [23] , [24] , [25] , [26] , [27] , [28] , [29] . Other than single-person-based analysis, some studies have focused on large-scale predictions using the time series to help in large-scale management decisions, e.g., the number of COVID-19 cases and the mortality rate of COVID-19 [30] , [31] , [32] , [33] .…”