ABSTRACT
The COVID-19 disease is a threat to public health around theworld. Early diagnosis and detection will be critical factors in preventing the spread of COVID-19. Computed tomography has a significant role in COVID-19 detection because it gives both fast and best results. Hence it is very significant to develop an accurate and rapid computer-assisted tool for helping clinical experts to identify COVID-19 patients from CT scan images. The project's main objective is to develop an artificial intelligence-assisted tool for predicting the severity of COVID-19 with the help of CT scan images. We introduce a new dataset that contains 47,144 CT scan images from 292 normal persons and 14,346 images from 92 patients with COVID-19 infections. In the first stage, the system runs our proposed image processing algorithm that analyses the view of the lung to discard those CT images inside the lung that are not properly visible. This action helps to reduce the processing time and false detection. Then those chosen images from the CT selection algorithm will be fed to the ResNet50V2 model, so the model becomes able to investigate different resolutions of the image and does not lose the data of small objects. Apart from 152 patients,47 patients have been detected with COVID-19, and 105 patients have been detected as Normal. It shows that the model obtained 97.89% correctness overall and 95.45% along with class with COVID-2019 sensitivity.
ABSTRACT
Background: Coronavirus disease 2019 (COVID-19) is associated with microvascular dysfunction. Non-invasive thermal imaging can hypothetically detect changes in perfusion, inflammation and vascular injury. We sought to develop a new point-of-care, non-contact thermal imaging tool to detect COVID-19 by microvascular dysfunction, based on image processing algorithms and machine learning analysis. Materials and methods: We captured thermal images of the back of 101 individuals, with (n=62) and without (n=39) COVID-19, using a portable thermal camera that connects directly to smartphones. We developed new image processing algorithms that automatically extract multiple texture and shape features of the thermal images (Figure 1A). We then evaluated the ability of our thermal features to detect COVID-19 and systemic changes of heat distribution associated with microvascular disease. We also assessed correlations between thermal imaging to conventional biomarkers and chest X-ray (CXR). Results: Our novel image processing algorithms achieved up to 92% sensitivity in detecting COVID-19 with an area under the curve of 0.85 (95% CI: 0.78, 0.93;p<0.01). Systemic alterations in blood flow associated with vascular disease were observed across the entire back. Thermal imaging scores were inversely correlated with clinical variables associated with COVID-19 disease progression, including blood oxygen saturation, C-reactive protein, and D-dimer. The thermal imaging findings were not correlated with the results of CXR. Conclusions: We show, for the first time, that a hand-held thermal imaging device can be used to detect COVID-19. Non-invasive thermal imaging could be used to screen for COVID-19 in out-of-hospital settings, especially in low-income regions with limited imaging resources. Moreover, thermal imaging might detect micro-angiopathies and endothelial dysfunction in patients with COVID-19 and could possibly improve risk stratification of infected individuals (Figure 1B).