Coronavirus is a large family of viruses that can cause a human being to develop a serious illness. The first reported major epidemic was Severe Acute Respiratory Syndrome (SARS) [1] in 2003, while the second severe outbreak of Middle East Respiratory Syndrome (MERS) [2, 15] in Saudi Arabia began in 2012. The latest outbreak of coronavirus disease was announced in late December 2019. This new virus is very infectious and has spread globally rapidly. On January 30, 2020, as it had spread to 18 countries, the World Health Organization (WHO) declared this outbreak a Public Health Emergency of International Concern (PHEIC) [3]. This virus was named 'COVID-19' by the World Health Organization on February 11, 2020 [4]. As of September 2020, the WHO reported that 31.3 million confirmed cases and over 965 thousand deaths have been registered in 213 countries.
Figure 1 shows confirmed cases of global COVID-19 as of September 2020. The disease has spread rapidly around the globe since it was first identified and has become an international concern. An analysis performed by Jiang et al. [5] found that COVID-19's death rate is 4.5% worldwide. In the age group of 70–79 years, the death rate for patients is 8.0%, while 14.8% for patients over 80 years. Patients over 50 years of age with chronic diseases are at the highest risk and it is critically important to find a way to detect illness before getting into serious conditions.
As the COVID-19 epidemic has become a global pandemic, real-time analysis of epidemiological data is required to prepare society for better disease response plans. COVID-19 belongs to the SARS-CoV and MERS-CoV families, where symptoms of the common cold to severe respiratory diseases, causing trouble breathing, exhaustion, fever, and dry cough, start at the initial level. Real-time Reverse Transcription-Polymerase Chain Reaction or also known as RT-PCR is the latest approach used to make a definitive diagnosis of SARS-CoV-2 infection [6]. PCR testing was found to have a high specificity (Sp) but rather low sensitivity (Sn) with a reported positive rate of only 38%~57%. In addition to etiological laboratory confirmation, Clinical Features (CFs) and chest Computed Tomography (CT) imaging include other key diagnostic elements that could facilitate the identification of COVID-19 pneumonia.
Early identification of patients with COVID-19 pneumonia for timely treatment is crucial to contain the spread, particularly in epidemic regions. According to information shared by the Radiological Society of North America (RSNA), X-ray and CT images of a Chinese person dead by COVID-19 showed the damages done to the human lungs. A research team led by Lucas [7] at The University of São Paulo demonstrated the chest imaging finding of COVID-19 on different modalities such as Chest Radiography (CXR), Computed Tomography (CT), and Ultrasonography. According to them, chest CT is the main imaging method used in the assessment of COVID-19 pneumonia. A structured chest CT report standardizes imaging results and optimizes contact with the prescribing physician, making it a valuable tool in the pandemic scenario. In addition, the CT imaging properties of infected lungs include Ground-Glass Opacity (GGO) and severity-correlated consolidation. In Hubei Province, China, CT scans have been used widely and on presentation in an attempt to rapidly detect, isolate, and control the spread of the epidemic.
Many studies have documented a high degree of chest CT sensitivity in the diagnosis of COVID-19 pneumonia. Previous studies have shown that the most common CT characteristic of COVID-19 pneumonia is the presence of multifocal Ground-Glass Opacity (GGOs). Figure 2 displays the CT scan image of a COVID-19 patient. Arrowheads reveal the recognizable hazy area on the outer edges of the lungs. As per the description, Ground-Glass Opacities refer to the distorted presence of the lungs in imaging experiments, almost as though parts were obscured by Ground-Glass. This may be due to the fluid filling of pulmonary airspace, the collapsing of airspace, or both. This is a trend that can be seen while the lungs are sick. Regular lung’s CT scans look black; rare chest CTs with GGOs reveal lighter colored or gray spots. Consolidation refers to the saturation of fluids or other inflammatory products in pulmonary airspace. Pleural effusion refers to abnormal fluids that form in the spaces surrounding the lungs.
PCR tests are taking time to diagnose COVID-19 patients and the test results appear to be of low accuracy compared to CT scan tests. However, CT scans can be used as a simple and quick way of categorizing patients into "probably positive" and "probably negative" cohorts. As the hospital admission rate of COVID-19 patients increases, the PCR test is not appropriate. Nowadays, tools for the identification of COVID-19 patients with high efficacy and accuracy are essential. Due to the poor contrast of infection regions of CT images and the large differences in both the shape and location of the lesions in different patients, the delineation of the infection regions in CT scans in the chest is very difficult for the physician. Image processing techniques may open new pathways to describe the state of the lungs using CT scans. The objective of this study is to develop a deep learning algorithm to detect COVID-19 patients using CT chest scan images and validate results for both COVID-19 positive and healthy test subjects.