Preprint Article Version 2 Preserved in Portico This version is not peer-reviewed

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

Version 1 : Received: 2 June 2020 / Approved: 4 June 2020 / Online: 4 June 2020 (08:29:03 CEST)
Version 2 : Received: 4 July 2020 / Approved: 5 July 2020 / Online: 5 July 2020 (05:31:44 CEST)
Version 3 : Received: 1 September 2020 / Approved: 5 September 2020 / Online: 5 September 2020 (03:36:20 CEST)

A peer-reviewed article of this Preprint also exists.

Mohammad Rahimzadeh, Abolfazl Attar, Seyed Mohammad Sakhaei, A fully automated deep learning-based network for detecting COVID-19 from a new and large lung CT scan dataset, Biomedical Signal Processing and Control, Volume 68, 2021, 102588, ISSN 1746-8094, https://doi.org/10.1016/j.bspc.2021.102588. (https://www.sciencedirect.com/science/article/pii/S1746809421001853) Abstract: This paper aims to propose a high-speed and accurate fully-automated method to detect COVID-19 from the patient's chest CT scan images. We introduce a new dataset that contains 48,260 CT scan images from 282 normal persons and 15,589 images from 95 patients with COVID-19 infections. At the first stage, this system runs our proposed image processing algorithm that analyzes the view of the lung to discard those CT images that inside the lung is not properly visible in them. This action helps to reduce the processing time and false detections. At the next stage, we introduce a novel architecture for improving the classification accuracy of convolutional networks on images containing small important objects. Our architecture applies a new feature pyramid network designed for classification problems to the ResNet50V2 model so the model becomes able to investigate different resolutions of the image and do not lose the data of small objects. As the infections of COVID-19 exist in various scales, especially many of them are tiny, using our method helps to increase the classification performance remarkably. After running these two phases, the system determines the condition of the patient using a selected threshold. We are the first to evaluate our system in two different ways on Xception, ResNet50V2, and our model. In the single image classification stage, our model achieved 98.49% accuracy on more than 7996 test images. At the patient condition identification phase, the system correctly identified almost 234 of 245 patients with high speed. Our dataset is accessible at https://github.com/mr7495/COVID-CTset. Keywords: Deep learning; Convolutional neural networks; COVID-19; Coronavirus; Radiology; CT scan; Medical image analysis; Automatic medical diagnosis; Lung CT scan dataset Mohammad Rahimzadeh, Abolfazl Attar, Seyed Mohammad Sakhaei, A fully automated deep learning-based network for detecting COVID-19 from a new and large lung CT scan dataset, Biomedical Signal Processing and Control, Volume 68, 2021, 102588, ISSN 1746-8094, https://doi.org/10.1016/j.bspc.2021.102588. (https://www.sciencedirect.com/science/article/pii/S1746809421001853) Abstract: This paper aims to propose a high-speed and accurate fully-automated method to detect COVID-19 from the patient's chest CT scan images. We introduce a new dataset that contains 48,260 CT scan images from 282 normal persons and 15,589 images from 95 patients with COVID-19 infections. At the first stage, this system runs our proposed image processing algorithm that analyzes the view of the lung to discard those CT images that inside the lung is not properly visible in them. This action helps to reduce the processing time and false detections. At the next stage, we introduce a novel architecture for improving the classification accuracy of convolutional networks on images containing small important objects. Our architecture applies a new feature pyramid network designed for classification problems to the ResNet50V2 model so the model becomes able to investigate different resolutions of the image and do not lose the data of small objects. As the infections of COVID-19 exist in various scales, especially many of them are tiny, using our method helps to increase the classification performance remarkably. After running these two phases, the system determines the condition of the patient using a selected threshold. We are the first to evaluate our system in two different ways on Xception, ResNet50V2, and our model. In the single image classification stage, our model achieved 98.49% accuracy on more than 7996 test images. At the patient condition identification phase, the system correctly identified almost 234 of 245 patients with high speed. Our dataset is accessible at https://github.com/mr7495/COVID-CTset. Keywords: Deep learning; Convolutional neural networks; COVID-19; Coronavirus; Radiology; CT scan; Medical image analysis; Automatic medical diagnosis; Lung CT scan dataset

Journal reference: Biomedical Signal Processing and Control 2021, 68, 102588
DOI: 10.1016/j.bspc.2021.102588

Abstract

COVID-19 is a severe global problem, and one of the primary ways to decrease its 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. In this paper, we aim to propose a high- speed and accurate fully-automated method to detect COVID-19 from the patient's CT scan. 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 automated system 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 system runs the proposed 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 processed, 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 new modified deep convolutional network that is based on ResNet50V2 and is enhanced by the feature pyramid network for classifying the selected CT images into COVID-19 or normal. After running these two phases, if enough number of chosen CT scan images of a patient be identified as COVID-19, the system considers that patient, infected to this disease. In the single image classification stage, the ResNet50V2 with feature pyramid network achieved 98.49% accuracy on more than 7996 validation images. At the fully automated phase, the automated system correctly identified almost 237 patients from 245 patients on average between five-folds with high speed. In the end, we also investigate the classified images with a feature visualization algorithm to indicate the area of infections in each image. We are implementing these materials on some medical centers in Iran, and we hope that it would be a great help in Intelligence disease detection anywhere.

Supplementary and Associated Material

https://github.com/mr7495/COVID-CTset: The Large COVID-19 CT Scans dataset
https://github.com/mr7495/COVID-CTset: Codes, Algorithms and Trained models

Subject Areas

Deep learning; Convolutional Neural Network; Coronavirus; COVID-19; radiology; CT scan; Medical image analysis; Automatic medical diagnosis; lung CT scan dataset

Comments (1)

Comment 1
Received: 5 July 2020
Commenter: Mohammad Rahimzadeh
Commenter's Conflict of Interests: Author
Comment: Dear editor,

The abstract and conclusion have been modified, and a new table and figure are added for showing the network speed and segmented infections, respectively.

Regards
+ Respond to this comment

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 1
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.