The Detection of COVID-19 in CT Medical Images: A Deep Learning Approach

Abstract

The COVID-19 coronavirus is one of the latest viruses that hit the earth in the new century. It was declared as a pandemic by the World Health Organization in 2020. In this chapter, a model for the detection of COVID-19 virus from CT chest medical images will be presented. The proposed model is based on Generative Adversarial Networks (GAN), and a fine-tuned deep transfer learning model. GAN is used to generate more images from the available dataset. While deep transfer models are used to classify the COVID-19 virus from the normal class. The original dataset consists of 746 images. The is divided into two parts; 90% for the training and validation phase, while 10% for the testing phase. The 90% then is divided into 80% percent for the training and 20% percent for the validation after using GAN as image augmenter. The proposed GAN architecture raises the number of images in the training and validation phase to be 10 times larger than the original dataset. The deep transfer models which are selected for experimental trials are Resnet50, Shufflenet, and Mobilenet. They were selected as they include a medium number of layers on their architectures if they are compared with large deep transfer models such as DenseNet, and Inception-ResNet. This will reflect on the performance of the proposed model in terms of reducing training time, memory and CPU usage. The

Combating COVID-19 Using Generative Adversarial Networks and Artificial Intelligence for Medical Images: Scoping Review

“…As shown in Table 2 , the included studies have reported 5 different tasks being addressed: augmentation (data augmentation), diagnosis of COVID-19, prognosis, segmentation (to identify the lung region), and diagnosis of lung diseases. As the diagnosis of COVID-19 using medical imaging has been a priority since the pandemic started, 39 (68%) of 57 studies reported the diagnosis of COVID-19 as the main focus of their work [ 19 - 21 , 23 - 33 , 35 - 37 , 39 , 41 , 42 , 44 , 46 , 50 , 52 , 53 , 55 , 56 , 58 - 60 , 63 - 69 , 71 , 72 ]. In addition, 9 (16%) studies reported data augmentation as the main task addressed in the work [ 18 , 43 , 45 , 49 , 54 , 61 , 62 ], 1 (2%) study reported prognosis of COVID-19 [ 22 ], 3 (5%) studies reported segmentation of lungs [ 34 , 51 , 57 ], and 1 (2%) study reported diagnosis of multiple lung diseases [ 47 ].…”

“…Specifically, the use of X-ray images dominated the studies. In total, 29 (51%) studies used X-ray images of lungs [ 20 , 21 , 25 , 27 - 29 , 31 , 32 , 35 , 37 , 40 - 43 , 45 , 50 , 52 , 54 , 56 , 57 , 59 , 60 , 62 , 64 , 65 , 67 , 70 , 73 , 74 ], while 21 (37%) studies used CT images [ 18 , 19 , 22 - 24 , 26 , 30 , 33 , 34 , 36 , 38 , 48 , 49 , 51 , 53 , 55 , 58 , 61 , 63 , 66 , 71 ], and 6 (11%) studies reported the use of both X-ray and CT images [ 39 , 44 , 46 , 47 , 68 , 72 ]. Only 1 (2%) study used ultrasound images for COVID-19 diagnosis [ 69 ], which shows that ultrasound is not a popular imaging modality for training GANs and other deep learning models for COVID-19 detection (also see Figure 4 ).…”

“…Generally, the popular metrics for evaluating the diagnosis and classification performances of neural networks are accuracy, precision, recall, dice score, and area under the receiver operating characteristic curve (AUROC). To evaluate the performance of neural networks for diagnosis of COVID-19, 38 (67%) of the 57 studies used accuracy, along with metrics such as precision, recall, and dice score [ 21 , 23 - 28 , 31 - 34 , 36 , 38 , 40 , 43 - 48 , 52 , 53 , 55 , 56 , 58 - 60 , 63 - 72 , 74 ]. Around one-fourth of the studies (n=18, 32%) used sensitivity and specificity.…”

Survey on using deep learning to detection COVID-19 disease

“…The results obtained are 96 % accuracy for testing, 95 % sensitivity and 96 % accuracy. and some researchers used the GAN method such as Khalifa et al [43](2020) model proposed to consist of three primary blocks and binary classification. Since the dataset is small, the first block used GAN.…”

Design and Analysis of a Deep Learning Ensemble Framework Model for the Detection of COVID-19 and Pneumonia Using Large-Scale CT Scan and X-ray Image Datasets

“…Transfer learning can be performed in three ways [ 16 , 17 , 18 , 19 , 20 ] as follows: shallow tuning adjusts individuals from the previous classification layer to novel problems while leaving the limitations of the remaining levels untrained; the deep tune function is used to retrain the variables that were before the network from end to end; fine tuning intends to prepare many layers after layer and gradually adjust to learning variables until a critical performance is obtained. Knowledge transfer in detecting X-ray images through an impressively executed fine-tuning procedure.…”