Physics and Imaging in Radiation Oncology最新文献

{"title":"Comparison of online adaptive and non-adaptive magnetic resonance image-guided radiation therapy in prostate cancer using dose accumulation","authors":"","doi":"10.1016/j.phro.2024.100662","DOIUrl":"10.1016/j.phro.2024.100662","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Conventional image-guided radiotherapy (conv-IGRT) is standard in prostate cancer (PC) but does not account for inter-fraction anatomical changes. Online-adaptive magnetic resonance-guided RT (OA-MRgRT) may improve organ-at-risk (OARs) sparing and clinical target volume (CTV) coverage. The aim of this study was to analyze accumulated OAR and target doses in PC after OA-MRgRT and conv-IGRT in comparison to pre-treatment reference planning (refPlan).</div></div><div><h3>Material and methods</h3><div>Ten patients with PC, previously treated with OA-MRgRT at the 1.5 T MR-Linac (20x3Gy), were included. Accumulated OA-MRgRT doses were determined by deformably registering all fraction’s MR-images. Conv-IGRT was simulated through rigid registration of the planning computed tomography with each fraction’s MR-image for dose mapping/accumulation. Dose-volume parameters (DVPs), including CTV D50% and D98%, rectum, bladder, urethra, Dmax and V56Gy for OA-MRgRT, conv-IGRT and refPlan were compared using the Wilcoxon signed-rank test. Clinical relevance of accumulated dose differences was analyzed using a normal-tissue complication-probability model.</div></div><div><h3>Results</h3><div>CTV-DVPs were comparable, whereas OA-MRgRT yielded decreased median OAR-DVPs compared to conv-IGRT, except for bladder V56Gy. OA-MRgRT demonstrated significantly lower median rectum Dmax over conv-IGRT (59.1/59.9 Gy, p = 0.006) and refPlan (60.1 Gy, p = 0.012). Similarly, OA-MRgRT yielded reduced median bladder Dmax compared to conv-IGRT (60.0/60.4 Gy, p = 0.006), and refPlan (61.2 Gy, p = 0.002). Overall, accumulated dose differences were small and did not translate into clinically relevant effects.</div></div><div><h3>Conclusion</h3><div>Deformably accumulated OA-MRgRT using 20x3Gy in PC showed significant but small dosimetric differences comparted to conv-IGRT. Feasibility of a dose accumulation methodology was demonstrated, which may be relevant for evaluating future hypo-fractionated OA-MRgRT approaches.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Results of 2023 survey on the use of synthetic computed tomography for magnetic resonance Imaging-only radiotherapy: Current status and future steps","authors":"","doi":"10.1016/j.phro.2024.100652","DOIUrl":"10.1016/j.phro.2024.100652","url":null,"abstract":"<div><h3>Background and purpose</h3><div>The emergence of synthetic CT (sCT) in MR-guided radiotherapy (MRgRT) represents a significant advancement, supporting MR-only workflows and online treatment adaptation. However, the lack of consensus guidelines has led to varied practices. This study reports results from a 2023 ESTRO survey aimed at defining current practices in sCT development and use.</div></div><div><h3>Materials and methods</h3><div>An survey was distributed to ESTRO members, including 98 questions across four sections on sCT algorithm generation and usage. By June 2023, 100 centers participated. The survey revealed diverse clinical experiences and roles, with primary sCT use in the pelvis (60%), brain (15%), abdomen (11%), thorax (8%), and head-and-neck (6%). sCT was mostly used for conventional fractionation treatments (68%), photon SBRT (40%), and palliative cases (28%), with limited use in proton therapy (4%).</div></div><div><h3>Results</h3><div>Conditional GANs and GANs were the most used neural network architectures, operating mainly on 1.5 T and 3 T MRI images. Less than half used paired images for training, and only 20% performed image selection. Key MR image quality parameters included magnetic field homogeneity and spatial integrity. Half of the respondents lacked a dedicated sCT-QA program, and many did not apply sanitychecks before calculation. Selection strategies included age, weight, and metal artifacts. A strong consensus (95%) emerged for vendor neutral guidelines.</div></div><div><h3>Conclusion</h3><div>The survey highlights the need for expert-based, vendor-neutral guidelines to standardize sCT tools, metrics, and clinical protocols, ensuring effective sCT use in MR-guided radiotherapy.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142357220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of deep learning-based target auto-segmentation for Magnetic Resonance Imaging-guided cervix brachytherapy","authors":"","doi":"10.1016/j.phro.2024.100669","DOIUrl":"10.1016/j.phro.2024.100669","url":null,"abstract":"<div><h3>Background and purpose</h3><div>The target structures for cervix brachytherapy are segmented by radiation oncologists using imaging and clinical information. At the first fraction, this is performed manually from scratch. For subsequent fractions the first fraction segmentations are rigidly propagated and edited manually. This process is time-consuming while patients wait immobilized. In this work, we evaluate the potential clinical impact of using population-based and patient-specific auto-segmentations as a starting point for target segmentation of the second fraction.</div></div><div><h3>Materials and method</h3><div>For twenty-eight patients with locally advanced cervical cancer, treated with MRI-guided brachytherapy, auto-segmentations were retrospectively generated for the second fraction image using two approaches: 1) population-based model, 2) patient-specific models fine-tuned on first fraction information. A radiation oncologist manually edited the auto-segmentations to assess model-induced bias. Pairwise geometric and dosimetric comparisons were performed for the automatic, edited and clinical structures. The time spent editing the auto-segmentations was compared to the current clinical workflow.</div></div><div><h3>Results</h3><div>The edited structures were more similar to the automatic than to the clinical structures. The geometric and dosimetric differences between the edited and the clinical structures were comparable to the inter-observer variability investigated in literature. Editing the auto-segmentations was faster than the manual segmentation performed during our clinical workflow. Patient-specific auto-segmentations required less edits than population-based structures.</div></div><div><h3>Conclusions</h3><div>Auto-segmentation introduces a bias in the manual delineations but this bias is clinically irrelevant. Auto-segmentation, particularly patient-specific fine-tuning, is a time-saving tool that can improve treatment logistics and therefore reduce patient burden during the second fraction of cervix brachytherapy.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic segmentation for magnetic resonance imaging guided individual elective lymph node irradiation in head and neck cancer patients","authors":"","doi":"10.1016/j.phro.2024.100655","DOIUrl":"10.1016/j.phro.2024.100655","url":null,"abstract":"<div><h3>Background and purpose</h3><div>In head and neck squamous cell carcinoma (HNSCC) patients, the radiation dose to nearby organs at risk can be reduced by restricting elective neck irradiation from lymph node levels to individual lymph nodes. However, manual delineation of every individual lymph node is time-consuming and error prone. Therefore, automatic magnetic resonance imaging (MRI) segmentation of individual lymph nodes was developed and tested using a convolutional neural network (CNN).</div></div><div><h3>Materials and methods</h3><div>In 50 HNSCC patients (UMC-Utrecht), individual lymph nodes located in lymph node levels Ib-II-III-IV-V were manually segmented on MRI by consensus of two experts, obtaining ground truth segmentations. A 3D CNN (nnU-Net) was trained on 40 patients and tested on 10. Evaluation metrics were Dice Similarity Coefficient (DSC), recall, precision, and F1-score. The segmentations of the CNN was compared to segmentations of two observers. Transfer learning was used with 20 additional patients to re-train and test the CNN in another medical center.</div></div><div><h3>Results</h3><div>nnU-Net produced automatic segmentations of elective lymph nodes with median DSC: 0.72, recall: 0.76, precision: 0.78, and F1-score: 0.78. The CNN had higher recall compared to both observers (p = 0.002). No difference in evaluation scores of the networks in both medical centers was found after re-training with 5 or 10 patients.</div></div><div><h3>Conclusion</h3><div>nnU-Net was able to automatically segment individual lymph nodes on MRI. The detection rate of lymph nodes using nnU-Net was higher than manual segmentations. Re-training nnU-Net was required to successfully transfer the network to the other medical center.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Monte Carlo simulated correction factors for high dose rate brachytherapy postal dosimetry audit methodology","authors":"","doi":"10.1016/j.phro.2024.100657","DOIUrl":"10.1016/j.phro.2024.100657","url":null,"abstract":"<div><h3>Background and Purpose</h3><div>Full-scatter conditions in water are impractical for postal dosimetry audits in brachytherapy. This work presents a method to obtain correction factors that account for deviations from full-scatter water-equivalent conditions for a small plastic phantom.</div></div><div><h3>Material and Methods</h3><div>A 16 × 8 × 3 cm phantom (PMMA) with a radiophotoluminescent dosimeter (RPLD) at the centre and two catheters on either side was simulated using Monte Carlo (MC) to calculate correction factors accounting for the lack of scatter, non-water equivalence of the RPLD and phantom, source model and backscatter for HDR ⁶⁰Co and ¹⁹²Ir sources.</div></div><div><h3>Results</h3><div>The correction factors for non-water equivalence, lack of full scatter, and the use of PMMA were 1.062 ± 0.013, 1.059 ± 0.008 and 0.993 ± 0.009 for ¹⁹²Ir and 1.129 ± 0.005, 1.009 ± 0.005 and 1.005 ± 0.005 for ⁶⁰Co respectively. Water-equivalent backscatter thickness of 5 cm was found to be adequate and increasing thickness of backscatter did not have an influence on the RPLD dose. The mean photon energy in the RPLD for four HDR ¹⁹²Ir sources was 279 ± 2 keV in full scatter conditions and 295 ± 1 keV in the audit conditions. For ⁶⁰Co source the corresponding mean energies were 989 ± 1 keV and 1022 ± 1 keV respectively.</div></div><div><h3>Conclusions</h3><div>Correction factors were obtained through the MC simulations for conditions deviating from TG-43, including the amount of back scatter, and the optimum audit set up. Additionally, the influence of different source models on the correction factors was negligible and demonstrates their generic applicability.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142560794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accuracy, repeatability, and reproducibility of water-fat magnetic resonance imaging in a phantom and healthy volunteer","authors":"","doi":"10.1016/j.phro.2024.100651","DOIUrl":"10.1016/j.phro.2024.100651","url":null,"abstract":"<div><div>Bone marrow (BM) damage due to chemoradiotherapy can increase BM fat in cervical cancer patients. Water-fat magnetic resonance (MR) scans were performed on a phantom and a healthy female volunteer to validate proton density fat fraction accuracy, reproducibility, and repeatability across different vendors, field strengths, and protocols. Phantom measurements showed a high accuracy, high repeatability, and excellent reproducibility. Volunteer measurements had an excellent intra- and interreader reliability, good repeatability, and moderate to good reproducibility. Water-fat MRI show potential for quantification of longitudinal vertebral BM fat changes. Further studies are needed to validate and extend these findings for broader clinical applicability.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparing robust proton versus online adaptive photon radiotherapy for short-course treatment of rectal cancer","authors":"","doi":"10.1016/j.phro.2024.100663","DOIUrl":"10.1016/j.phro.2024.100663","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Image-guided proton beam therapy (IG-PBT) and cone-beam CT (CBCT)-based online adaptive photon radiotherapy (oART) have potentials to restrict radiation toxicity. They are both hypothesised to reduce therapy limiting bowel toxicity in the multimodality treatment of locally advanced rectal cancer (LARC). This study aimed to quantify the difference in relevant dose-volume metrics for these modalities.</div></div><div><h3>Material and Methods</h3><div>Six-degrees-of-freedom IG-PBT and oART short-course radiotherapy (SCRT) were simulated for 18 LARC patients. Relative biological effectiveness (RBE) was 1.1 for IG-PBT. Delivered dose was evaluated using post-CBCTs. Target coverage was considered robust if average dose to 99% of the clinical target volume was <span><math><mrow><mo>≥</mo></mrow></math></span> 95% of the prescription. Organ at risk (OAR) doses were compared using dose-volume histograms and severe bowel toxicity estimated using dose–response modelling.</div></div><div><h3>Results</h3><div>Target coverage was robust in all patients for oART and all but one patient for IG-PBT. For the main OARs, IG-PBT increased the volume exposed to <span><math><mrow><mo>≥</mo></mrow></math></span> 15 Gy (RBE), but reduced volumes exposed to lower doses. Both low- and high-dose exposure to bowel loops were significantly different between the modalities (median (interquartile range) IG-PBT-V_8.9Gy(RBE) = 92 (51–156) cm³, oART-V_8.9Gy(RBE) = 166 (107–234) cm³, p &lt; 0.001; IG-PBT-V_23Gy(RBE) = 62 (25–106) cm³, oART-V_23Gy(RBE) = 38 (18–75) cm³, p &lt; 0.001), translating into similar total grade ≥ 3 bowel toxicity risk.</div></div><div><h3>Conclusion</h3><div>IG-PBT and oART delivered comparable and satisfying target coverage in SCRT for LARC with similar estimated risk of severe bowel toxicity. Volumes of OAR exposed to 15 Gy (RBE) or more were reduced by oART, while IG-PBT reduced the volumes receiving doses below this level.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and international multicentre pilot testing of a postal dosimetry audit methodology for high dose rate brachytherapy","authors":"","doi":"10.1016/j.phro.2024.100665","DOIUrl":"10.1016/j.phro.2024.100665","url":null,"abstract":"<div><h3>Background and Purpose</h3><div>Dosimetry audits are essential for reducing errors in brachytherapy. A postal dosimetry audit methodology was developed and tested in an international multicentre pilot, to assess the accuracy of the Reference Air Kerma Rate of ¹⁹²Ir and ⁶⁰Co brachytherapy sources.</div></div><div><h3>Materials and Methods</h3><div>A compact phantom made of polymethyl methacrylate was developed to accommodate two catheters, a radiophotoluminescence dosimeter (RPLD) for dose measurements and a Gafchromic (RTQA2) film strip for source position verification. Deviations of the audit setup from TG-43 conditions were quantified experimentally and compared to previous Monte Carlo (MC) simulations. A measurement uncertainty budget was estimated for the RPLD analysis. The methodology was tested in an international pilot study consisting of 59 dosimeter sets among 48 centres from 11 countries.</div></div><div><h3>Results</h3><div>The experimental correction factors showed good agreement with previous MC simulations, and the total correction factor accounting for non-water equivalence, lack of scatter and beam quality was found to be 1.029 ± 0.009 for ¹⁹²Ir and 1.059 ± 0.007 for ⁶⁰Co sources, to be employed in audit measurement. The total uncertainty budget was estimated to be 2.24 % (k = 1). In the multicentre study, the ratio between measured and reported user dose ranged from 0.968 to 1.049, with all irradiated dosimeter sets within ± 5 %, and 54 out of 59 within ± 3 %.</div></div><div><h3>Conclusions</h3><div>The methodology was tested in an international multicentre pilot study and has shown good performance validating the uncertainty budget.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Head and neck automatic multi-organ segmentation on Dual-Energy Computed Tomography","authors":"","doi":"10.1016/j.phro.2024.100654","DOIUrl":"10.1016/j.phro.2024.100654","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Deep-learning-based automatic segmentation is widely used in radiation oncology to delineate organs-at-risk. Dual-energy CT (DECT) allows the reconstruction of enhanced contrast images that could help with manual and auto-delineation. This paper presents a performance evaluation of a commercial auto-segmentation software on image series generated by a DECT.</div></div><div><h3>Material and methods</h3><div>Different types of DECT images from seventy four head-and-neck (HN) patients were retrieved, including polyenergetic images at different voltages [80 kV reconstructed with a kernel corresponding to the commercial algorithm DirectDensity™ (PEI80-DD), 80 kV (PEI80), 120 kV-mixed (PEI120)] and a virtual-monoenergetic image at 40 keV (VMI40). Delineations used for treatment planning were considered as ground truth (GT) and were compared with the auto-segmentations performed on the 4 DECT images. A blinded qualitative evaluation of 3 structures (thyroid, left parotid, left nodes level II) was carried out. Performance metrics were calculated for thirteen HN structures to evaluate the auto-contours including dice similarity coefficient (DSC), 95th percentile Hausdorff distance (95HD) and mean surface distance (MSD).</div></div><div><h3>Results</h3><div>We observed a high rate of low scores for PEI80-DD and VMI40 auto-segmentations on the thyroid and for GT and VMI40 contours on the nodes level II. All images received excellent scores for the parotid glands. The metrics comparison between GT and auto-segmented contours revealed that PEI80-DD had the highest DSC scores, significantly outperforming other reconstructed images for all organs (p &lt; 0.05).</div></div><div><h3>Conclusions</h3><div>The results indicate that the auto-contouring system cannot generalize to images derived from DECT acquisition. It is therefore crucial to identify which organs benefit from these acquisitions to adapt the training datasets accordingly.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142421243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Proton dose calculation on cone-beam computed tomography using unsupervised 3D deep learning networks","authors":"","doi":"10.1016/j.phro.2024.100658","DOIUrl":"10.1016/j.phro.2024.100658","url":null,"abstract":"<div><h3>Background and Purpose</h3><div>Poor image quality of cone-beam computed tomography (CBCT) images can hinder proton dose calculation to assess the influence of anatomy changes. The aim of this study was to evaluate image quality and proton dose calculation accuracy of synthetic CTs generated from CBCT using unsupervised 3D deep-learning networks.</div></div><div><h3>Materials and methods</h3><div>A total of 102 head-and-neck cancer patients were used to train (N=82) and test (N=20) i) a cycle-consistent generative adversarial network, ii) a contrastive unpaired translation, and iii) a fusion of the two (CycleCUT). For patients in the test set, a repeat CT was deformably registered to a same-day CBCT to create a ground-truth CT for comparison. The proton plan was re-calculated on the ground-truth CT and synthetic CTs. The image quality of the synthetic CTs was evaluated using peak signal-to-noise ratio, structural similarity index measure, mean error, and mean absolute error (MAE). Proton dose calculation accuracy was assessed through 3D gamma analysis and dose-volume-histogram parameters.</div></div><div><h3>Results</h3><div>All synthetic CTs accurately preserved the CBCT anatomy (verified by visual inspection) while improving the image quality. The CycleCUT network had slightly improved image quality compared to the other networks (MAE in body: 53 Hounsfield units (HU) vs. 54/55 HU). All networks had similar proton dose calculation accuracy with gamma passing rate above 97%.</div></div><div><h3>Conclusions</h3><div>All three evaluated networks generated synthetic CT images with dose distributions comparable to those of conventional fan-beam CT. The synthetic CT generation was fast, making all networks feasible for adaptive proton therapy.</div></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142560603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}