Frequency-Domain-Based Structure Losses for CycleGAN-Based Cone-Beam Computed Tomography Translation

Sensors, vol. 23, pp. 1089

Abstract

Research exploring CycleGAN-based synthetic image generation has recently accelerated in the medical community due to its ability to leverage unpaired images effectively. However, a commonly established drawback of the CycleGAN, the introduction of artifacts in generated images, makes it unreliable for medical imaging use cases. In an attempt to address this, we explore the effect of structure losses on the CycleGAN and propose a generalized frequency-based loss that aims at preserving the content in the frequency domain. We apply this loss to the use-case of cone-beam computed tomography (CBCT) translation to computed tomography (CT)-like quality. Synthetic CT (sCT) images generated from our methods are compared against baseline CycleGAN along with other existing structure losses proposed in the literature. Our methods (MAE: 85.5, MSE: 20433, NMSE: 0.026, PSNR: 30.02, SSIM: 0.935) quantitatively and qualitatively improve over the baseline CycleGAN (MAE: 88.8, MSE: 24244, NMSE: 0.03, PSNR: 29.37, SSIM: 0.935) across all investigated metrics and are more robust than existing methods. Furthermore, no observable artifacts or loss in image quality were observed. Finally, we demonstrated that sCTs generated using our methods have superior performance compared to the original CBCT images on selected downstream tasks.

Authors 8

1. Suraj Pai corresponding

   Maastricht University Medical Centre

   Affiliation as printed

   GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, 6229 HX Maastricht, The Netherlands

2. Ibrahim Hadžić

   Maastricht University Medical Centre

   Affiliation as printed

   GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, 6229 HX Maastricht, The Netherlands

3. Chinmay Rao Aachen Division of Image Processing (LKEB)

   Leiden University Medical Center

   Affiliation as printed

   Division of Image Processing, Leiden University Medical Center, 2333 ZA Leiden, The Netherlands

4. Ivan Zhovannik

   Maastricht University Medical Centre

   Affiliation as printed

   GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, 6229 HX Maastricht, The Netherlands

5. Andre L.A.J. Dekker

   Maastricht University Medical Centre

   Affiliation as printed

   GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, 6229 HX Maastricht, The Netherlands

6. Alberto Traverso

   Maastricht University Medical Centre

   Affiliation as printed

   GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, 6229 HX Maastricht, The Netherlands

7. Stylianos Asteriadis

   Maastricht University

   Affiliation as printed

   Department of Advanced Computing Sciences, Maastricht University, 6229 EN Maastricht, The Netherlands

8. Enrique Hortal corresponding

   Maastricht University

   Affiliation as printed

   Department of Advanced Computing Sciences, Maastricht University, 6229 EN Maastricht, The Netherlands