{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T04:34:13Z","timestamp":1775277253846,"version":"3.50.1"},"reference-count":37,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T00:00:00Z","timestamp":1673913600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/s23031089","type":"journal-article","created":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T01:33:26Z","timestamp":1674005606000},"page":"1089","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Frequency-Domain-Based Structure Losses for CycleGAN-Based Cone-Beam Computed Tomography Translation"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8043-2230","authenticated-orcid":false,"given":"Suraj","family":"Pai","sequence":"first","affiliation":[{"name":"GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, 6229 HX Maastricht, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8397-5940","authenticated-orcid":false,"given":"Ibrahim","family":"Hadzic","sequence":"additional","affiliation":[{"name":"GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, 6229 HX Maastricht, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2472-2409","authenticated-orcid":false,"given":"Chinmay","family":"Rao","sequence":"additional","affiliation":[{"name":"Division of Image Processing, Leiden University Medical Center, 2333 ZA Leiden, The Netherlands"}]},{"given":"Ivan","family":"Zhovannik","sequence":"additional","affiliation":[{"name":"GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, 6229 HX Maastricht, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0422-7996","authenticated-orcid":false,"given":"Andre","family":"Dekker","sequence":"additional","affiliation":[{"name":"GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, 6229 HX Maastricht, The Netherlands"}]},{"given":"Alberto","family":"Traverso","sequence":"additional","affiliation":[{"name":"GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, 6229 HX Maastricht, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4298-6870","authenticated-orcid":false,"given":"Stylianos","family":"Asteriadis","sequence":"additional","affiliation":[{"name":"Department of Advanced Computing Sciences, Maastricht University, 6229 EN Maastricht, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2119-4169","authenticated-orcid":false,"given":"Enrique","family":"Hortal","sequence":"additional","affiliation":[{"name":"Department of Advanced Computing Sciences, Maastricht University, 6229 EN Maastricht, The Netherlands"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1259\/dmfr\/30642039","article-title":"Artefacts in CBCT: A review","volume":"40","author":"Schulze","year":"2011","journal-title":"Dentomaxillofac. Radiol."},{"key":"ref_2","first-page":"e778","article-title":"Cone Beam CT vs. Fan Beam CT: A Comparison of Image Quality and Dose Delivered Between Two Differing CT Imaging Modalities","volume":"8","author":"Lechuga","year":"2016","journal-title":"Cureus"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5634","DOI":"10.1118\/1.3497272","article-title":"Combining scatter reduction and correction to improve image quality in cone-beam computed tomography (CBCT)","volume":"37","author":"Jin","year":"2010","journal-title":"Med. Phys."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1007\/s00066-015-0890-7","article-title":"Vergleich unterschiedlicher CT-Kalibrierungsmethoden zur Dosisberechnung auf Basis der Kegelstrahlcomputertomographie","volume":"191","author":"Dunlop","year":"2015","journal-title":"Strahlenther. Und Onkol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1354","DOI":"10.1118\/1.4908223","article-title":"Investigating CT to CBCT image registration for head and neck proton therapy as a tool for daily dose recalculation","volume":"42","author":"Landry","year":"2015","journal-title":"Med. Phys."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1736","DOI":"10.1118\/1.4943796","article-title":"A model-based scatter artifacts correction for cone beam CT","volume":"43","author":"Zhao","year":"2016","journal-title":"Med. Phys."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_8","first-page":"e2548","article-title":"Cone Beam Computed Tomography Image Quality Improvement Using a Deep Convolutional Neural Network","volume":"10","author":"Kida","year":"2018","journal-title":"Cureus"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"035011","DOI":"10.1088\/1361-6560\/aaf496","article-title":"Corrigendum: Comparing Unet training with three different datasets to correct CBCT images for prostate radiotherapy dose calculations","volume":"64","author":"Landry","year":"2019","journal-title":"Phys. Med. Biol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"035003","DOI":"10.1088\/1361-6560\/ab6240","article-title":"Convolutional neural network enhancement of fast-scan low-dose cone-beam CT images for head and neck radiotherapy","volume":"65","author":"Yuan","year":"2020","journal-title":"Phys. Med. Biol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"095002","DOI":"10.1088\/1361-6560\/ab7d54","article-title":"Comparison of CBCT based synthetic CT methods suitable for proton dose calculations in adaptive proton therapy","volume":"65","author":"Thummerer","year":"2020","journal-title":"Phys. Med. Biol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., and Efros, A.A. (2017, January 21\u201326). Image-To-Image Translation With Conditional Adversarial Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2816","DOI":"10.1002\/mp.14624","article-title":"Improving CBCT quality to CT level using deep learning with generative adversarial network","volume":"48","author":"Zhang","year":"2021","journal-title":"Med. Phys."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"5130","DOI":"10.1002\/mp.15083","article-title":"Multitask 3D CBCT-to-CT translation and organs-at-risk segmentation using physics-based data augmentation","volume":"48","author":"Dahiya","year":"2021","journal-title":"Med. Phys."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1002\/acm2.13176","article-title":"Dosimetric evaluation of synthetic CT image generated using a neural network for MR-only brain radiotherapy","volume":"22","author":"Tang","year":"2021","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22\u201329). Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"225004","DOI":"10.1088\/1361-6560\/ab4d8c","article-title":"CBCT correction using a cycle-consistent generative adversarial network and unpaired training to enable photon and proton dose calculation","volume":"64","author":"Kurz","year":"2019","journal-title":"Phys. Med. Biol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.phro.2020.04.002","article-title":"A single neural network for cone-beam computed tomography-based radiotherapy of head-and-neck, lung and breast cancer","volume":"14","author":"Maspero","year":"2020","journal-title":"Phys. Imaging Radiat. Oncol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2472","DOI":"10.1002\/mp.14121","article-title":"CBCT-based synthetic CT generation using deep-attention cycleGAN for pancreatic adaptive radiotherapy","volume":"47","author":"Liu","year":"2020","journal-title":"Med. Phys."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"3998","DOI":"10.1002\/mp.13656","article-title":"Paired cycle-GAN-based image correction for quantitative cone-beam computed tomography","volume":"46","author":"Harms","year":"2019","journal-title":"Med. Phys."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1016\/j.ejmp.2020.11.007","article-title":"Evaluation of a cycle-generative adversarial network-based cone-beam CT to synthetic CT conversion algorithm for adaptive radiation therapy","volume":"80","author":"Eckl","year":"2020","journal-title":"Phys. Medica"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"998","DOI":"10.1002\/mp.13963","article-title":"Visual enhancement of Cone-beam CT by use of CycleGAN","volume":"47","author":"Kida","year":"2020","journal-title":"Med. Phys."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., and Webb, R. (2017, January 21\u201326). Learning from simulated and unsupervised images through adversarial training. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.241"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yang, H., Sun, J., Carass, A., Zhao, C., Lee, J., Xu, Z., and Prince, J. (2018). Unpaired brain MR-to-CT synthesis using a structure-constrained CycleGAN. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer.","DOI":"10.1007\/978-3-030-00889-5_20"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Jiang, L., Dai, B., Wu, W., and Loy, C.C. (2021, January 10\u201317). Focal frequency loss for image reconstruction and synthesis. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.01366"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"ref_28","unstructured":"Mirza, M., and Osindero, S. (2014). Conditional Generative Adversarial Nets. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.bspc.2016.02.006","article-title":"Review of medical image quality assessment","volume":"27","author":"Chow","year":"2016","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, X., Karaman, S., and Chang, S.F. (2019, January 9\u201312). Detecting and Simulating Artifacts in GAN Fake Images. Proceedings of the 2019 IEEE International Workshop on Information Forensics and Security (WIFS), Delft, The Netherlands.","DOI":"10.1109\/WIFS47025.2019.9035107"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1186\/s41747-020-00173-2","article-title":"Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem","volume":"4","author":"Hofmanninger","year":"2020","journal-title":"Eur. Radiol. Exp."},{"key":"ref_32","unstructured":"Hadzic, I., Pai, S., Rao, C., and Teuwen, J. (2021, September 08). Ganslate-Team\/Ganslate: A Simple and Extensible Gan Image-to-Image Translation Framework. Available online: https:\/\/doi.org\/10.5281\/zenodo.5494572."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Judy, P.F., Balter, S., Bassano, D., McCullough, E.C., Payne, J.T., and Rothenberg, L. (1977). Phantoms for Performance Evaluation and Quality Assurance of CT Scanners, American Association of Physicists in Medicine. Report No. 1. 1977, Diagnostic Radiology Committee Task Force on CT Scanner Phantoms.","DOI":"10.37206\/1"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"45","DOI":"10.3389\/fninf.2013.00045","article-title":"The Design of SimpleITK","volume":"7","author":"Lowekamp","year":"2013","journal-title":"Front. Neuroinform."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Marstal, K., Berendsen, F., Staring, M., and Klein, S. (July, January 26). SimpleElastix: A User-Friendly, Multi-lingual Library for Medical Image Registration. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Las Vegas, NV, USA.","DOI":"10.1109\/CVPRW.2016.78"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., and Ahmadi, S.A. (2016, January 25\u201328). V-net: Fully convolutional neural networks for volumetric medical image segmentation. Proceedings of the 2016 fourth international conference on 3D vision (3DV), Stanford, CA, USA.","DOI":"10.1109\/3DV.2016.79"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Gragnaniello, D., Cozzolino, D., Marra, F., Poggi, G., and Verdoliva, L. (2021). Are GAN generated images easy to detect? A critical analysis of the state-of-the-art. arXiv.","DOI":"10.1109\/ICME51207.2021.9428429"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/3\/1089\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:08:38Z","timestamp":1760119718000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/3\/1089"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,17]]},"references-count":37,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["s23031089"],"URL":"https:\/\/doi.org\/10.3390\/s23031089","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,17]]}}}