The updating operation repeated until reaching the stop condition. (22) can be written as follows: By using the discrete form of GL definition of Eq. The given Kaggle dataset consists of chest CT scan images of patients suffering from the novel COVID-19, other pulmonary disorders, and those of healthy patients. Appl. 0.9875 and 0.9961 under binary and multi class classifications respectively. The first one is based on Python, where the deep neural network architecture (Inception) was built and the feature extraction part was performed. Whereas the worst one was SMA algorithm. One of the best methods of detecting. Chong et al.8 proposed an FS model, called Robustness-Driven FS (RDFS) to select futures from lung CT images to classify the patterns of fibrotic interstitial lung diseases. Sahlol, A.T., Yousri, D., Ewees, A.A. et al. Syst. 79, 18839 (2020). In57, ResNet-50 CNN has been applied after applying horizontal flipping, random rotation, random zooming, random lighting, and random wrapping on raw images. They applied the SVM classifier with and without RDFS. Eng. In general, feature selection (FS) methods are widely employed in various applications of medical imaging applications. In this paper, filters of size 2, besides a stride of 2 and \(2 \times 2\) as Max pool, were adopted. Vis. The symbol \(r\in [0,1]\) represents a random number. It based on using a deep convolutional neural network (Inception) for extracting features from COVID-19 images, then filtering the resulting features using Marine Predators Algorithm (MPA), enhanced by fractional-order calculus(FO). Thereafter, the FO-MPA parameters are applied to update the solutions of the current population. Besides, all algorithms showed the same statistical stability in STD measure, except for HHO and HGSO. This paper reviews the recent progress of deep learning in COVID-19 images applications from five aspects; Firstly, 33 COVID-19 datasets and data enhancement methods are introduced; Secondly, COVID-19 classification methods . Rajpurkar, P. etal. For the exploration stage, the weibull distribution has been applied rather than Brownian to bost the performance of the predator in stage 2 and the prey velocity in stage 1 based on the following formula: Where k, and \(\zeta\) are the scale and shape parameters. Civit-Masot et al. & SHAH, S. S.H. The diagnostic evaluation of convolutional neural network (cnn) for the assessment of chest x-ray of patients infected with covid-19. The evaluation confirmed that FPA based FS enhanced classification accuracy. where \(ni_{j}\) is the importance of node j, while \(w_{j}\) refers to the weighted number of samples reaches the node j, also \(C_{j}\) determines the impurity value of node j. left(j) and right(j) are the child nodes from the left split and the right split on node j, respectively. Inspired by this concept, Faramarzi et al.37 developed the MPA algorithm by considering both of a predator a prey as solutions. A deep feature learning model for pneumonia detection applying a combination of mRMR feature selection and machine learning models. The 1360 revised papers presented in these proceedings were carefully reviewed and selected from . Support Syst. Using X-ray images we can train a machine learning classifier to detect COVID-19 using Keras and TensorFlow. In this paper, we used TPUs for powerful computation, which is more appropriate for CNN. It is also noted that both datasets contain a small number of positive COVID-19 images, and up to our knowledge, there is no other sufficient available published dataset for COVID-19. To obtain Design incremental data augmentation strategy for COVID-19 CT data. PubMedGoogle Scholar. a cough chills difficulty breathing tiredness body aches headaches a new loss of taste or smell a sore throat nausea and vomiting diarrhea Not everyone with COVID-19 develops all of these. Abbas, A., Abdelsamea, M.M. & Gaber, M.M. Classification of covid-19 in chest x-ray images using detrac deep convolutional neural network. They also used the SVM to classify lung CT images. As seen in Fig. Moreover, from Table4, it can be seen that the proposed FO-MPA provides better results in terms of F-Score, as it has the highest value in datatset1 and datatset2 which are 0.9821 and 0.99079, respectively. The proposed cascaded system is proposed to segment the lung, detect, localize, and quantify COVID-19 infections from computed tomography images, which can reliably localize infections of various shapes and sizes, especially small infection regions, which are rarely considered in recent studies. where \(fi_{i}\) represents the importance of feature I, while \(ni_{j}\) refers to the importance of node j. Provided by the Springer Nature SharedIt content-sharing initiative, Environmental Science and Pollution Research (2023), Archives of Computational Methods in Engineering (2023), Arabian Journal for Science and Engineering (2023). A.T.S. 152, 113377 (2020). 132, 8198 (2018). used a dark Covid-19 network for multiple classification experiments on Covid-19 with an accuracy of 87% [ 23 ]. These datasets contain hundreds of frontal view X-rays and considered the largest public resource for COVID-19 image data. Faramarzi et al.37 divided the agents for two halves and formulated Eqs. The data was collected mainly from retrospective cohorts of pediatric patients from Guangzhou Women and Childrens medical center. Chollet, F. Keras, a python deep learning library. arXiv preprint arXiv:2003.11597 (2020). Heidari, A. Lilang Zheng, Jiaxuan Fang, Xiaorun Tang, Hanzhang Li, Jiaxin Fan, Tianyi Wang, Rui Zhou, Zhaoyan Yan: PVT-COV19D: COVID-19 Detection Through Medical Image Classification Based on Pyramid Vision Transformer. 6 (left), for dataset 1, it can be seen that our proposed FO-MPA approach outperforms other CNN models like VGGNet, Xception, Inception, Mobilenet, Nasnet, and Resnet. In our experiment, we randomly split the data into 70%, 10%, and 20% for training, validation, and testing sets, respectively. M.A.E. The combination of SA and GA showed better performances than the original SA and GA. Narayanan et al.33 proposed a fuzzy particle swarm optimization (PSO) as an FS method to enhance the classification of CT images of emphysema. is applied before larger sized kernels are applied to reduce the dimension of the channels, which accordingly, reduces the computation cost. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate. 198 (Elsevier, Amsterdam, 1998). Deep residual learning for image recognition. Robertas Damasevicius. Two real datasets about COVID-19 patients are studied in this paper. chest X-ray images into three classes of COVID-19, normal chest X-ray and other lung diseases. Sci. Background The large volume and suboptimal image quality of portable chest X-rays (CXRs) as a result of the COVID-19 pandemic could post significant challenges for radiologists and frontline physicians. Med. \(Fit_i\) denotes a fitness function value. The whale optimization algorithm. 11314, 113142S (International Society for Optics and Photonics, 2020). Eq. While the second half of the agents perform the following equations. The algorithm combines the assessment of image quality, digital image processing and deep learning for segmentation of the lung tissues and their classification. Bibliographic details on CECT: Controllable Ensemble CNN and Transformer for COVID-19 image classification by capturing both local and global image features. . The symbol \(R_B\) refers to Brownian motion. Convolutional neural networks were implemented in Python 3 under Google Colaboratory46, commonly referred to as Google Colab, which is a research project for prototyping machine learning models on powerful hardware options such as GPUs and TPUs. So, transfer learning is applied by transferring weights that were already learned and reserved into the structure of the pre-trained model, such as Inception, in this paper. Then, using an enhanced version of Marine Predators Algorithm to select only relevant features. Figure5, shows that FO-MPA shows an efficient and faster convergence than the other optimization algorithms on both datasets. Li et al.34 proposed a self-adaptive bat algorithm (BA) to address two problems in lung X-ray images, rebalancing, and feature selection. The next process is to compute the performance of each solution using fitness value and determine which one is the best solution. Inf. Chowdhury, M.E. etal. Eng. J. Med. & Zhu, Y. Kernel feature selection to fuse multi-spectral mri images for brain tumor segmentation. Propose similarity regularization for improving C. Whereas, FO-MPA, MPA, HGSO, and WOA showed similar STD results. In Inception, there are different sizes scales convolutions (conv. However, it was clear that VGG19 and MobileNet achieved the best performance over other CNNs. To segment brain tissues from MRI images, Kong et al.17 proposed an FS method using two methods, called a discriminative clustering method and the information theoretic discriminative segmentation. & Cmert, Z. In14, the authors proposed an FS method based on a convolutional neural network (CNN) to detect pneumonia from lung X-ray images. EMRes-50 model . In this paper, we proposed a novel COVID-19 X-ray classification approach, which combines a CNN as a sufficient tool to extract features from COVID-19 X-ray images. Adv. implemented the FO-MPA swarm optimization and prepared the related figures and manuscript text. MPA simulates the main aim for most creatures that is searching for their foods, where a predator contiguously searches for food as well as the prey. Stage 1: After the initialization, the exploration phase is implemented to discover the search space. where CF is the parameter that controls the step size of movement for the predator. It classifies the chest X-ray images into three categories that includes Covid-19, Pneumonia and normal. 92, 103662. https://doi.org/10.1016/j.engappai.2020.103662 (2020). While, MPA, BPSO, SCA, and SGA obtained almost the same accuracy, followed by both bGWO, WOA, and SMA. The results are the best achieved compared to other CNN architectures and all published works in the same datasets. SMA is on the second place, While HGSO, SCA, and HHO came in the third to fifth place, respectively. The evaluation showed that the RDFS improved SVM robustness against reconstruction kernel and slice thickness. Besides, the used statistical operations improve the performance of the FO-MPA algorithm because it supports the algorithm in selecting only the most important and relevant features. To evaluate the performance of the proposed model, we computed the average of both best values and the worst values (Max) as well as STD and computational time for selecting features. Its structure is designed based on experts' knowledge and real medical process. The parameters of each algorithm are set according to the default values. Med. The proposed IMF approach is employed to select only relevant and eliminate unnecessary features. The HGSO also was ranked last. The 30-volume set, comprising the LNCS books 12346 until 12375, constitutes the refereed proceedings of the 16th European Conference on Computer Vision, ECCV 2020, which was planned to be held in Glasgow, UK, during August 23-28, 2020. Chong, D. Y. et al. Whereas, the slowest and the insufficient convergences were reported by both SGA and WOA in Dataset 1 and by SGA in Dataset 2. Podlubny, I. Also, they require a lot of computational resources (memory & storage) for building & training. Covid-19 dataset. While55 used different CNN structures. While the second dataset, dataset 2 was collected by a team of researchers from Qatar University in Qatar and the University of Dhaka in Bangladesh along with collaborators from Pakistan and Malaysia medical doctors44. However, it has some limitations that affect its quality. The combination of Conv. In 2018 IEEE International Symposium on Circuits and Systems (ISCAS), 15 (IEEE, 2018). COVID-19 tests are currently hard to come by there are simply not enough of them and they cannot be manufactured fast enough, which is causing panic. The convergence behaviour of FO-MPA was evaluated over 25 independent runs and compared to other algorithms, where the x-axis and the y-axis represent the iterations and the fitness value, respectively. Havaei, M. et al. We are hiring! The experimental results and comparisons with other works are presented inResults and discussion section, while they are discussed in Discussion section Finally, the conclusion is described in Conclusion section. Stage 2 has been executed in the second third of the total number of iterations when \(\frac{1}{3}t_{max}< t< \frac{2}{3}t_{max}\). Multimedia Tools Appl. Huang, P. et al. Google Scholar. Chollet, F. Xception: Deep learning with depthwise separable convolutions. A combination of fractional-order and marine predators algorithm (FO-MPA) is considered an integration among a robust tool in mathematics named fractional-order calculus (FO). (1): where \(O_k\) and \(E_k\) refer to the actual and the expected feature value, respectively. Memory FC prospective concept (left) and weibull distribution (right). Sign up for the Nature Briefing newsletter what matters in science, free to your inbox daily. For fair comparison, each algorithms was performed (run) 25 times to produce statistically stable results.The results are listed in Tables3 and4.