DenResCov-19: A deep transfer learning network for robust automatic classification of COVID-19, pneumonia, and tuberculosis from X-rays

Michail Mamalakis, Andrew J. Swift, Bart Vorselaars, Surajit Ray, Simonne Weeks, Weiping Ding, Richard H. Clayton, Louise S Mackenzie, Abhirup Banerjee

Research output: Contribution to journalArticlepeer-review


The global pandemic of coronavirus disease 2019 (COVID-19) is continuing to have a significant effect on the well-being of the global population, thus increasing the demand for rapid testing, diagnosis, and treatment. As COVID-19 can cause severe pneumonia, early diagnosis is essential for correct treatment, as well as to reduce the stress on the healthcare system. Along with COVID-19, other etiologies of pneumonia and Tuberculosis (TB) constitute additional challenges to the medical system. Pneumonia (viral as well as bacterial) kills about 2 million infants every year and is consistently estimated as one of the most important factor of childhood mortality (according to the World Health Organization). Chest X-ray (CXR) and computed tomography (CT) scans are the primary imaging modalities for diagnosing respiratory diseases. Although CT scans are the gold standard, they are more expensive, time consuming, and are associated with a small but significant dose of radiation. Hence, CXR have become more widespread as a first line investigation. In this regard, the objective of this work is to develop a new deep transfer learning pipeline, named DenResCov-19, to diagnose patients with COVID-19, pneumonia, TB or healthy based on CXR images. The pipeline consists of the existing DenseNet-121 and the ResNet-50 networks. Since the DenseNet and Resnet have orthogonal performances in some instances, in the proposed model we have created an extra layer with convolutional neural network (CNN) blocks to join these two models together to establish superior performance as compared to the two individual networks. This strategy can be applied universally in cases where two competing networks are observed. We have tested the performance of our proposed network on two-class (pneumonia and healthy), three-class (COVID-19 positive, healthy, and pneumonia), as well as four-class (COVID-19 positive, healthy, TB, and pneumonia) classification problems. We have validated that our proposed network has been able to successfully classify these lung-diseases on our four datasets and this is one of our novel findings. In particular, the AUC-ROC are 99.60, 96.51, 93.70, 96.40% and the F1 values are 98.21, 87.29, 76.09, 83.17% on our Dataset X-Ray 1, 2, 3, and 4 (DXR1, DXR2, DXR3, DXR4), respectively.
Original languageEnglish
Article number102008
Number of pages1
JournalComputerized Medical Imaging and Graphics
Publication statusPublished - 23 Oct 2021

Bibliographical note

Funding Information:
The work of Andrew J. Swift was supported by the Wellcome Trust UK fellowship grant 205188/Z/16/Z . The work of Surajit Ray was supported by the EPSRC IAA ( EP/R511705/1 ) Finger prick test for early prediction of SARS-CoV-2; a screening method using changes in full blood count parameters. The work of Weiping Ding was supported in part by the National Natural Science Foundation of China under Grant 61976120 , in part by the Natural Science Foundation of Jiangsu Province under Grant BK20191445 , in part by the Natural Science Key Foundation of Jiangsu Education Department under Grant 21KJA510004 , and sponsored by Qing Lan Project of Jiangsu Province. The authors acknowledge the use of facilities of the Research Software Engineering (RSE) Sheffield, UK. The authors express no conflict of interest.


  • COVID-19
  • Pneumonia
  • Chest X-Rays
  • DenseNet-121
  • ResNet-50
  • Deep transfer learning network
  • Automatic classification
  • Tuberculosis
  • Chest X-rays
  • automatic classification
  • Deep Transfer Learning Network
  • Covid-19


Dive into the research topics of 'DenResCov-19: A deep transfer learning network for robust automatic classification of COVID-19, pneumonia, and tuberculosis from X-rays'. Together they form a unique fingerprint.

Cite this