An Efficient Mixture of Deep and Machine Learning Models for COVID-19 and Tuberculosis Detection Using X-Ray Images in Resource Limited Settings

Clinicians in the frontline need to assess quickly whether a patient with symptoms indeed has COVID-19 or not. The difficulty of this task is exacerbated in low resource settings that may not have access to biotechnology tests. Furthermore, Tuberculosis (TB) remains amajor health problemin several low- and middle-income countries and its common symptoms include fever, cough and tiredness, similarly to COVID-19. In order to help in the detection of COVID-19, we propose the extraction of deep features (DF) from chest X-ray images, a technology available in most hospitals, and their subsequent classification using machine learning that do not require large computational resources. We compiled a five-class dataset of X-ray chest images including a balanced number of COVID-19, viral pneumonia, bacterial pneumonia, TB, and healthy cases. We compared the performance of proposed pipelines combining 14 individual pre-trained deep networks for DF extraction with machine learning classifiers. A novel pipeline consisting of ResNet-50 for DF computation and ensemble of subspace discriminant classifier was the best performer in the classification of the five classes, achieving a detection accuracy of 91.6 ± 0.57% (± Confidence Interval, CI, at 95% confidence level). Furthermore, the same pipeline achieved accuracies of 98.6 ± 0.34% (± CI) and 99.9% in three-class and two-class problems focused on distinguishing COVID-19, TB and healthy cases; and COVID-19 and healthy images; respectively. The pipeline was computationally efficient requiring just 0.19 s to extractDF perX-ray image and 2min for training a classifier on a CPU machine. The results suggest the potential benefits of using our pipeline in the detection of COVID-19, particularly in resource-limited settings as it relies in accessible X-rays and limited computational resources. The final constructed dataset, named COVID-19 five-class dataset and codes, are available from https://drive.google.com/drive/folders/1toMymyHTy0DR_fyE7hjO3LSBGWtVoPNf?usp=sharing.