A Multi-Stage Progressive Learning Strategy for COVID-19 Diagnosis using Chest Computed Tomography with Imbalanced Data

Zaifeng Yang, Yubo Hou, Zhenghua Chen, Le Zhang, Jie Chen

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

Abstract

In this paper, a multi-stage progressive learning strategy is investigated to train classifiers for COVID-19 Diagnosis using imbalanced Chest Computed Tomography Data acquired from patients infected with COVID-19 Pneumonia, Community Acquired Pneumonia (CAP) and from normal healthy subjects. In the first learning stage, pre-processed volumetric CT data together with the segmented lung masks are fed into a 3D ResNet module, and an initial classification result can be obtained. However, due to categorical data imbalance, we observe large differences in sensitivity between COVID-19 and CAP cases. In the second stage, five learning models are independently trained over data with only COVID-19 and CAP cases, and are then ensembled to further discriminate the two classes. The final classification results are obtained by combining the predictions from both stages. Based on the validation dataset, we have evaluated our method and compared it with up-to-date methods in terms of overall accuracy and sensitivity for each class. The validation results validate the accuracy of the proposed multi-stage learning strategy. The overall accuracy of the validation dataset is 88.8%, and the sensitivities are 0.873, 0.789 and 1 for COVID-19, CAP and normal cases, respectively.
Original languageEnglish
Title of host publicationICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherIEEE
Pages8578-8582
Number of pages5
ISBN (Electronic)9781728176055
ISBN (Print)9781728176062
DOIs
Publication statusPublished - Jun 2021
Event2021 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021 - Virtual, Toronto, ON, Canada
Duration: 6 Jun 202111 Jun 2021
https://www.2021.ieeeicassp.org/2021.ieeeicassp.org/index.html
https://ieeexplore.ieee.org/xpl/conhome/9413349/proceeding

Publication series

NameIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ISSN (Print)1520-6149
ISSN (Electronic)2379-190X

Conference

Conference2021 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021
Country/TerritoryCanada
CityVirtual, Toronto, ON
Period6/06/2111/06/21
Internet address

User-Defined Keywords

  • COVID-19
  • computed tomography
  • multi-stage learning
  • imbalanced data classification
  • 3D ResNet

Fingerprint

Dive into the research topics of 'A Multi-Stage Progressive Learning Strategy for COVID-19 Diagnosis using Chest Computed Tomography with Imbalanced Data'. Together they form a unique fingerprint.

Cite this