A Fully Automated Deep Learning-based Network For Detecting COVID-19 from a New And Large Lung CT Scan Dataset

Abstract

<jats:p>COVID-19 is a severe global problem that has crippled many industries and killed many people around the world. One of the primary ways to decrease the casualties is the infected person's identification at the proper time. AI can play a significant role in these cases by monitoring and detecting infected persons in early-stage so that it can help many organizations. In this paper, we aim to propose a fully-automated method to detect COVID-19 from the patient's CT scan without needing a clinical technician. We introduce a new dataset that contains 48260 CT scan images from 282 normal persons and 15589 images from 95 patients with COVID-19 infection. Our proposed network takes all the CT scan image sequences of a patient as the input and determines if the patient is infected with COVID-19. At the first stage, this network runs an image processing algorithm to discard those CT images that inside the lung is not properly visible in them. This helps to reduce the number of images that shall be identified as normal or COVID-19, so it reduces the processing time. Also, running this algorithm makes the deep network at the next stage to analyze only the proper images and thus reduces false detections. At the next stage, we propose a modified version of ResNet50V2 that is enhanced by a feature pyramid network for classifying the selected CT images into COVID-19 or normal. If enough number of chosen CT scan images of a patient be identified as COVID-19, the network considers that patient, infected to this disease. The ResNet50V2 with feature pyramid network achieved 98.49% accuracy on more than 7996 validation images and correctly identified almost 237 patients from 245 patients.</jats:p>

Deep learning‐based COVID‐19 diagnosis using CT scans with laboratory and physiological parameters

“…Rahimzadeh et al. [33] proposed pre‐processing CT scan images of patients to improve quality and exclude blurred images, which can impact a model's accuracy and speed. Then, a CNN‐based classification structure was developed to improve accuracy without the loss of minute details existing in small object data.…”

Online Unsupervised Learning for Domain Shift in Covid-19 CT Scan Datasets

“…We kept the images and labels that were positive for COVID-19 and CAP, but we did not keep the negative ones. Instead we extracted slices from healthy patients with large lung area, in a similar manner to Rahimzadeh et al [15]. We made an image selection algorithm to filter out images without lungs, or with small sections of lung, as well as images with lungs where much of the lung is not visible.…”

MedPipe: End-to-End Joint Search of Data Augmentation and Neural Architecture for 3D Medical Image Classification

“…The existing DL-based methods for 3D medical image classification can be broadly divided into three classes according to the types of neural architecture: 2D, 2.5D, and 3D CNNs. The 2D CNN-based methods [28], [29] treat the 3D volumetric data as a sequence of 2D slices and use 2D CNN to extract features slice-by-slice and then fuse these features to make classifications. The 2.5D CNN is to feed 2D CNN with multiple angled slices from the 3D-space [30], [31] or with tri-slice data (a center slice with its two neighbor slices forming a normal three-channel RGB image) [32].…”

“…1) Three COVID-19 3D CT Datasets: Table II shows the statistics of three COVID-19 3D CT datasets: Clean-CC-CCII [47], MosMed [50] and COVID-CTset [28], where NCP indicate novel coronavirus pneumonia and common pneumonia, respectively. Clean-CC-CCII is a cleaned version of CC-CCII [51] by removing noisy data and correcting the order of slices.…”