Recently, deep learning (DL)-based methods for the generation of synthetic computed tomography (sCT) have received significant research attention as an alternative to classical ones. We present here a systematic review of these methods by grouping them into three categories, according to their clinical applications: I) To replace CT in magnetic resonance (MR)-based treatment planning. II) Facilitate cone-beam computed tomography (CBCT)-based image-guided adaptive radiotherapy. III) Derive attenuation maps for the correction of positron emission tomography (PET). Appropriate database searching was performed on journal articles published between January 2014 and December 2020. The DL methods' key characteristics were extracted from each eligible study, and a comprehensive comparison among network architectures and metrics was reported. A detailed review of each category was given, highlighting essential contributions, identifying specific challenges, and summarising the achievements. Lastly, the statistics of all the cited works from various aspects were analysed, revealing the popularity and future trends, and the potential of DL-based sCT generation. The current status of DL-based sCT generation was evaluated, assessing the clinical readiness of the presented methods.
University of California Los Angeles（加利福尼亚大学洛杉矶分校）；Duke University Medical Center（杜克大学医学中心）
This paper develops a method of biologically guided deep learning for post-radiation FDG-PET image outcome prediction based on pre-radiation images and radiotherapy dose information. Based on the classic reaction-diffusion mechanism, a novel biological model was proposed using a partial differential equation that incorporates spatial radiation dose distribution as a patient-specific treatment information variable. A 7-layer encoder-decoder-based convolutional neural network (CNN) was designed and trained to learn the proposed biological model. As such, the model could generate post-radiation F…
The RefleXion X1 is the first biology-guided radiotherapy (BgRT) system. Its dual 90-degree PET detector collects fewer pair production events compared to a full-ring diagnostic PET system. In the proposed BgRT workflow, a short scan is acquired before treatment delivery to ensure image quality and consistency. The shorter scan time, a quarter of the simulation scan time, also leads to fewer coincidence events and hence reduced image quality. In this study, we proposed a patient-specific mean teacher UNet (MT-UNet) to enhance PET image quality and low-dose PET reconstruction on RefleXion X1. P…
Electron density maps must be accurately estimated to achieve valid dose calculation in MR-only radiotherapy. The goal of this study is to assess whether two deep learning models, the conditional generative adversarial network (cGAN) and the cycle-consistent generative adversarial network (cycleGAN), can generate accurate abdominal synthetic CT (sCT) images from 0.35T MR images for MR-only liver radiotherapy. A retrospective study was performed using CT images and 0.35T MR images of 12 patients with liver (n=8) and non-liver abdominal (n=4) cancer. CT images were deformably registered to the c…
Purpose: Beam range control is the essence of radiotherapy with heavy charged particles. In conventional broad-beam delivery, fine range adjustment is achieved by insertion of range shifting and compensating materials. In dosimetry, solid phantoms are often used for convenience. These materials should ideally be equivalent to water. In this study, we evaluated dosimetric water equivalence of four common plastics, HDPE, PMMA, PET, and POM. Methods: Using the Bethe formula for energy loss, the Gottschalk formula for multiple scattering, and the Sihver formula for nuclear interactions, we calcula…
Purpose: Organ-at-risk (OAR) delineation is a key step for cone-beam CT (CBCT) based adaptive radiotherapy planning that can be a time-consuming, labor-intensive, and subject-to-variability process. We aim to develop a fully automated approach aided by synthetic MRI for rapid and accurate CBCT multi-organ contouring in head-and-neck (HN) cancer patients. MRI has superb soft-tissue contrasts, while CBCT offers bony-structure contrasts. Using the complementary information provided by MRI and CBCT is expected to enable accurate multi-organ segmentation in HN cancer patients. In our proposed metho…
To enable magnetic resonance (MR)-only radiotherapy and facilitate modelling of radiation attenuation in humans, synthetic-CT (sCT) images need to be generated. Considering the application of MR-guided radiotherapy and online adaptive replanning, sCT generation should occur within minutes. This work aims at assessing whether an existing deep learning network can rapidly generate sCT images to be used for accurate MR-based dose calculations in the entire pelvis. A study was conducted on data of 91 patients with prostate, rectal and cervical cancer who underwent external beam radiotherapy acquir…
Dose painting of hypoxic tumour sub-volumes using positron-emission tomography (PET) has been shown to improve tumour control in silico in several sites. Pancreatic cancer presents a more stringent challenge, given its proximity to critical organs-at-risk (OARs) and anatomic motion. A radiobiological model was developed to estimate clonogen survival fraction (SF), using 18F-fluoroazomycin arabinoside PET (FAZA PET) images from ten patients with pancreatic cancer to quantify oxygen enhancement effects. For each patient, four simulated five-fraction stereotactic body radiotherapy (SBRT) plans we…
SynthRAD2025 Grand Challenge dataset: generating synthetic CTs for radiotherapy
LMU University Hospital, LMU Munich（慕尼黑大学附属医院，慕尼黑大学）；Radboud University Medical Center（拉德堡德大学医学中心）；University Medical Center Groningen, University of Groningen（格罗宁根大学医学中心，格罗宁根大学）；University Hospital of Cologne（科隆大学附属医院）；University Medical Center Utrecht（乌得勒支大学医学中心）；German Cancer Consortium (DKTK)（德国癌症联盟）；Bavarian Cancer Research Center (BZKF)（巴伐利亚癌症研究中心）；Skåne University Hospital（斯科讷大学医院）；Lund University（隆德大学）；Deutsches Krebsforschungszentrum (DKFZ)（德国癌症研究中心）
SynthRAD2023 Grand Challenge dataset: generating synthetic CT for radiotherapy
University Medical Center Groningen, University of Groningen（格罗宁根大学医学中心，格罗宁根大学）；Radboud University Medical Center（拉德堡德大学医学中心）；University Medical Center Utrecht（乌得勒支大学医学中心）
Purpose: This study assessed the dosimetric accuracy of synthetic CT images generated from magnetic resonance imaging (MRI) data for focal brain radiation therapy, using a deep learning approach. Material and Methods: We conducted a study in 77 patients with brain tumors who had undergone both MRI and computed tomography (CT) imaging as part of their simulation for external beam treatment planning. We designed a generative adversarial network (GAN) to generate synthetic CT images from MRI images. We used Mutual Information (MI) as the loss function in the generator to overcome the misalignment…
An MRI-only adaptive radiotherapy (ART) workflow is desirable for managing interfractional changes in anatomy, but producing synthetic CT (sCT) data through paired data-driven deep learning (DL) for abdominal dose calculations remains a challenge due to the highly variable presence of intestinal gas. We present the preliminary dosimetric evaluation of our novel approach to sCT reconstruction that is well suited to handling intestinal gas in abdominal MRI-only ART. We utilize a paired data DL approach enabled by the intensity projection prior, in which well-matching training pairs are created b…
University of California, San Francisco（加州大学旧金山分校）；University of New Mexico（新墨西哥大学）；Washington University（华盛顿大学）；University of Iowa（爱荷华大学）；University of Washington（华盛顿大学）
Historically, patient datasets have been used to develop and validate various reconstruction algorithms for PET/MRI and PET/CT. To enable such algorithm development, without the need for acquiring hundreds of patient exams, in this paper we demonstrate a deep learning technique to generate synthetic but realistic whole-body PET sinograms from abundantly-available whole-body MRI. Specifically, we use a dataset of 56 $^{18}$F-FDG-PET/MRI exams to train a 3D residual UNet to predict physiologic PET uptake from whole-body T1-weighted MRI. In training we implemented a balanced loss function to gene…
University of British Columbia Data Science Institute（不列颠哥伦比亚大学数据科学研究所）；BC Cancer Research Institute（不列颠哥伦比亚省癌症研究所）；University of British Columbia（不列颠哥伦比亚大学）
Training computer-vision related algorithms on medical images for disease diagnosis or image segmentation is difficult due to the lack of training data, labeled samples, and privacy concerns. For this reason, a robust generative method to create synthetic data is highly sought after. However, most three-dimensional image generators require additional image input or are extremely memory intensive. To address these issues we propose adapting video generation techniques for 3-D image generation. Using the temporal GAN (TGAN) architecture, we show we are able to generate realistic head and neck PE…
Development of an Unpaired Deep Neural Network for Synthesizing X-ray Fluoroscopic Images from Digitally Reconstructed Tomography in Image Guided Radiotherapy
Institute for Quantum Medical Science, National Institutes for Quantum Science and Technology（量子科学技术研究开发机构量子医疗科学研究所）；Graduate School of Science and Engineering, Chiba University（千叶大学大学院理工学研究科）；Graduate School of Engineering, Chiba University（千叶大学大学院工学研究科）；QST hospital, National Institutes for Quantum Science and Technology（量子科学技术研究开发机构QST医院）
Catching magnetic resonance imaging outliers in artificial intelligence-supported radiotherapy workflows: unsupervised detection and localization of image anomalies using deep learning
Physics and Imaging in Radiation Oncology (phiRO)（物理与放射治疗成像（phiRO））
Currently, MRI-only radiotherapy (RT) eliminates some of the concerns about using CT images in RT chains such as the registration of MR images to a separate CT, extra dose delivery, and the additional cost of repeated imaging. However, one remaining challenge is that the signal intensities of MRI are not related to the attenuation coefficient of the biological tissue. This work compares the performance of two state-of-the-art deep learning models; a generative adversarial network (GAN) and a residual network (ResNet) for synthetic CTs (sCT) generation from MR images. The brain MR and CT images…
Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report
Radiation Physics, Department of Hematology, Oncology；Radiation Physics, Skåne University Hospital, Lund, Sweden；Medical Radiation Physics, Department of Clinical Sciences Lund, Lund University, Lund, Sweden；Radiotherapy Department, University Medical Center Utrecht, Utrecht, The Netherlands；Computational Imaging Group for MR Diagnostics \& Therapy, University Medical Center Utrecht, Utrecht, The Netherlands；Division of Medical Physics in Radiation Oncology, Deutsches Krebsforschungszentrum (DKFZ), Heidelberg, Germany；Heidelberg Institute for Radiation Oncology (HIRO)；National Center for Radiation Research in Oncology (NCRO), Heidelberg, Germany；Department of Radiation Oncology；Cyberknife Center, University Hospital of Cologne, Cologne, Germany；Department of Radiation Oncology, Radboud University Medical Center, Nijmegen, The Netherlands；Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands；Department of Radiation Oncology, LMU University Hospital, LMU Munich, Munich, Germany；Bavarian Cancer Research Center (BZKF), Munich, Germany；Australian eHealth Research Center, CSIRO, Brisbane, Australia；School of Computer Science, University of Sydney, Sydney, Australia；Department of Orthodontics；Pattern Recognition Lab, FAU Erlangen-Nuremberg, Germany；RIKEN Center for Integrative Medical Sciences, Tokyo, Japan；Erasmus Mundus Joint Master's Degree IPCVai, University of Bordeaux, France；Computer Science, Huazhong University of Science；Huazhong University of Science；Canon Medical Systems (China) CO., LTD., Beijing, China；Department of Radiation Oncology, Inselspital, Bern University Hospital；University of Bern, Bern, Switzerland
University College London（伦敦大学学院）；King's College London（伦敦国王学院）
Attenuation correction is an essential requirement of positron emission tomography (PET) image reconstruction to allow for accurate quantification. However, attenuation correction is particularly challenging for PET-MRI as neither PET nor magnetic resonance imaging (MRI) can directly image tissue attenuation properties. MRI-based computed tomography (CT) synthesis has been proposed as an alternative to physics based and segmentation-based approaches that assign a population-based tissue density value in order to generate an attenuation map. We propose a novel deep fully convolutional neural ne…
To achieve magnetic resonance (MR)-only radiotherapy, a method needs to be employed to estimate a synthetic CT (sCT) for generating electron density maps and patient positioning reference images. We investigated 2D and 3D convolutional neural network (CNN) methods to generate a male pelvic sCT using a T1-weighted MR image. A retrospective study was performed using CTs and T1-weighted MR images of 20 prostate cancer patients. The proposed 2D CNN model, which contained 27 convolutional layers, was modified from the SegNet for better performance. 3D version of the CNN model was also developed. Bo…
COBRA2026: a large-scale multicenter pelvic cone-beam computed tomography projection dataset
University of Bern（伯尔尼大学）；LMU Munich（慕尼黑大学）；University Hospital of Cologne（科隆大学医院）；University Medical Center Utrecht（乌得勒支大学医学中心）；Medical University of Graz（格拉茨医科大学）；Lund University（隆德大学）；Skåne University Hospital（斯卡奈大学医院）
