Diagnosing COVID-19 pneumonia from x-ray and CT images using deep learning and transfer learning algorithms

Abstract

The novel coronavirus 2019 first appeared in Wuhan province of China and spread quickly around the globe and became a pandemic. The gold standard for confirming COVID-19 infection is through Reverse Transcription-Polymerase Chain Reaction (RT-PCR) assay. The lack of sufficient RT-PCR testing capacity, false negative results of RT-PCR, time to get back the results and other logistical constraints enabled the epidemic to continue to spread albeit interventions like regional or complete country lockdowns. Therefore, chest radiographs such as CT and X-ray can be used to supplement PCR in combating the virus from spreading. In this work, we focus on proposing a deep learning tool that can be used by radiologists or healthcare professionals to diagnose COVID-19 cases in a quick and accurate manner. However, the lack of a publicly available dataset of X-ray and CT images makes the design of such AI tools a challenging task. To this end, this study aims to build a comprehensive dataset of X-rays and CT scan images from multiple sources as well as provides a simple but an effective COVID-19 detection technique using deep learning and transfer learning algorithms. In this vein, a simple convolution neural network (CNN) and modified pre-trained AlexNet model are applied on the prepared X-rays and CT scan images. The result of the experiments shows that the utilized models can provide accuracy up to 98% via pre-trained network and 94.1% accuracy by using the modified CNN.

The Promise of AI in Detection, Diagnosis, and Epidemiology for Combating COVID-19: Beyond the Hype

“…There are many ways in which AI can help in the fight against the COVID-19 pandemic. For example, AI could be used to track the spread of the virus (Al-Qaness et al, 2020;Bandyopadhyay and Dutta, 2020;Carrillo-Larco and Castillo-Cara, 2020;Hu et al, 2020;Jana and Bhaumik, 2020;Huang et al, 2020b;Kavadi et al, 2020;Sameni, 2020), identify patients with high mortality risk (Jiang et al, 2020a;Qi et al, 2020;Xu et al, 2020b;Yan et al, 2020a), diagnose and screen a population for COVID-19 (Ghoshal and Tucker, 2020;Hassanien et al, 2020;Hemdan et al, 2020;Jin et al, 2020b;Maghdid et al, 2020a;Narin et al, 2020;Wang et al, 2020c,e;Wu et al, 2020a;Zhang et al, 2021;Xu et al, 2020c), or reduce the time for diagnosis (Vaishya et al, 2020a). Many of the AI techniques currently being deployed in the battle already existed prior to the pandemic.…”

Transfer deep learning approach for detecting coronavirus disease in X-ray images

“…Maghdid et al [19] presented the idea of proposing AI tools for COVID-19 diagnosis as well as performing deep learning system using CT and x-ray images. Similarly, Xu et al [20] studied the possibility of proposing deep learning approaches to be used as a diagnostic system to predict COVID-19 or other pneumonia using CT scans.…”

“… True Positives (TP): can be defined as the cases in which the predicted case diagnosed as COVID- 19 and the actual diagnose is COVID-19.  True Negatives (TN): can be defined as the cases in which the predicted case diagnosed as non-COVID-19 and the actual case diagnosed as nonCOVID.…”

“… True Negatives (TN): can be defined as the cases in which the predicted case diagnosed as non-COVID-19 and the actual case diagnosed as nonCOVID.  False Positives (FP): can be defined as the cases in which the predicted case diagnosed as COVID- 19 whereas the actual case diagnosed as nonCOVID.  False Negatives (FN): can be defined as the cases in which the predicted case diagnosed as non-COVID-19 where as the actual case diagnosed as COVID-19.…”

A Deep Learning Ensemble Approach for Automated COVID-19 Detection from Chest CT Images

“…In recent years, many research groups have tried to address the need for automated COVID-19 detection by proposing machine learning approaches that are based on clinical neuroimaging data. Although there are many studies that make use of CXR [16][17][18] or both image types (CXR and CT) [19,20], we only reported studies that make use of chest CT images, because these images are more accurate in COVID-19 diagnosis [12]. Shan et al [21] proposed a deep learning-based segmentation system for quantitative infection assessment.…”