Learning-to-augment strategy using noisy and denoised data: Improving generalizability of deep CNN for the detection of COVID-19 in X-ray images.

Journal: Computers in biology and medicine
Published Date:

Abstract

Chest X-ray images are used in deep convolutional neural networks for the detection of COVID-19, the greatest human challenge of the 21st century. Robustness to noise and improvement of generalization are the major challenges in designing these networks. In this paper, we introduce a strategy for data augmentation using the determination of the type and value of noise density to improve the robustness and generalization of deep CNNs for COVID-19 detection. Firstly, we present a learning-to-augment approach that generates new noisy variants of the original image data with optimized noise density. We apply a Bayesian optimization technique to control and choose the optimal noise type and its parameters. Secondly, we propose a novel data augmentation strategy, based on denoised X-ray images, that uses the distance between denoised and original pixels to generate new data. We develop an autoencoder model to create new data using denoised images corrupted by the Gaussian and impulse noise. A database of chest X-ray images, containing COVID-19 positive, healthy, and non-COVID pneumonia cases, is used to fine-tune the pre-trained networks (AlexNet, ShuffleNet, ResNet18, and GoogleNet). The proposed method performs better results compared to the state-of-the-art learning to augment strategies in terms of sensitivity (0.808), specificity (0.915), and F-Measure (0.737). The source code of the proposed method is available at https://github.com/mohamadmomeny/Learning-to-augment-strategy.

Authors

  • Mohammad Momeny
    Department of Computer Engineering, Yazd University, Yazd, Iran. Electronic address: mohamad.momeny@gmail.com.
  • Ali Asghar Neshat
    Department of Environmental Engineering, Esfarayen Faculty of Medical Science, Esfarayen, Iran. Electronic address: en.neshat@gmail.com.
  • Mohammad Arafat Hussain
  • Solmaz Kia
    Department of Engineering Science, Faculty of Advanced Technologies, University of Mohaghegh Ardabili, Namin, Iran.
  • Mahmoud Marhamati
    Department of Medical-Surgical Nursing, Esfarayen Faculty of Medical Science, Esfarayen, Iran.
  • Ahmad Jahanbakhshi
    Department of Biosystems Engineering, University of Mohaghegh Ardabili, Ardabil, Iran.
  • Ghassan Hamarneh
    Medical Image Analysis Lab, Simon Fraser University, Burnaby, BC, Canada. Electronic address: hamarneh@sfu.ca.