Uncertainty-aware convolutional neural network for COVID-19 X-ray images classification. (January 2022)

• Record Type: Journal Article
• Authors: Gour, Mahesh; Jain, Sweta
• Is Part Of: Computers in biology and medicine. Volume 140(2022)
• Publication Date: 2022-01
• Subjects: COVID-19 automatic screening uncertainty estimation Monte Carlo dropout pre-trained EfficientNet CNN Chest X-ray images; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.105047
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Deep learning (DL) has shown great success in the field of medical image analysis. In the wake of the current pandemic situation of SARS-CoV-2, a few pioneering works based on DL have made significant progress in automated screening of COVID-19 disease from the chest X-ray (CXR) images. But these DL models have no inherent way of expressing uncertainty associated with the model's prediction, which is very important in medical image analysis. Therefore, in this paper, we develop an uncertainty-aware convolutional neural network model, named UA-ConvNet, for the automated detection of COVID-19 disease from CXR images, with an estimation of associated uncertainty in the model's predictions. The proposed approach utilizes the EfficientNet-B3 model and Monte Carlo (MC) dropout, where an EfficientNet-B3 model has been fine-tuned on the CXR images. During inference, MC dropout has been applied for M forward passes to obtain the posterior predictive distribution. After that mean and entropy have been calculated on the obtained predictive distribution to get the mean prediction and model uncertainty. The proposed method is evaluated on the three different datasets of chest X-ray images, namely the COVID19CXr, X-ray image, and Kaggle datasets. The proposed UA-ConvNet model achieves a G-mean of 98.02% (with a Confidence Interval (CI) of 97.99–98.07) and sensitivity of 98.15% for the multi-class classification task on the COVID19CXr dataset. For binary classification, the proposed model achieves a G-mean of 99.16% (with a CI of 98.81–99.19) and a sensitivity of 99.30% on the X-ray Image dataset. Our proposed approach shows its superiority over the existing methods for diagnosing the COVID-19 cases from the CXR images. Highlights: We develop an uncertainty-aware CNN model that detects COVID-19 disease, with an estimation of associated uncertainty in the model's predictions. We demonstrate how uncertainty can be modeled in the CAD system for COVID-19 detection from the CXR images. We add Monte Carlo (MC) dropout with the EfficientNet-B3 network for making it Bayesian. We estimate the model uncertainty by modeling the posterior predictive distribution of M predictions of the model. This framework provides a predictive error estimator and demonstrates how much the model is confident in classifying for the given images. We also investigate the performance of various pre-trained networks for COVID-19 disease detection from CXR images.