A computationally-inexpensive strategy in CT image data augmentation for robust deep learning classification in the early stages of an outbreak
Biomedical Physics & Engineering Express · 2023
DOI: 10.1088/2057-1976/ace4cf ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomedical Physics & Engineering Express, 2023. Verfasst von Yikun Hou und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic, Electrical and Systems Engineering, University of Birmingham, Birmingham B15 2TT, United Kingdom. Hauptthemen laut MEDLINE: COVID-19, Deep Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council.
Abstract (Originalsprache)
Coronavirus disease 2019 (COVID-19) has spread globally for over three years, and chest computed tomography (CT) has been used to diagnose COVID-19 and identify lung damage in COVID-19 patients. Given its widespread, CT will remain a common diagnostic tool in future pandemics, but its effectiveness at the beginning of any pandemic will depend strongly on the ability to classify CT scans quickly and correctly when only limited resources are available, as it will happen inevitably again in future pandemics. Here, we resort into the transfer learning procedure and limited hyperparameters to use as few computing resources as possible for COVID-19 CT images classification. Advanced Normalisation Tools (ANTs) are used to synthesise images as augmented/independent data and trained on EfficientNet to investigate the effect of synthetic images. On the COVID-CT dataset, classification accuracy increases from 91.15% to 95.50% and Area Under the Receiver Operating Characteristic (AUC) from 96.40% to 98.54%. We also customise a small dataset to simulate data collected in the early stages of the outbreak and report an improvement in accuracy from 85.95% to 94.32% and AUC from 93.21% to 98.61%. This study provides a feasible Low-Threshold, Easy-To-Deploy and Ready-To-Use solution with a relatively low computational cost for medical image classification at an early stage of an outbreak in which scarce data are available and traditional data augmentation may fail. Hence, it would be most suitable for low-resource settings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electronic, Electrical and Systems Engineering, University of Birmingham, Birmingham B15 2TT, United Kingdom.
- School of Physics and Astronomy, University of Birmingham, Birmingham B15 2TT, United Kingdom.
ORCID-Profile: Yikun Hou, Miguel Navarro-Cía
Förderung
- Engineering and Physical Sciences Research Council
Zitieren
APA
Hou, Y., & Navarro-Cía, M. (2023). A computationally-inexpensive strategy in CT image data augmentation for robust deep learning classification in the early stages of an outbreak. Biomedical Physics & Engineering Express. https://doi.org/10.1088/2057-1976/ace4cf
Vancouver
Hou Y, Navarro-Cía M. A computationally-inexpensive strategy in CT image data augmentation for robust deep learning classification in the early stages of an outbreak. Biomedical Physics & Engineering Express. 2023. doi:10.1088/2057-1976/ace4cf
BibTeX
@article{Hou2023,
author = {Hou, Yikun and Navarro-Cía, Miguel},
title = {A computationally-inexpensive strategy in CT image data augmentation for robust deep learning classification in the early stages of an outbreak},
journal = {Biomedical Physics & Engineering Express},
year = {2023},
doi = {10.1088/2057-1976/ace4cf}
}
EUVIMED