DML-OFA: Deep mutual learning with online feature alignment for the detection of COVID-19 from chest x-ray images

Zhihao Liang, Huijuan Lu, Zhendong Ming, Zhuijun Chai, Yudong Yao

Research output: Contribution to journalArticlepeer-review

Abstract

COVID-19 is a novel coronavirus-induced disease and automatic identification of COVID-19 using computer-assisted methods can facilitate faster diagnostic efficiency. Current research typically employs a single model for COVID-19 identification, while implicit and complementary knowledge between heterogeneous networks is neglected. To address these issues, we propose a new model based on deep mutual learning with online feature alignment called DML-OFA to more effectively diagnose COVID-19. First, we use a traditional deep mutual learning (DML) framework to allow two parallel heterogeneous networks to learn from each other to form two effective feature extractors. In addition, we embed the adaptive feature fusion classifier and logits ensembling module in the proposed DML-OFA, which can simultaneously learn implicit complementary knowledge from feature maps and logits. We evaluated DML-OFA on four public datasets: Covid-chestxray-dataset, ChestXRay2017, Coronavirus-dataset and COVIDx. The results showed that our model attains 97.10 (Formula presented.) Accuracy, 97.28 (Formula presented.) Specificity, 96.21 (Formula presented.) Recall, 97.45 (Formula presented.) Precision, and 96.82 (Formula presented.) F1-score, which outperforms other previous related works.

Original languageEnglish
Article numbere8023
JournalConcurrency and Computation: Practice and Experience
Volume36
Issue number11
DOIs
StatePublished - 15 May 2024

Keywords

  • COVID-19 recognition
  • deep mutual learning
  • feature fusion

Fingerprint

Dive into the research topics of 'DML-OFA: Deep mutual learning with online feature alignment for the detection of COVID-19 from chest x-ray images'. Together they form a unique fingerprint.

Cite this