Using a Generative Adversarial Network for CT Normalization and Its Impact on Radiomic Features

Computer-Aided-Diagnosis (CADx) systems assist radiologists with identifying and classifying potentially malignant pulmonary nodules on chest CT scans using morphology and texture-based (radiomic) features. However, radiomic features are sensitive to differences in acquisitions due to variations in dose levels and slice thickness. This study investigates the feasibility of generating a normalized scan from heterogeneous CT scans as input. We obtained projection data from 40 low-dose chest CT scans, simulating acquisitions at 10%, 25% and 50% dose and reconstructing the scans at 1.0mm and 2.0mm slice thickness. A 3D generative adversarial network (GAN) was used to simultaneously normalize reduced dose, thick slice (2.0mm) images to normal dose (100%), thinner slice (1.0mm) images. We evaluated the normalized image quality using peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) and Learned Perceptual Image Patch Similarity (LPIPS). Our GAN improved perceptual similarity by 35%, compared to a baseline CNN method. Our analysis also shows that the GAN-based approach led to a significantly smaller error (p-value < 0.05) in nine studied radiomic features. These results indicated that GANs could be used to normalize heterogeneous CT images and reduce the variability in radiomic feature values.

[1]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[2]  Alexei A. Efros,et al.  The Unreasonable Effectiveness of Deep Features as a Perceptual Metric , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[4]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[5]  Michael F. McNitt-Gray,et al.  Towards quantitative imaging: stability of fully automated nodule segmentation across varied dose levels and reconstruction parameters in a low-dose CT screening patient cohort , 2018, Medical Imaging.

[6]  Kyoung Mu Lee,et al.  Enhanced Deep Residual Networks for Single Image Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[7]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  F Noo,et al.  TH-AB-207A-05: A Fully-Automated Pipeline for Generating CT Images Across a Range of Doses and Reconstruction Methods. , 2016, Medical physics.

[9]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[10]  C. Gatsonis,et al.  Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening , 2012 .

[11]  Guang Li,et al.  CT Super-Resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE) , 2018, IEEE Transactions on Medical Imaging.

[12]  Max A. Viergever,et al.  Generative Adversarial Networks for Noise Reduction in Low-Dose CT , 2017, IEEE Transactions on Medical Imaging.

[13]  Denise R. Aberle,et al.  EDICNet: An end-to-end detection and interpretable malignancy classification network for pulmonary nodules in computed tomography , 2020, Medical Imaging.

[14]  Xuanqin Mou,et al.  Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss , 2017, IEEE Transactions on Medical Imaging.

[15]  Andriy Fedorov,et al.  Computational Radiomics System to Decode the Radiographic Phenotype. , 2017, Cancer research.

[16]  M. L. R. D. Christenson,et al.  Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening , 2012 .

[17]  Michael F. McNitt-Gray,et al.  The effects of slice thickness and radiation dose level variations on computer-aided diagnosis (CAD) nodule detection performance in pediatric chest CT scans , 2017, Medical Imaging.