Chest X-ray Classification for the Detection of COVID-19 Using Deep Learning Techniques

Abstract

Recent technological developments pave the path for deep learning-based techniques to be used in almost every domain of life. The precision of deep learning techniques make it possible for these to be used in the medical field for the classification and detection of various diseases. Recently, the coronavirus (COVID-19) pandemic has put a lot of pressure on the health system all around the world. The diagnosis of COVID-19 is possible by PCR testing and medical imagining. Since COVID-19 is highly contagious, diagnosis using chest X-ray is considered safe in various situations. In this study, a deep learning-based technique is proposed to classify COVID-19 infection from other non-COVID-19 infections. To classify COVID-19, three different pre-trained models named EfficientNetB1, NasNetMobile and MobileNetV2 are used. The augmented dataset is used for training deep learning models while two different training strategies have been used for classification. In this study, not only are the deep learning model fine-tuned but also the hyperparameters are fine-tuned, which significantly improves the performance of the fine-tuned deep learning models. Moreover, the classification head is regularized to improve the performance. For the evaluation of the proposed techniques, several performance parameters are used to gauge the performance. EfficientNetB1 with regularized classification head outperforms the other models. The proposed technique successfully classifies four classes that include COVID-19, viral pneumonia, lung opacity, and normal, with an accuracy of 96.13%. The proposed technique shows superiority in terms of accuracy when compared with recent techniques present in the literature.

COVID-19 classification using chest X-ray images: A framework of CNN-LSTM and improved max value moth flame optimization

“…They used ChestXImageNet CNN model for the classification purpose and tested on the open-access dataset that consisted of both binary classes and multiclass and achieved accuracies of 100 and 100%, respectively. Khan et al ( 32 ) described a deep learning technique in which they used three pre-trained models named EfficientNet B1, NasNetMobile, and MobileNetV2. Before training deep models, they performed data augmentation.…”

Multiclass Classification for Detection of COVID-19 Infection in Chest X-Rays Using CNN

“…On the other hand, numerous studies merged the two different concepts and were focused on distinguishing between pneumonia infection and COVID-19 infection since that can be a challenging task for radiologists. e study by Khan et al [21] discussed the capability of different deep learning models in different training techniques in the proper differentiation between COVID-19 infection and viral pneumonia infection. e authors tried to gather a large dataset of chest X-Ray images from several sources such as Kaggle, RSNA, GitHub, and others, which comprise images of COVID-19 patients, normal patients, patients with lung opacity, and pneumonia patients.…”

“…As a matter of fact, there exist several studies that employ CNN models to identify the presence of pneumonia infection, as well as COVID-19 infections. Such models are the VGGs (16 and 19), ResNet, Xception, and DenseNet [21]. ese models are either developed from scratch or modi ed and ne-tuned in order to Computational Intelligence and Neuroscience produce accurate results for the detection of COVID-19 infections in lung X-Rays.…”

Deep Learning-Based Defect Prediction for Mobile Applications

“…Machine learning uses various algorithms to analyze and learn data then make predictions and take decisions for future. Nowadays machine learning is a well-known technique and used in different areas, such as healthcare [7][8][9][10], industrial applications [11], banking [12], telecommunication [13,14], software development [15], etc. Machine learning is also used for regression tasks and defective classes (i.e., binary class classification).…”

“…With a convolutional layer, this transform is a convolutional operation. Recall that Tensors are N-dimensional arrays that we build up to: Scaler-3, Vector- [3][4][5], Matrix-( [3,4], [5,6], [7,8]), Tensor-(([1,2], [3,4]), ( [5,6], [7,8])). Tensors make it very convenient to feed in sets of images into our model-(I, H, W, C).…”