The Effectiveness of Image Augmentation in Deep Learning Networks for Detecting COVID-19: A Geometric Transformation Perspective

Frontiers in Medicine

Richard Ribbon Fletcher¹  Muhammad Umer Nasir²  William Parker²  Savvas Nicolaou³  Catherine Batte⁴  Bradley Spieler⁵  John-Paul Grenier⁵  David Smith⁵  Newton Howard⁶  William Donald Leslie⁷  Mohamed Elgendi⁸  Qunfeng Tang⁹  Rabab Ward⁹  Carlo Menon^1,10 

[1] D-Lab, Massachusetts Institute of Technology, Cambridge, MA, United States;Department of Emergency and Trauma Radiology, Vancouver General Hospital, Vancouver, BC, Canada;Department of Emergency and Trauma Radiology, Vancouver General Hospital, Vancouver, BC, Canada;Department of Radiology, Faculty of Medicine, University of British Columbia, Vancouver, BC, Canada;Department of Physics & Astronomy, Louisiana State University, Baton Rouge, LA, United States;Department of Radiology, Louisiana State University Health Sciences Center, New Orleans, LA, United States;Nuffield Department of Surgical Sciences, University of Oxford, Oxford, United Kingdom;Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, MB, Canada;Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, MB, Canada;School of Mechatronic Systems Engineering, Simon Fraser University, Burnaby, BC, Canada;Nuffield Department of Surgical Sciences, University of Oxford, Oxford, United Kingdom;School of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada;School of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada;School of Mechatronic Systems Engineering, Simon Fraser University, Burnaby, BC, Canada;Biomedical and Mobile Health Technology Laboratory, Department of Health Sciences and Technology, ETH Zurich, Zurich, Switzerland;

关键词: radiology;    corona virus;    transfer learning;    data augmentation;    chest X-ray;    digital health;    machine learning;    artificial intelligence;   

DOI  :  10.3389/fmed.2021.629134

来源: Frontiers

【 摘 要 】

Chest X-ray imaging technology used for the early detection and screening of COVID-19 pneumonia is both accessible worldwide and affordable compared to other non-invasive technologies. Additionally, deep learning methods have recently shown remarkable results in detecting COVID-19 on chest X-rays, making it a promising screening technology for COVID-19. Deep learning relies on a large amount of data to avoid overfitting. While overfitting can result in perfect modeling on the original training dataset, on a new testing dataset it can fail to achieve high accuracy. In the image processing field, an image augmentation step (i.e., adding more training data) is often used to reduce overfitting on the training dataset, and improve prediction accuracy on the testing dataset. In this paper, we examined the impact of geometric augmentations as implemented in several recent publications for detecting COVID-19. We compared the performance of 17 deep learning algorithms with and without different geometric augmentations. We empirically examined the influence of augmentation with respect to detection accuracy, dataset diversity, augmentation methodology, and network size. Contrary to expectation, our results show that the removal of recently used geometrical augmentation steps actually improved the Matthews correlation coefficient (MCC) of 17 models. The MCC without augmentation (MCC = 0.51) outperformed four recent geometrical augmentations (MCC = 0.47 for Data Augmentation 1, MCC = 0.44 for Data Augmentation 2, MCC = 0.48 for Data Augmentation 3, and MCC = 0.49 for Data Augmentation 4). When we retrained a recently published deep learning without augmentation on the same dataset, the detection accuracy significantly increased, with a χMcNemar′s statistic2=163.2 and a p-value of 2.23 × 10−37. This is an interesting finding that may improve current deep learning algorithms using geometrical augmentations for detecting COVID-19. We also provide clinical perspectives on geometric augmentation to consider regarding the development of a robust COVID-19 X-ray-based detector.

【 授权许可】

CC BY