Non-contrast CT synthesis using patch-based cycle-consistent generative adversarial network (Cycle-GAN) for radiomics and deep learning in the era of COVID-19.

Thumbnail Image

Files

Non-contrast CT synthesis using patch-based cycle-consistent generative adversarial network (Cycle-GAN) for radiomics and de.pdf (4.97 MB)

Embargo End Date

ICR Authors

Kalantar, Reza
 Sharma, Bhupinder
 Koh, Dow-mu
 Blackledge, Matthew

Authors

Kalantar, R
Hindocha, S
Hunter, B
Sharma, B
Khan, N
Koh, D-M
Ahmed, M
Aboagye, EO
Lee, RW
Blackledge, MD

Document Type

Journal Article

Date

2023-06-29

Date Accepted

2023-06-07

Abstract

Handcrafted and deep learning (DL) radiomics are popular techniques used to develop computed tomography (CT) imaging-based artificial intelligence models for COVID-19 research. However, contrast heterogeneity from real-world datasets may impair model performance. Contrast-homogenous datasets present a potential solution. We developed a 3D patch-based cycle-consistent generative adversarial network (cycle-GAN) to synthesize non-contrast images from contrast CTs, as a data homogenization tool. We used a multi-centre dataset of 2078 scans from 1,650 patients with COVID-19. Few studies have previously evaluated GAN-generated images with handcrafted radiomics, DL and human assessment tasks. We evaluated the performance of our cycle-GAN with these three approaches. In a modified Turing-test, human experts identified synthetic vs acquired images, with a false positive rate of 67% and Fleiss' Kappa 0.06, attesting to the photorealism of the synthetic images. However, on testing performance of machine learning classifiers with radiomic features, performance decreased with use of synthetic images. Marked percentage difference was noted in feature values between pre- and post-GAN non-contrast images. With DL classification, deterioration in performance was observed with synthetic images. Our results show that whilst GANs can produce images sufficient to pass human assessment, caution is advised before GAN-synthesized images are used in medical imaging applications.

Citation

Scientific Reports, 2023, 13 (1), pp. 10568 -

DOI

10.1038/s41598-023-36712-1

URI

https://repository.icr.ac.uk/handle/internal/5942

Rights

http://creativecommons.org/licenses/by/4.0/

Source Title

Scientific Reports

Publisher

NATURE PORTFOLIO

ISSN

2045-2322

eISSN

2045-2322
2045-2322

Collections

Radiotherapy and Imaging

Research Team

Computational Imaging
RMH Honorary Faculty

Notes