volume10, Articlenumber:15364 (2020) Med. Methods: We employed a public dataset acquired from 20 COVID-19 patients, which . Havaei, M. et al. Luz, E., Silva, P.L., Silva, R. & Moreira, G. Towards an efficient deep learning model for covid-19 patterns detection in x-ray images. Our dataset consisting of 60 chest CT images of COVID-19 and non-COVID-19 patients was pre-processed and segmented using a hybrid watershed and fuzzy c-means algorithm. Negative COVID-19 images were collected from another Chest X-ray Kaggle published dataset43. where \(REfi_{i}\) represents the importance of feature i that were calculated from all trees, where \(normfi_{ij}\) is the normalized feature importance for feature i in tree j, also T is the total number of trees. The main purpose of Conv. 25, 3340 (2015). Google Scholar. Both the model uses Lungs CT Scan images to classify the covid-19. The test accuracy obtained for the model was 98%. In 2019 26th National and 4th International Iranian Conference on Biomedical Engineering (ICBME), 194198 (IEEE, 2019). 4b, FO-MPA algorithm selected successfully fewer features than other algorithms, as it selected 130 and 86 features from Dataset 1 and Dataset 2, respectively. We have used RMSprop optimizer for weight updates, cross entropy loss function and selected learning rate as 0.0001. Therefore, several pre-trained models have won many international image classification competitions such as VGGNet24, Resnet25, Nasnet26, Mobilenet27, Inception28 and Xception29. HIGHLIGHTS who: Qinghua Xie and colleagues from the Te Afliated Changsha Central Hospital, Hengyang Medical School, University of South China, Changsha, Hunan, China have published the Article: Automatic Segmentation and Classification for Antinuclear Antibody Images Based on Deep Learning, in the Journal: Computational Intelligence and Neuroscience of 14/08/2022 what: Terefore, the authors . Hence, the FC memory is applied during updating the prey locating in the second step of the algorithm to enhance the exploitation stage. So some statistical operations have been added to exclude irrelevant and noisy features, and by making it more computationally efficient and stable, they are summarized as follows: Chi-square is applied to remove the features which have a high correlation values by computing the dependence between them. Therefore, a feature selection technique can be applied to perform this task by removing those irrelevant features. The parameters of each algorithm are set according to the default values. The proposed IMF approach is employed to select only relevant and eliminate unnecessary features. The proposed CNN architecture for Task 2 consists of 14 weighted layers, in which there are three convolutional layers and one fully connected layer, as shown in Fig. In this work, we have used four transfer learning models, VGG16, InceptionV3, ResNet50, and DenseNet121 for the classification tasks. A deep feature learning model for pneumonia detection applying a combination of mRMR feature selection and machine learning models. Furthermore, deep learning using CNN is considered one of the best choices in medical imaging applications20, especially classification. Narayanan, S.J., Soundrapandiyan, R., Perumal, B. Simonyan, K. & Zisserman, A. Wish you all a very happy new year ! The algorithm combines the assessment of image quality, digital image processing and deep learning for segmentation of the lung tissues and their classification. To further analyze the proposed algorithm, we evaluate the selected features by FO-MPA by performing classification. So, there might be sometimes some conflict issues regarding the features vector file types or issues related to storage capacity and file transferring. The second one is based on Matlab, where the feature selection part (FO-MPA algorithm) was performed. IEEE Trans. Also, they require a lot of computational resources (memory & storage) for building & training. The prey follows Weibull distribution during discovering the search space to detect potential locations of its food. 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). PubMed Bisong, E. Building Machine Learning and Deep Learning Models on Google Cloud Platform (Springer, Berlin, 2019). Ozturk, T. et al. The model was developed using Keras library47 with Tensorflow backend48. In our experiment, we randomly split the data into 70%, 10%, and 20% for training, validation, and testing sets, respectively. Accordingly, that reflects on efficient usage of memory, and less resource consumption. Authors https://www.sirm.org/category/senza-categoria/covid-19/ (2020). For the image features that led to categorization, there were varied levels of agreement in the interobserver and intraobserver components that . Based on54, the later step reduces the memory requirements, and improve the efficiency of the framework. Efficient classification of white blood cell leukemia with improved swarm optimization of deep features. In ancient India, according to Aelian, it was . CAS Memory FC prospective concept (left) and weibull distribution (right). Kharrat, A. Harikumar et al.18 proposed an FS method based on wavelets to classify normality or abnormality of different types of medical images, such as CT, MRI, ultrasound, and mammographic images. Biol. In the meantime, to ensure continued support, we are displaying the site without styles For Dataset 2, FO-MPA showed acceptable (not the best) performance, as it achieved slightly similar results to the first and second ranked algorithm (i.e., MPA and SMA) on mean, best, max, and STD measures. Our results indicate that the VGG16 method outperforms . Med. Donahue, J. et al. These datasets contain hundreds of frontal view X-rays and considered the largest public resource for COVID-19 image data. Eng. The conference was held virtually due to the COVID-19 pandemic. Al-qaness, M. A., Ewees, A. 11314, 113142S (International Society for Optics and Photonics, 2020). Sahlol, A. T., Kollmannsberger, P. & Ewees, A. HIGHLIGHTS who: Yuan Jian and Qin Xiao from the Fukuoka University, Japan have published the Article: Research and Application of Fine-Grained Image Classification Based on Small Collar Dataset, in the Journal: (JOURNAL) what: MC-Loss drills down on the channels to effectively navigate the model, focusing on different distinguishing regions and highlighting diverse features. In this paper, we used two different datasets. However, it has some limitations that affect its quality. We do not present a usable clinical tool for COVID-19 diagnosis, but offer a new, efficient approach to optimize deep learning-based architectures for medical image classification purposes. The proposed approach was evaluated on two public COVID-19 X-ray datasets which achieves both high performance and reduction of computational complexity. 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. Google Scholar. Robustness-driven feature selection in classification of fibrotic interstitial lung disease patterns in computed tomography using 3d texture features. arXiv preprint arXiv:2003.11597 (2020). J. \(Fit_i\) denotes a fitness function value. Zhang et al.16 proposed a kernel feature selection method to segment brain tumors from MRI images. In Proceedings of the IEEE Conference on computer vision and pattern recognition workshops, 806813 (2014). Thereafter, the FO-MPA parameters are applied to update the solutions of the current population. The data was collected mainly from retrospective cohorts of pediatric patients from Guangzhou Women and Childrens medical center. Corona Virus lung infected X-Ray Images accessible by Kaggle a complete 590 images, which classified in 2 classes: typical and Covid-19. Then the best solutions are reached which determine the optimal/relevant features that should be used to address the desired output via several performance measures. & Cmert, Z. Civit-Masot et al. In 2018 IEEE International Symposium on Circuits and Systems (ISCAS), 15 (IEEE, 2018). In general, feature selection (FS) methods are widely employed in various applications of medical imaging applications. Math. & Wang, W. Medical image segmentation using fruit fly optimization and density peaks clustering. Besides, the binary classification between two classes of COVID-19 and normal chest X-ray is proposed. Finally, the predator follows the levy flight distribution to exploit its prey location. (1): where \(O_k\) and \(E_k\) refer to the actual and the expected feature value, respectively. Therefore, reducing the size of the feature from about 51 K as extracted by deep neural networks (Inception) to be 128.5 and 86 in dataset 1 and dataset 2, respectively, after applying FO-MPA algorithm while increasing the general performance can be considered as a good achievement as a machine learning goal. The Shearlet transform FS method showed better performances compared to several FS methods. Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. Appl. How- individual class performance. The HGSO also was ranked last. PubMed The symbol \(R_B\) refers to Brownian motion. Comput. where r is the run numbers. }, \end{aligned}$$, $$\begin{aligned} D^{\delta }[U(t)]=\frac{1}{T^\delta }\sum _{k=0}^{m} \frac{(-1)^k\Gamma (\delta +1)U(t-kT)}{\Gamma (k+1)\Gamma (\delta -k+1)} \end{aligned}$$, $$\begin{aligned} D^1[U(t)]=U(t+1)-U(t) \end{aligned}$$, $$\begin{aligned} U=Lower+rand_1\times (Upper - Lower ) \end{aligned}$$, $$\begin{aligned} Elite=\left[ \begin{array}{cccc} U_{11}^1&{}U_{12}^1&{}\ldots &{}U_{1d}^1\\ U_{21}^1&{}U_{22}^1&{}\ldots &{}U_{2d}^1\\ \ldots &{}\ldots &{}\ldots &{}\ldots \\ U_{n1}^1&{}U_{n2}^1&{}\ldots &{}U_{nd}^1\\ \end{array}\right] , \, U=\left[ \begin{array}{cccc} U_{11}&{}U_{12}&{}\ldots &{}U_{1d}\\ U_{21}&{}U_{22}&{}\ldots &{}U_{2d}\\ \ldots &{}\ldots &{}\ldots &{}\ldots \\ U_{n1}&{}U_{n2}&{}\ldots &{}U_{nd}\\ \end{array}\right] , \, \end{aligned}$$, $$\begin{aligned} S_i&= {} R_B \bigotimes (Elite_i-R_B\bigotimes U_i), i=1,2,\ldots ,n \end{aligned}$$, $$\begin{aligned} U_i&= {} U_i+P.R\bigotimes S_i \end{aligned}$$, \(\frac{1}{3}t_{max}< t< \frac{2}{3}t_{max}\), $$\begin{aligned} S_i&= {} R_L \bigotimes (Elite_i-R_L\bigotimes U_i), i=1,2,\ldots ,n/2 \end{aligned}$$, $$\begin{aligned} S_i&= {} R_B \bigotimes (R_B \bigotimes Elite_i- U_i), i=1,2,\ldots ,n/2 \end{aligned}$$, $$\begin{aligned} U_i&= {} Elite_i+P.CF\bigotimes S_i,\, CF= \left( 1-\frac{t}{t_{max}} \right) ^{\left(2\frac{t}{t_{max}}\right) } \end{aligned}$$, $$\begin{aligned} S_i&= {} R_L \bigotimes (R_L \bigotimes Elite_i- U_i), i=1,2,\ldots ,n \end{aligned}$$, $$\begin{aligned} U_i&= {} Elite_i+P.CF\bigotimes S_i,\, CF= \left( 1-\frac{t}{t_{max}}\right) ^{\left(2\frac{t}{t_{max}} \right) } \end{aligned}$$, $$\begin{aligned} U_i=\left\{ \begin{array}{ll} U_i+CF [U_{min}+R \bigotimes (U_{max}-U_{min})]\bigotimes W &{} r_5 < FAD \\ U_i+[FAD(1-r)+r](U_{r1}-U_{r2}) &{} r_5 > FAD\\ \end{array}\right. Use the Previous and Next buttons to navigate the slides or the slide controller buttons at the end to navigate through each slide. Harikumar, R. & Vinoth Kumar, B. (18)(19) for the second half (predator) as represented below. is applied before larger sized kernels are applied to reduce the dimension of the channels, which accordingly, reduces the computation cost. Biocybern. Huang, P. et al. Imag. Both datasets shared some characteristics regarding the collecting sources. used VGG16 to classify Covid-19 and achieved good results with an accuracy of 86% [ 22 ]. and pool layers, three fully connected layers, the last one performs classification. This dataset currently contains hundreds of frontal view X-rays and is the largest public resource for COVID-19 image and prognostic data, making it a necessary resource to develop and evaluate tools to aid in the treatment of CO VID-19. Then, applying the FO-MPA to select the relevant features from the images. Lett. A. et al. Chong, D. Y. et al. where \(R_L\) has random numbers that follow Lvy distribution. Softw. This task is achieved by FO-MPA which randomly generates a set of solutions, each of them represents a subset of potential features. The whale optimization algorithm. In this subsection, the results of FO-MPA are compared against most popular and recent feature selection algorithms, such as Whale Optimization Algorithm (WOA)49, Henry Gas Solubility optimization (HGSO)50, Sine cosine Algorithm (SCA), Slime Mould Algorithm (SMA)51, Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO)52, Harris Hawks Optimization (HHO)53, Genetic Algorithm (GA), and basic MPA. 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. In this paper, filters of size 2, besides a stride of 2 and \(2 \times 2\) as Max pool, were adopted. Cancer 48, 441446 (2012). In this paper, different Conv. Performance analysis of neural networks for classification of medical images with wavelets as a feature extractor. The name "pangolin" comes from the Malay word pengguling meaning "one who rolls up" from guling or giling "to roll"; it was used for the Sunda pangolin (Manis javanica). For example, Da Silva et al.30 used the genetic algorithm (GA) to develop feature selection methods for ranking the quality of medical images. 69, 4661 (2014). Refresh the page, check Medium 's site status, or find something interesting. Table2 shows some samples from two datasets. A.A.E. I. S. of Medical Radiology. Transmission scenarios for middle east respiratory syndrome coronavirus (mers-cov) and how to tell them apart. ADS Tree based classifier are the most popular method to calculate feature importance to improve the classification since they have high accuracy, robustness, and simple38. It can be concluded that FS methods have proven their advantages in different medical imaging applications19. We build the first Classification model using VGG16 Transfer leaning framework and second model using Deep Learning Technique Convolutional Neural Network CNN to classify and diagnose the disease and we able to achieve the best accuracy in both the model. and A.A.E. Image Anal. Also, As seen in Fig. M.A.E. Extensive evaluation experiments had been carried out with a collection of two public X-ray images datasets. CNNs are more appropriate for large datasets. 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. Radiology 295, 2223 (2020). \end{aligned} \end{aligned}$$, $$\begin{aligned} \begin{aligned} U_{i}(t+1)&= \frac{1}{1!} Since its structure consists of some parallel paths, all the paths use padding of 1 pixel to preserve the same height & width for the inputs and the outputs. 2 (left). Cite this article. Also, in12, an Fs method based on SVM was proposed to detect Alzheimers disease from SPECT images. all above stages are repeated until the termination criteria is satisfied. Fractional Differential Equations: An Introduction to Fractional Derivatives, Fdifferential Equations, to Methods of their Solution and Some of Their Applications Vol. They applied the SVM classifier with and without RDFS. In14, the authors proposed an FS method based on a convolutional neural network (CNN) to detect pneumonia from lung X-ray images. Syst. Adv. Also, because COVID-19 is a virus, distinguish COVID-19 from common viral . The proposed IMF approach successfully achieves two important targets, selecting small feature numbers with high accuracy. Dhanachandra, N. & Chanu, Y. J. Although convolutional neural networks (CNNs) is considered the current state-of-the-art image classification technique, it needs massive computational cost for deployment and training. Also, image segmentation can extract critical features, including the shape of tissues, and texture5,6. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770778 (2016). Chollet, F. Xception: Deep learning with depthwise separable convolutions. In transfer learning, a CNN which was previously trained on a large & diverse image dataset can be applied to perform a specific classification task by23. In this paper, we propose an improved hybrid classification approach for COVID-19 images by combining the strengths of CNNs (using a powerful architecture called Inception) to extract features and a swarm-based feature selection algorithm (Marine Predators Algorithm) to select the most relevant features. On January 20, 2023, Japanese Prime Minister Fumio Kishida announced that the country would be downgrading the COVID-19 classification. The evaluation confirmed that FPA based FS enhanced classification accuracy. The memory properties of Fc calculus makes it applicable to the fields that required non-locality and memory effect. In Medical Imaging 2020: Computer-Aided Diagnosis, vol. A., Fan, H. & Abd ElAziz, M. Optimization method for forecasting confirmed cases of covid-19 in china. The different proposed models will be trained with three-class balanced dataset which consists of 3000 images, 1000 images for each class. J. Med. I am passionate about leveraging the power of data to solve real-world problems. Continuing on my commitment to share small but interesting things in Google Cloud, this time I created a model for a Inception architecture is described in Fig. Currently, we witness the severe spread of the pandemic of the new Corona virus, COVID-19, which causes dangerous symptoms to humans and animals, its complications may lead to death. The largest features were selected by SMA and SGA, respectively. To survey the hypothesis accuracy of the models. Initialize solutions for the prey and predator. In Iberian Conference on Pattern Recognition and Image Analysis, 176183 (Springer, 2011). The MPA starts with the initialization phase and then passing by other three phases with respect to the rational velocity among the prey and the predator. chest X-ray images into three classes of COVID-19, normal chest X-ray and other lung diseases. Such methods might play a significant role as a computer-aided tool for image-based clinical diagnosis soon. Multimedia Tools Appl. & 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. Whereas, the slowest and the insufficient convergences were reported by both SGA and WOA in Dataset 1 and by SGA in Dataset 2. One of the best methods of detecting. (14)-(15) are implemented in the first half of the agents that represent the exploitation. <span> <h5>Background</h5> <p>The COVID19 pandemic has precipitated global apprehensions about increased fatalities and raised concerns about gaps in healthcare . 2. With the help of numerous algorithms in AI, modern COVID-19 cases can be detected and managed in a classified framework. In the last two decades, two famous types of coronaviruses SARS-CoV and MERS-CoV had been reported in 2003 and 2012, in China, and Saudi Arabia, respectively3. Scientific Reports Volume 10, Issue 1, Pages - Publisher. The focus of this study is to evaluate and examine a set of deep learning transfer learning techniques applied to chest radiograph images for the classification of COVID-19, normal (healthy), and pneumonia. They were also collected frontal and lateral view imagery and metadata such as the time since first symptoms, intensive care unit (ICU) status, survival status, intubation status, or hospital location.