Paper ID | CHLG-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 | ||
Session | CHLG-1: COVID-19 Diagnosis | ||
Location | Zoom | ||
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. |