Deep Learning-Based Prediction of SARS-CoV-2 (COVID-19) and its Severity Classification using Multimodal Chest Radiography Images
Embedded Files
Fig. 1 X-ray Image
Introduction:
Introduction:
The Coronavirus 2019, or shortly COVID-19, is a viral disease that causes serious pneumonia and impacts our different body parts from mild to severe depending on the patient’s immune system. This infection was first reported in Wuhan city of China in December 2019, and afterward, it became a global pandemic spreading rapidly around the world. As the virus spreads through human-to-human contact, it has affected our lives in a devastating way, including the vigorous pressure on the public health system, the world economy, education sector, workplaces, and shopping malls. Preventing viral spreading requires early detection of positive cases and treating infected patients as quickly as possible. The need for COVID-19 testing kits has increased, and many of the developing countries in the world are facing a shortage of testing kits as new cases are increasing day by day.
In this situation, the recent research using radiology imaging (such as X-ray and CT scan Fig. 1) techniques can be proven helpful to detect COVID-19 as X-ray and CT scan images provide important information about the disease caused by the COVID-19 virus by use of deep learning techniques. There are X-ray images and computer tomography (CT) of healthy people and patients suffering from COVID-19 available publicly that enable us to inspect and diagnose the conceivable patterns that may help to detect COVID-19 and its severity i.e. Atypical, Indeterminate and Typical.
Fig. 2 CRIs
Motivation:
Motivation:
RT-PCR is an expansive, time-consuming, and tedious task. But due to the emergence of Deep Learning methods in medical imaging, we can automate this task.
Most of the researchers did not use multi-modalities (X-rays, Ultrasounds, and CTs) for model training and prediction.
Chest Radiography Images(CRIs) analysis can provide proper guidance and direction to medical specialists and radiologists to understand the disease and examine clinical challenges.
To the best of our knowledge, so far there is no such published research that predicts the different severity levels (Typical, Indeterminate, and Atypical) of COVID-19.
Researchers could not achieve high accuracy, particularly for 4-class classification (COVID vs. normal vs. bacterial pneumonia vs. viral pneumonia) Fig. 2.
Applications:
Applications:
Available DataSets:
Available DataSets:
Flow Diagram:
Flow Diagram:
Fig. 3 Research Methodology
Model Architecture:
Model Architecture:
Fig. 4 Architecture
Evaluation Measures:
Evaluation Measures:
Confusion Matrix
Accuracy
F-Measure
Precision
Sensitivity
Specificity
False Negative Rate
False Positive Rate
Conclusion:
Conclusion:
Lightweight ResGRU novel and hybrid system to diagnose Non-COVID chest infections and COVID-19 chest infections, including its different severity types.
The vital role of the study is the acquisition and creation of a large dataset for chest infection prediction.
A multi-model based approach which has better performance even on external cohort.
The proposed model achieved 99.5%, 98.4%, 90.2%, and 80.7% accuracy for 2 class, 3 class, 4 class classification, and COVID-19 severity classification on a large test data.
Relevant Journal Papers:
Relevant Journal Papers:
COVIDetection-Net: A tailored COVID-19 detection from chest radiography images using deep learning. [1]
CoroDet: A deep learning based classification for COVID-19 detection using chest X-ray images. [2]
TLCoV- An automated Covid-19 screening model using Transfer Learning from chest X-ray images. [3]
Coronavirus (COVID-19) Detection from Chest Radiology Images using Convolutional Neural Networks. [4]
DeepCoroNet: A deep LSTM approach for automated detection of COVID-19 cases from chest X-ray images. [5]
COVID faster R–CNN: A novel framework to Diagnose Novel Coronavirus Disease (COVID-19) in X-Ray images. [6]
Automated detection of COVID-19 cases using deep neural networks with X-ray images. [7]
Coronavirus (COVID-19) detection from chest radiology images using convolutional neural network. [8]
Application of deep learning technique to manage COVID-19 in routine clinical practice using CT images: Results of 10 convolutional neural networks. [9]
COVID-19 and Non-COVID-19 Classification using Multi-layers Fusion From Lung Ultrasound Images. [10]
Synopsis Presentation:
Synopsis Presentation:
Synopsis_Presentation_V1.2.pptxTeam:
Team:
Dr. Usama Ijaz Bajwa
Co-PI, Video Analytics lab, National Centre in Big Data and Cloud Computing,Program Chair (FIT 2019),HEC Approved PhD Supervisor,Assistant Professor & Associate Head of DepartmentDepartment of Computer Science,COMSATS University Islamabad, Lahore Campus, Pakistanwww.usamaijaz.comwww.fit.edu.pkJob ProfileGoogle Scholar Profile
Mughees Ahmad
Email: mugheessarfraz@gmail.comPhone Number: 0332 4510888(Research in Computer Science(RCS), COMSATS Lahore)Page updated
Google Sites
Report abuse