2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDCHLG-1.4
Paper Title COVID-19 DIAGNOSTIC USING 3D DEEP TRANSFER LEARNING FOR CLASSIFICATION OF VOLUMETRIC COMPUTERISED TOMOGRAPHY CHEST SCANS
Authors Shuohan Xue, Charith Abhayaratne, University of Sheffield, United Kingdom
SessionCHLG-1: COVID-19 Diagnosis
LocationZoom
Session Time:Monday, 07 June, 09:30 - 12:00
Presentation Time:Monday, 07 June, 09:30 - 12:00
Presentation Poster
Topic Grand Challenge: COVID-19 Diagnosis
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract The Novel Coronavirus, known as COVID-19, can cause acute respiratory distress syndrome symptoms to human beings and has become a major threat to public health [1]. This paper proposes a COVID-19 diagnosis based on analysis of Computerised tomography (CT) chest scans. In recent years, deep learning-based analysis of CT chest scans has demonstrated competitive sensitivity for pneumonia prognosis. We exploit a 3D Network-based transfer learning approach to classify volumetric CT scans with a novel pre-processing method to render the volume with salient features. This work uses the pre-trained 3D ResNet50 as the backbone network. The 3D network is trained on a dataset consisting of3 classes: Community-Acquired Pneumonia(CAP), COVID-19 and Normal patient. The experimental results using 4-fold cross-validation has shown an overall accuracy of 86.94%with the COVID-19 sensitivity and specificity attaining to87.79%and89.88%, respectively.