{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T05:50:48Z","timestamp":1776491448054,"version":"3.51.2"},"reference-count":19,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T00:00:00Z","timestamp":1696982400000},"content-version":"vor","delay-in-days":0,"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":[[2024,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Chest x\u2010ray is widely utilized for the evaluation of pulmonary conditions due to its technical simplicity, cost\u2010effectiveness, and portability. However, as a two\u2010dimensional (2\u2010D) imaging modality, chest x\u2010ray images depict limited anatomical details and are challenging to interpret.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>To validate the feasibility of reconstructing three\u2010dimensional (3\u2010D) lungs from a single 2\u2010D chest x\u2010ray image via Vision Transformer (ViT).<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We created a cohort of 2525 paired chest x\u2010ray images (scout images) and computed tomography (CT) acquired on different subjects and we randomly partitioned them as follows: (1) 1800 \u2010 training set, (2) 200 \u2010 validation set, and (3) 525 \u2010 testing set. The 3\u2010D lung volumes segmented from the chest CT scans were used as the ground truth for supervised learning. We developed a novel model termed XRayWizard that employed ViT blocks to encode the 2\u2010D chest x\u2010ray image. The aim is to capture global information and establish long\u2010range relationships, thereby improving the performance of 3\u2010D reconstruction. Additionally, a pooling layer at the end of each transformer block was introduced to extract feature information. To produce smoother and more realistic 3\u2010D models, a set of patch discriminators was incorporated. We also devised a novel method to incorporate subject demographics as an auxiliary input to further improve the accuracy of 3\u2010D lung reconstruction. Dice coefficient and mean volume error were used as performance metrics as the agreement between the computerized results and the ground truth.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In the absence of subject demographics, the mean Dice coefficient for the generated 3\u2010D lung volumes achieved a value of 0.738\u00a0\u00b1\u00a00.091. When subject demographics were included as an auxiliary input, the mean Dice coefficient significantly improved to 0.769\u00a0\u00b1\u00a00.089 (<jats:italic>p<\/jats:italic>\u00a0&lt;\u00a00.001), and the volume prediction error was reduced from 23.5\u00a0\u00b1\u00a02.7%. to 15.7\u00a0\u00b1\u00a02.9%.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Our experiment demonstrated the feasibility of reconstructing 3\u2010D lung volumes from 2\u2010D chest x\u2010ray images, and the inclusion of subject demographics as additional inputs can significantly improve the accuracy of 3\u2010D lung volume reconstruction.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.16781","type":"journal-article","created":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T05:33:23Z","timestamp":1697088803000},"page":"2806-2816","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["XRayWizard: Reconstructing 3\u2010D lung surfaces from a single 2\u2010D chest x\u2010ray image via Vision Transformer"],"prefix":"10.1002","volume":"51","author":[{"given":"Zhiyi","family":"Shi","sequence":"first","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiwen","family":"Geng","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farhad","family":"Mahmoudi","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher J","family":"Haas","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph K.","family":"Leader","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emrah","family":"Duman","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiantao","family":"Pu","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"},{"name":"Department of Bioengineering University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2023,10,11]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chest.2017.07.035"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1097\/MCP.0000000000000567"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/20009666.2020.1711639"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajem.2012.08.041"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.02375-2017"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-019-0466-4"},{"key":"e_1_2_9_8_1","doi-asserted-by":"crossref","unstructured":"HenzlerP RascheV RopinskiT RitschelT.Single\u2010image tomography: 3D volumes from 2D cranial X\u2010rays. Paper presented at: Computer Graphics Forum.2018.","DOI":"10.1111\/cgf.13369"},{"key":"e_1_2_9_9_1","doi-asserted-by":"crossref","unstructured":"KastenY DoktofskyD KovlerI.End\u2010to\u2010end convolutional neural network for 3D reconstruction of knee bones from bi\u2010planar X\u2010ray images. Paper presented at: International Workshop on Machine Learning for Medical Image Reconstruction.2020.","DOI":"10.1007\/978-3-030-61598-7_12"},{"key":"e_1_2_9_10_1","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume":"29","author":"Luo W","year":"2016","journal-title":"Adv Neural Inform Process Syst"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.200802-336OC"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2008.04.005"},{"key":"e_1_2_9_13_1","first-page":"30","article-title":"Attention is all you need","author":"Vaswani A","year":"2017","journal-title":"Adv Neural Inform Process Systems"},{"key":"e_1_2_9_14_1","doi-asserted-by":"crossref","unstructured":"ShengL WangW ShiZ ZhanJ KongY Brainnetformer: decoding Brain Cognitive States with Spatial\u2010Temporal Cross Attention.Paper presented at: ICASSP 2023\u20102023 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP).2023.","DOI":"10.1109\/ICASSP49357.2023.10094655"},{"key":"e_1_2_9_15_1","unstructured":"VoitaE TalbotD MoiseevF SennrichR TitovI.Analyzing multi\u2010head self\u2010attention: specialized heads do the heavy lifting the rest can be pruned.arXiv preprint arXiv:190509418.2019."},{"key":"e_1_2_9_16_1","unstructured":"DosovitskiyA BeyerL KolesnikovA et\u00a0al.An image is worth 16\u00d716 words: transformers for image recognition at scale.arXiv preprint arXiv:201011929.2020."},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"e_1_2_9_18_1","doi-asserted-by":"crossref","unstructured":"IsolaP ZhuJ\u2010Y ZhouT EfrosAA.Image\u2010to\u2010image translation with conditional adversarial networks. Paper presented at:Proceedings of the IEEE conference on computer vision and pattern recognition2017.","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_2_9_19_1","doi-asserted-by":"crossref","unstructured":"HeoB YunS HanD ChunS ChoeJ OhSJ.Rethinking spatial dimensions of vision transformers.Paper presented at: Proceedings of the IEEE\/CVF International Conference on Computer Vision2021.","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15019"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16781","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,4]],"date-time":"2024-04-04T15:26:25Z","timestamp":1712244385000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16781"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,11]]},"references-count":19,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["10.1002\/mp.16781"],"URL":"https:\/\/doi.org\/10.1002\/mp.16781","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,11]]},"assertion":[{"value":"2023-07-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-27","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-10-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}