{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T12:39:40Z","timestamp":1792154380668,"version":"4.4.0"},"reference-count":29,"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>Projection interpolation can be used to reduce streak artifacts caused by sparse sampling in cone\u2010beam computed tomography (CBCT) image reconstruction. Conventional analytical interpolation methods create additional blur and artifacts at locations away from the centers of reconstructed CBCT image slices. We hypothesize that the deep learning (DL) interpolation technique may mitigate these limitations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>The purpose of this study is to develop a DL\u2010based technique that interpolates sparsely sampled real patient CBCT projections before reconstruction and post\u2010process reconstructed images for improved image quality and reduced patient imaging dose.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Real patient CBCT projections are acquired from projection angles that are not exactly evenly spread. The proposed method first linearly interpolates under\u2010sampled projections according to densely sampled angles. Each set of projections is a projection stack of three axes: x, y, and z that represent width, height, and number of projections. The proposed technique re\u2010slices the stack of interpolated projections along y\u2010axis, and each acquired x\u2010z plane slice is processed by a deep residual U\u2010Net (DRU) model to augment the slice's image quality. The resulting slices are reassembled into a stack of densely\u2010sampled projections to be reconstructed into a CBCT volume with the FDK algorithm. A second DRU model further post\u2010processes the reconstructed CBCT volume to improve the image quality. The proposed technique is compared with conventional linear interpolation on sparsely\u2010sampled real patient CBCT projection data (76, 98, and 136 extracted from 680 projections in half\u2010fan geometry). A quantitative analysis is conducted with metrics of peak\u2010signal\u2010to\u2010noise\u2010ratio (PSNR), structural\u2010similarity\u2010index\u2010measure (SSIM), and root\u2010mean\u2010square\u2010error (RMSE).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The PSNR, SSIM, and RMSE results of CBCT reconstructed using DRU optimized projections (98\u2013680 projections in half\u2010fan geometry; 49\u2013340 projections in full\u2010fan geometry) are substantially improved compared to those reconstructed using sparsely sampled projections and those reconstructed using linearly interpolated projections. The application of the DRU post\u2010processing technique further improves the image quality. The reconstructed CBCT with combined workflow using 98 sparsely sampled projections for half\u2010fan geometry and 49 projections for full\u2010fan geometry achieved reasonable image and reduced patient imaging dose by 86%. The reconstruction time is about 15 s in addition to a regular FDK reconstruction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The combined workflow is the first DL CBCT projection interpolation technique that is demonstrated to work on real patient projection data. Preliminary results demonstrate that the proposed DL interpolation and post\u2010processing techniques performed well in reducing the artifacts of reconstructed CBCT images using under\u2010sampled patient projections with substantially reduced patient imaging dose.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.17953","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T07:33:31Z","timestamp":1752564811000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep residual network\u2010based projection interpolation and post\u2010processing techniques for thoracic patient CBCT reconstruction"],"prefix":"10.1002","volume":"52","author":[{"given":"Ke","family":"Lu","sequence":"first","affiliation":[{"name":"Medical Physics Graduate Program Duke University  Durham North Carolina USA"},{"name":"Department of Radiation Oncology Duke University  Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Medical Physics Graduate Program Duke University  Durham North Carolina USA"},{"name":"Department of Radiation Oncology Duke University  Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Ren","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of Maryland School of Medicine  Baltimore Maryland USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang\u2010Fang","family":"Yin","sequence":"additional","affiliation":[{"name":"Medical Physics Graduate Program Duke University  Durham North Carolina USA"},{"name":"Department of Radiation Oncology Duke University  Durham North Carolina USA"},{"name":"Medical Physics Graduate Program Duke Kunshan University  Kunshan China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00066\u2010011\u20102236\u20104"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.1.000612"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/016173468400600107"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/42.20361"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.2836423"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/53\/17\/021"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/aab68d"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010018\u20105810\u20107"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.5772\/52351"},{"key":"e_1_2_8_11_1","volume-title":"Principles of Computerized Tomographic Imaging","author":"Kak AC","year":"1988"},{"key":"e_1_2_8_12_1","unstructured":"SidkyEY KaoCM PanX.Accurate image reconstruction from few\u2010views and limited\u2010angle data in divergent\u2010beam CT.ArXiv09044495 Phys. Published online April 28 2009. Accessed December 19 2018.http:\/\/arxiv.org\/abs\/0904.4495"},{"key":"e_1_2_8_13_1","doi-asserted-by":"crossref","unstructured":"BertramM RoseG SchaferD WiegertJ AachT.Directional interpolation of sparsely sampled cone\u2010beam CT sinogram data. In:2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano (IEEE Cat No. 04EX821). Vol2.IEEE;2004:928\u2010931. doi:10.1109\/ISBI.2004.1398691","DOI":"10.1109\/ISBI.2004.1398691"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2008.2011550"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.3233\/XST\u2010130401"},{"key":"e_1_2_8_16_1","doi-asserted-by":"crossref","unstructured":"ChenH ZhangY ZhangW et\u00a0al.Low\u2010dose CT denoising with convolutional neural network. In:2017IEEE 14th International Symposium on Biomedical Imaging(ISBI 2017).IEEE;2017:143\u2010146. doi:10.1109\/ISBI.2017.7950488","DOI":"10.1109\/ISBI.2017.7950488"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2708987"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2766438"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2827462"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2912791"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.2611474"},{"key":"e_1_2_8_22_1","unstructured":"LuK RenL Fang\u2010FangY.A Deep Learning Technique for Projection Interpolation in CBCT Reconstruction. In:AAPM 63rd Annual Meeting & Exhibition.AAPM;2021.https:\/\/w4.aapm.org\/meetings\/2021AM\/programInfo\/programAbs.php?sid=9204&aid=58798"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2802944"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13687"},{"key":"e_1_2_8_25_1","unstructured":"PaszkeA GrossS MassaF et\u00a0al.PyTorch: An Imperative Style High\u2010Performance Deep Learning Library.ArXiv191201703 Cs Stat. Published online December 3 2019. Accessed April 21 2022.http:\/\/arxiv.org\/abs\/1912.01703"},{"key":"e_1_2_8_26_1","unstructured":"ReddiSJ KaleS KumarS.On the Convergence of Adam and Beyond.ArXiv 190409237. Published online 2019:23."},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_2_8_28_1","unstructured":"MeyesR LuM dePuiseauCW MeisenT.Ablation Studies in Artificial Neural Networks. Published online February 18 2019. Accessed August 2 2022.http:\/\/arxiv.org\/abs\/1901.08644"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1120\/jacmp.v17i6.6459"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4745559"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.17953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T10:37:53Z","timestamp":1765190273000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.17953"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":29,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.1002\/mp.17953"],"URL":"https:\/\/doi.org\/10.1002\/mp.17953","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"2022-05-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-10","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":"e17953"}}