Improving reproducibility and performance of radiomics in low‐dose CT using cycle GANs. Issue 10 (30th July 2022)

• Record Type: Journal Article
• Authors: Chen, Junhua; Wee, Leonard; Dekker, Andre; Bermejo, Inigo
• Is Part Of: Journal of applied clinical medical physics. Volume 23:Issue 10(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-07-30
• Subjects: computed tomography -- cycle GAN -- denoising -- radiomics -- reproducibility; Medical physics -- Periodicals; Clinical medicine -- Periodicals; Health Physics; Clinical Medicine; Electronic journals; Periodicals; Periodicals; Fulltext; Internet Resources; 610.153
• DOI: 10.1002/acm2.13739
• Languages: English
• ISSNs: 1526-9914

Abstract

Abstract: Background: As a means to extract biomarkers from medical imaging, radiomics has attracted increased attention from researchers. However, reproducibility and performance of radiomics in low‐dose CT scans are still poor, mostly due to noise. Deep learning generative models can be used to denoise these images and in turn improve radiomics' reproducibility and performance. However, most generative models are trained on paired data, which can be difficult or impossible to collect. Purpose: In this article, we investigate the possibility of denoising low‐dose CTs using cycle generative adversarial networks (GANs) to improve radiomics reproducibility and performance based on unpaired datasets. Methods and materials: Two cycle GANs were trained: (1) from paired data, by simulating low‐dose CTs (i.e., introducing noise) from high‐dose CTs and (2) from unpaired real low dose CTs. To accelerate convergence, during GAN training, a slice‐paired training strategy was introduced. The trained GANs were applied to three scenarios: (1) improving radiomics reproducibility in simulated low‐dose CT images and (2) same‐day repeat low dose CTs (RIDER dataset), and (3) improving radiomics performance in survival prediction. Cycle GAN results were compared with a conditional GAN (CGAN) and an encoder–decoder network (EDN) trained on simulated paired data. Results: The cycle GAN trained on simulated data improved concordance correlation coefficients (CCC) of radiomic features from 0.87 (95%CI, [0.833, 0.901]) to 0.93 (95%CI, [0.916, 0.949]) on simulated noise CT and from 0.89 (95%CI, [0.881, 0.914]) to 0.92 (95%CI, [0.908, 0.937]) on the RIDER dataset, as well improving the area under the receiver operating characteristic curve (AUC) of survival prediction from 0.52 (95%CI, [0.511, 0.538]) to 0.59 (95%CI, [0.578, 0.602]). The cycle GAN trained on real data increased the CCCs of features in RIDER to 0.95 (95%CI, [0.933, 0.961]) and the AUC of survival prediction to 0.58 (95%CI, [0.576, 0.596]). Conclusion: The results show that cycle GANs trained on both simulated and real data can improve radiomics' reproducibility and performance in low‐dose CT and achieve similar results compared to CGANs and EDNs.