Repository logo

Impact of GAN-based lesion-focused medical image super-resolution on the robustness of radiomic features

Published version

Change log


de Farias, Erick Costa 
di Noia, Christian 
Han, Changhee 
Sala, Evis 
Castelli, Mauro 


Abstract: Robust machine learning models based on radiomic features might allow for accurate diagnosis, prognosis, and medical decision-making. Unfortunately, the lack of standardized radiomic feature extraction has hampered their clinical use. Since the radiomic features tend to be affected by low voxel statistics in regions of interest, increasing the sample size would improve their robustness in clinical studies. Therefore, we propose a Generative Adversarial Network (GAN)-based lesion-focused framework for Computed Tomography (CT) image Super-Resolution (SR); for the lesion (i.e., cancer) patch-focused training, we incorporate Spatial Pyramid Pooling (SPP) into GAN-Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE). At 2× SR, the proposed model achieved better perceptual quality with less blurring than the other considered state-of-the-art SR methods, while producing comparable results at 4× SR. We also evaluated the robustness of our model’s radiomic feature in terms of quantization on a different lung cancer CT dataset using Principal Component Analysis (PCA). Intriguingly, the most important radiomic features in our PCA-based analysis were the most robust features extracted on the GAN-super-resolved images. These achievements pave the way for the application of GAN-based image Super-Resolution techniques for studies of radiomics for robust biomarker discovery.



Article, /692/53, /692/699/67, /692/700/1421, /692/308/53, /692/4028/67/2321, /692/4028/67/1612, /639/166/985, article

Journal Title

Scientific Reports

Conference Name

Journal ISSN


Volume Title



Nature Publishing Group UK
Mark Foundation For Cancer Research (C9685/A25177, C9685/A25177)
Cancer Research UK (C42780/A27066, C42780/A27066)
NIHR Cambridge Biomedical Research Centre (BRC-1215-20014, BRC-1215-20014)
Wellcome Trust (215733/Z/19/Z)
Fundação para a Ciência e a Tecnologia (DSAIPA/DS/0022/2018)
Javna Agencija za Raziskovalno Dejavnost RS (P5-0410)