CovXNet: A multi-dilation convolutional neural network for automatic COVID-19 and other pneumonia detection from chest X-ray images with transferable multi-receptive feature optimization

• Published in: Computers in biology and medicine Vol. 122; p. 103869
• Main Authors: Mahmud, Tanvir, Rahman, Md Awsafur, Fattah, Shaikh Anowarul
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01-07-2020; Elsevier Limited
• Subjects: Algorithms; Artificial neural networks; Bacteria; Betacoronavirus; Chest; Clinical Laboratory Techniques - methods; Convolution; Coronavirus Infections - diagnosis; Coronavirus Infections - diagnostic imaging; Coronaviruses; COVID-19; COVID-19 diagnosis; COVID-19 Testing; Databases, Factual; Deep Learning; Diagnostic systems; Dilation; Feature extraction; Humans; Image detection; Image Processing, Computer-Assisted - methods; Imaging informatics; Localization; Machine learning; Medical diagnosis; Medical imaging; Neural network; Neural networks; Neural Networks, Computer; Optimization; Pandemics; Pneumonia; Pneumonia diagnosis; Pneumonia, Viral - diagnostic imaging; Radiography, Thoracic - methods; Reproducibility of Results; SARS-CoV-2; Transfer learning; Viral diseases; X-ray; X-rays; COVID-19 diagnosis; Imaging informatics; Neural network; X-ray; Pneumonia diagnosis; Transfer learning
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2020.103869

With the recent outbreak of COVID-19, fast diagnostic testing has become one of the major challenges due to the critical shortage of test kit. Pneumonia, a major effect of COVID-19, needs to be urgently diagnosed along with its underlying reasons. In this paper, deep learning aided automated COVID-19 and other pneumonia detection schemes are proposed utilizing a small amount of COVID-19 chest X-rays. A deep convolutional neural network (CNN) based architecture, named as CovXNet, is proposed that utilizes depthwise convolution with varying dilation rates for efficiently extracting diversified features from chest X-rays. Since the chest X-ray images corresponding to COVID-19 caused pneumonia and other traditional pneumonias have significant similarities, at first, a large number of chest X-rays corresponding to normal and (viral/bacterial) pneumonia patients are used to train the proposed CovXNet. Learning of this initial training phase is transferred with some additional fine-tuning layers that are further trained with a smaller number of chest X-rays corresponding to COVID-19 and other pneumonia patients. In the proposed method, different forms of CovXNets are designed and trained with X-ray images of various resolutions and for further optimization of their predictions, a stacking algorithm is employed. Finally, a gradient-based discriminative localization is integrated to distinguish the abnormal regions of X-ray images referring to different types of pneumonia. Extensive experimentations using two different datasets provide very satisfactory detection performance with accuracy of 97.4% for COVID/Normal, 96.9% for COVID/Viral pneumonia, 94.7% for COVID/Bacterial pneumonia, and 90.2% for multiclass COVID/normal/Viral/Bacterial pneumonias. Hence, the proposed schemes can serve as an efficient tool in the current state of COVID-19 pandemic. All the architectures are made publicly available at: https://github.com/Perceptron21/CovXNet.
•A novel deep neural network architecture is proposed based on depthwise dilated convolutions.•Larger database containing non-COVID pneumonia X-rays are used for initial training stage that are effectively transferred for utilizing smaller database containing COVID-19 X-rays.•Features extracted from different resolutions of X-rays are jointly converged by the proposed stacking algorithm.•Clinical investigation is carried out by analyzing the gradient based activation mapping.