{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T10:34:27Z","timestamp":1765190067230,"version":"3.46.0"},"reference-count":47,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"vor","delay-in-days":14,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Kilovoltage cone\u2010beam computed tomography (kV CBCT) is vital for image\u2010guided radiotherapy (IGRT). The new RTI4343iL panel on the Varian TrueBeam LINAC offers higher resolution but requires binning to achieve practical frame rates, leading to projection resolution loss. Existing super\u2010resolution (SR) techniques have been applied to enhance CBCT image quality but primarily operate in the image domain, struggling to restore resolution loss in the projection domain.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This study aimed to evaluate the feasibility of a deep learning (DL) SR model, based on a conditional Generative Adversarial Networks (cGANs) architecture, for enhancing the spatial resolution of CBCT acquired with the new RTI4343iL panel in the projection domain. We hypothesize that projection\u2010domain deblurring will primarily depend on the detector and minimally on patient anatomy, enhancing primary signal resolution without significantly altering scatter distribution. The study quantitatively assessed the impact of SR\u2010enhanced projections on the quality of reconstructed CBCT images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A DLSR model was developed to enhance CBCT resolution in the projection domain. \u00a0For data acquisition, a Varian TrueBeam system equipped with the RTI4343iL panel was used, which features a native high\u2010resolution image size of 2848\u00a0\u00d7\u00a02144 pixels, but operates in 2\u00a0\u00d7\u00a08 binning mode (1424\u00a0\u00d7\u00a0268 pixels) during CBCT scans to mitigate data readout speed limitations. Following thorax CBCT protocols, 576 pairs of CBCT projections were acquired at two resolutions using Rando, Longman, and Steeve phantoms. Of these, 460 pairs were allocated for model training, while 116 were reserved for validation. Model testing involved 144 Dynamic Thorax projections and CBCT reconstructions utilizing Catphan 604 phantoms. The DL SR model was built on a cGANs framework with a U\u2010Net generator. Image enhancement was quantitatively evaluated with metrics including peak signal\u2010to\u2010noise ratio (PSNR), mean square error (MSE), structural similarity index measure (SSIM), feature similarity index measure (FSIM), and mean absolute percentage error (MAPE).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The DL SR model effectively enhanced image resolution, producing SR projections with greater detail and improved structural clarity. Quantitative analysis showed that the SR\u2010enhanced projections outperformed upscaled low\u2010resolution (LR) projections with higher PSNR (44.4\u00a0vs. 43.7,\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&lt;\u00a00.001), lower MSE (187,083.7\u00a0vs. 205,364.4,\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&lt;\u00a00.001), and improved MAPE (7.6%\u00a0vs. 13.5%,\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&lt;\u00a00.001). While SSIM and FSIM values were similar for both methods, the SR\u2010enhanced projections demonstrated a slight advantage, achieving an FSIM of 0.998. Reconstructed CBCT images from SR\u2010enhanced projections exhibited improved spatial resolution as well, increasing from 0.6 lp\/mm to 0.9 lp\/mm on the Catphan 604 phantom image. Enhanced structural detail and sharper intensity profiles in SR CBCT images further validated the model's potential to restore resolution lost during the acquisition process.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study underscores the efficacy of a projection\u2010domain DL SR method for CBCT enhancement. The developed model presents a promising avenue for attaining high\u2010resolution CBCT, potentially benefiting for many clinical applications.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.18000","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T04:35:42Z","timestamp":1752640542000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Super\u2010resolution CBCT on a new generation flat panel imager of a C\u2010arm gantry linear accelerator"],"prefix":"10.1002","volume":"52","author":[{"given":"Licheng","family":"Kuo","sequence":"first","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center  New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feifei","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center  New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yabo","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center  New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center  New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura A.","family":"Cervino","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center  New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean M.","family":"Moran","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center  New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center  New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianfang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center  New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2009.03.059"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12885\u2010016\u20102165\u20109"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prro.2015.10.004"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2015.09.035"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rpor.2015.10.005"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.12659\/PJR.890745"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/53\/17\/021"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.ob013e3181dzfeec"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/55\/22\/001"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4901265"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16734"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3557468"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/55\/22\/007"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12850"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12849"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.2548"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14624"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010020\u201080803\u20102"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15840"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4875978"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13396"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/acae15"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ad40f3"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13246\u2010019\u201000817\u20107"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.14337"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ad3cb0"},{"volume-title":"Computer Vision\u2014ECCV 2014","author":"Dong C","key":"e_1_2_8_28_1"},{"key":"e_1_2_8_29_1","doi-asserted-by":"crossref","unstructured":"LedigC TheisL Husz\u00e1rF et\u00a0al.Photo\u2010realistic single image super\u2010resolution using a generative adversarial network. In:IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE;2017:4681\u20104690. doi:10.1109\/CVPR.2017.19","DOI":"10.1109\/CVPR.2017.19"},{"key":"e_1_2_8_30_1","doi-asserted-by":"crossref","unstructured":"LiangJ CaoJ SunG ZhangK Van GoolL TimofteR.SwinIR: image restoration using Swin transformer. In:Proceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE;2021:1833\u20101844. doi:10.1109\/ICCVW54120.2021.00210","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"e_1_2_8_31_1","doi-asserted-by":"crossref","unstructured":"CondeMV ChoiU BurchiM TimofteR Swin2SR: Swinv2 transformer for compressed image super\u2010resolution and restoration. In:European Conference on Computer Vision.Springer Nature Switzerland;2022:669\u2010687. doi:10.1007\/978\u20103\u2010031\u201025063\u20107_42","DOI":"10.1007\/978-3-031-25063-7_42"},{"key":"e_1_2_8_32_1","unstructured":"ZhangD HuangF LiuS WangX JinZ.SwinFIR: revisiting the SwinIR with fast Fourier convolution and improved training for image super\u2010resolution.arXiv preprint arXiv:220811247.2022. doi:10.48550\/arXiv.2208.11247"},{"key":"e_1_2_8_33_1","unstructured":"BaghelN DubeySR SinghSK.SRTransGAN: image super\u2010resolution using transformer based generative adversarial network.arXiv preprint arXiv:231201999.2023. doi:10.48550\/arXiv.2312.01999"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.irbm.2020.08.004"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.08.110"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489\u2010023\u201004566\u20109"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107590"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16825"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10439\u2010024\u201003450\u2010y"},{"key":"e_1_2_8_40_1","doi-asserted-by":"crossref","unstructured":"IsolaP ZhuJ ZhouT EfrosAA Image\u2010to\u2010image translation with conditional adversarial networks. In:2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE;2017:1125\u20101134. doi:10.1109\/CVPR.2017.632","DOI":"10.1109\/CVPR.2017.632"},{"volume-title":"Generative adversarial nets","year":"2014","author":"Goodfellow I","key":"e_1_2_8_41_1"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.01703"},{"key":"e_1_2_8_43_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT U\u2010Net: convolutional networks for biomedical image segmentation. In:International Conference on Medical Image Computing and Computer\u2010assisted Intervention.Springer;2015:234\u2010241. doi:10.1007\/978\u20103\u2010319\u201024574\u20104_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2109730"},{"key":"e_1_2_8_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2022.08.013"},{"key":"e_1_2_8_46_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.597866"},{"key":"e_1_2_8_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2827462"},{"key":"e_1_2_8_48_1","doi-asserted-by":"crossref","unstructured":"PhamCH DucournauA FabletR RousseauF.Brain MRI super\u2010resolution using deep 3D convolutional networks. In:2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).IEEE;2017:197\u2010200. doi:10.1109\/ISBI.2017.7950500","DOI":"10.1109\/ISBI.2017.7950500"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.18000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T10:29:46Z","timestamp":1765189786000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.18000"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":47,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.1002\/mp.18000"],"URL":"https:\/\/doi.org\/10.1002\/mp.18000","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"type":"print","value":"0094-2405"},{"type":"electronic","value":"2473-4209"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"2025-03-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e18000"}}