{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T09:33:22Z","timestamp":1787045602873,"version":"build-2736575974"},"reference-count":47,"publisher":"IOP Publishing","issue":"16","license":[{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2026,8,28]]},"abstract":"Abstract<\/jats:title>\n \n Objective.<\/jats:italic>\n To develop a fast and accurate physics-informed framework for real-time three-dimensional dose reconstruction directly from machine delivery beams for adaptive radiotherapy and intra-fraction dose monitoring.\n Approach.<\/jats:italic>\n We propose a two-stage beam physics-driven dose reconstruction framework that integrates machine photon beam characteristics into fluence-to-dose estimation. In Stage 1, beam-related physical characteristics, including beam profiles and percent depth dose, are extracted from the institutional beam database using a large language model (LLM) assistant tuned on beam commissioning guidelines and encoded as beam-specific priors. In Stage 2, beam-wise fluence-to-dose reconstruction is performed in beam-eye-view space using a multimodal neural network that incorporates BEV-aligned CT images, optimal fluence, and the LLM-derived beam priors. Training uses a composite physics-aware loss, and performance is evaluated using two-dimensional and three-dimensional gamma analysis.\n Main Results.<\/jats:italic>\n The study included 180 lung radiotherapy patients for model development and internal evaluation, and an external prostate cohort of 5 patients for cross-site testing. The predicted dose distributions showed strong agreement with reference dose maps, with residual errors mainly confined to low-dose regions and within\n \n \n \n <\/jats:tex-math>\n \n \n \u00b1<\/mml:mo>\n 3<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n \u2009Gy relative to a maximum dose of approximately 75 Gy. The proposed framework achieved a mean 3D gamma passing rate (3%, 2 mm\/10%) of\n \n \n \n <\/jats:tex-math>\n \n \n 0.975<\/mml:mn>\n \u00b1<\/mml:mo>\n 0.056<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n , outperforming 3D U-Net (\n \n \n \n <\/jats:tex-math>\n \n \n 0.931<\/mml:mn>\n \u00b1<\/mml:mo>\n 0.113<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n ), Dose-Net (\n \n \n \n <\/jats:tex-math>\n \n \n 0.939<\/mml:mn>\n \u00b1<\/mml:mo>\n 0.120<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n ), and CLIP-UNet (\n \n \n \n <\/jats:tex-math>\n \n \n 0.945<\/mml:mn>\n \u00b1<\/mml:mo>\n 0.087<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n ) (\n \n \n \n <\/jats:tex-math>\n \n \n p<\/mml:mi>\n <<\/mml:mo>\n 0.05<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n ). The corresponding mean 2D gamma passing rate was\n \n \n \n <\/jats:tex-math>\n \n \n 0.962<\/mml:mn>\n \u00b1<\/mml:mo>\n 0.073<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n . External testing achieved a gamma passing rate of\n \n \n \n <\/jats:tex-math>\n \n \n 0.953<\/mml:mn>\n \u00b1<\/mml:mo>\n 0.088<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n . The model required approximately 6.3 seconds to reconstruct a 9-field treatment plan.\n Significance.<\/jats:italic>\n By incorporating LLM-encoded beam physics into a multimodal dose reconstruction framework, this method improves dosimetric accuracy over existing learning-based approaches while maintaining rapid inference, supporting its potential for adaptive radiotherapy and real-time three-dimensional\n in vivo<\/jats:italic>\n dosimetry.\n <\/jats:p>","DOI":"10.1088\/1361-6560\/ae95ab","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T22:54:56Z","timestamp":1785970496000},"page":"165007","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reconstructing delivered dose in real time: a beam physics-embedded, language-model-driven approach"],"prefix":"10.1088","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3311-2810","authenticated-orcid":true,"given":"Yuli","family":"Wang","sequence":"first","affiliation":[{"name":"Icahn School of Medicine at Mount Sinai"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"Icahn School of Medicine at Mount Sinai"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Icahn School of Medicine at Mount Sinai"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhang","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Nebraska Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Chao","sequence":"additional","affiliation":[{"name":"Icahn School of Medicine at Mount Sinai"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyi","family":"Xia","sequence":"additional","affiliation":[{"name":"Icahn School of Medicine at Mount Sinai"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruirui","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Nebraska Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Nebraska Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Lei","sequence":"additional","affiliation":[{"name":"University of Nebraska Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karyn A","family":"Goodman","sequence":"additional","affiliation":[{"name":"Icahn School of Medicine at Mount Sinai"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Liu","sequence":"additional","affiliation":[{"name":"Icahn School of Medicine at Mount Sinai"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3572-0345","authenticated-orcid":true,"given":"Yang","family":"Lei","sequence":"additional","affiliation":[{"name":"Icahn School of Medicine at Mount Sinai"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,8,18]]},"reference":[{"key":"pmbae95abbib1","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1118\/1.596856","type":"journal-article","article-title":"A pencil beam model for photon dose calculation","volume":"19","author":"Ahnesj\u00f6","year":"1992","journal-title":"Med. Phys."},{"key":"pmbae95abbib2","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/s00411-025-01117-3","type":"journal-article","article-title":"Commissioning and performance assessment of diodes and MOSFETs in in-vivo dosimetry for external beam radiation therapy","volume":"64","author":"Al Kharusi","year":"2025","journal-title":"Radiat. Environ. Biophys."},{"key":"pmbae95abbib3","doi-asserted-by":"publisher","first-page":"1847","DOI":"10.1118\/1.598691","type":"journal-article","article-title":"AAPM\u2019s TG-51 protocol for clinical reference dosimetry of high-energy photon and electron beams","volume":"26","author":"Almond","year":"1999","journal-title":"Med. Phys."},{"key":"pmbae95abbib4","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abdbfe","type":"journal-article","article-title":"Deep dose plugin: towards real-time Monte Carlo dose calculation through a deep learning-based denoising algorithm","volume":"2","author":"Bai","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"pmbae95abbib5","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1007\/s00411-022-00989-z","type":"journal-article","article-title":"A matter of space: how the spatial heterogeneity in energy deposition determines the biological outcome of radiation exposure","volume":"61","author":"Baiocco","year":"2022","journal-title":"Radiat. Environ. Biophys."},{"key":"pmbae95abbib6","first-page":"pp 205","author":"Cao","year":"2022","type":"conference-proceedings"},{"key":"pmbae95abbib7","doi-asserted-by":"publisher","first-page":"4818","DOI":"10.1118\/1.2795842","type":"journal-article","article-title":"Report of the AAPM Task Group No. 105: issues associated with clinical implementation of Monte Carlo-based photon and electron external beam treatment planning","volume":"34","author":"Chetty","year":"2007","journal-title":"Med. Phys."},{"key":"pmbae95abbib8","first-page":"pp 255","author":"Chinnalagu","year":"2024","type":"conference-proceedings"},{"key":"pmbae95abbib9","doi-asserted-by":"publisher","first-page":"4186","DOI":"10.1118\/1.2969070","type":"journal-article","article-title":"Accelerator beam data commissioning equipment and procedures: report of the TG-106 of the Therapy Physics Committee of the AAPM","volume":"35","author":"Das","year":"2008","journal-title":"Med. Phys."},{"key":"pmbae95abbib10","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1120\/jacmp.v16i3.5283","type":"journal-article","article-title":"Anatomy-based, patient-specific VMAT QA using EPID or MLC log files","volume":"16","author":"Defoor","year":"2015","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"pmbae95abbib11","first-page":"pp 4171","author":"Devlin","year":"2019","type":"conference-proceedings"},{"key":"pmbae95abbib12","first-page":"pp 191","author":"Feng","year":"2023","type":"conference-proceedings"},{"key":"pmbae95abbib13","first-page":"pp 715","author":"Gao","year":"2023","type":"conference-proceedings"},{"key":"pmbae95abbib14","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2025.100890","type":"journal-article","article-title":"A deep learning approach for predicting linear accelerator output settings in automated radiotherapy planning of oligometastatic cancer","volume":"37","author":"Gaudreault","year":"2025","journal-title":"Phys. Imaging Radiat. Oncol."},{"key":"pmbae95abbib15","author":"Grattafiori","year":"2024","type":"preprint"},{"key":"pmbae95abbib16","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.70304","type":"journal-article","article-title":"PlanAct: an eclipse scripting API-based module embedding clinical optimization strategies for automated planning in locally advanced non-small cell lung cancer","volume":"26","author":"Guo","year":"2025","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"pmbae95abbib17","doi-asserted-by":"publisher","first-page":"3679","DOI":"10.1088\/0031-9155\/52\/13\/002","type":"journal-article","article-title":"Collapsed cone convolution and analytical anisotropic algorithm dose calculations compared to VMC++ Monte Carlo simulations in clinical cases","volume":"52","author":"Hasenbalg","year":"2007","journal-title":"Phys. Med. Biol."},{"key":"pmbae95abbib18","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1118\/1.3539725","type":"journal-article","article-title":"GPUMCD: a new GPU-oriented Monte Carlo dose calculation platform","volume":"38","author":"Hissoiny","year":"2011","journal-title":"Med. Phys."},{"key":"pmbae95abbib19","doi-asserted-by":"publisher","first-page":"7017","DOI":"10.1088\/0031-9155\/56\/22\/002","type":"journal-article","article-title":"GPU-based fast Monte Carlo simulation for radiotherapy dose calculation","volume":"56","author":"Jia","year":"2011","journal-title":"Phys. Med. Biol."},{"key":"pmbae95abbib20","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102902","type":"journal-article","article-title":"TransDose: transformer-based radiotherapy dose prediction from CT images guided by super-pixel-level GCN classification","volume":"89","author":"Jiao","year":"2023","journal-title":"Med. Image Anal."},{"key":"pmbae95abbib21","doi-asserted-by":"publisher","DOI":"10.1016\/j.canrad.2025.104630","type":"journal-article","article-title":"Artificial intelligence for radiotherapy dose prediction: A comprehensive review","volume":"29","author":"Kazemzadeh","year":"2025","journal-title":"Cancer\/Radioth\u00e9rapie"},{"key":"pmbae95abbib22","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaef74","type":"journal-article","article-title":"DoseNet: a volumetric dose prediction algorithm using 3D fully-convolutional neural networks","volume":"63","author":"Kearney","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"pmbae95abbib23","author":"Kingma","year":"2014","type":"preprint"},{"key":"pmbae95abbib24","author":"Koroteev","year":"2021","type":"preprint"},{"key":"pmbae95abbib25","first-page":"pp 8758","author":"Li","year":"2024","type":"conference-proceedings"},{"key":"pmbae95abbib26","doi-asserted-by":"publisher","first-page":"12482","DOI":"10.21037\/qims-2025-168","type":"journal-article","article-title":"Fully automated intensity-modulated radiotherapy plans for rectal cancer based on deep learning predictions of three-dimensional dose distributions","volume":"15","author":"Liu","year":"2025","journal-title":"Quant. Imaging Med. Surg."},{"key":"pmbae95abbib27","doi-asserted-by":"publisher","first-page":"1391","DOI":"10.1002\/mp.15461","type":"journal-article","article-title":"Site-agnostic 3D dose distribution prediction with deep learning neural networks","volume":"49","author":"Mashayekhi","year":"2022","journal-title":"Med. Phys."},{"key":"pmbae95abbib28","author":"McMahon","year":"2004","type":"book"},{"key":"pmbae95abbib29","doi-asserted-by":"publisher","first-page":"e53","DOI":"10.1002\/mp.12810","type":"journal-article","article-title":"Tolerance limits and methodologies for IMRT measurement-based verification QA: recommendations of AAPM Task Group No. 218","volume":"45","author":"Miften","year":"2018","journal-title":"Med. Phys."},{"key":"pmbae95abbib30","doi-asserted-by":"publisher","first-page":"147","DOI":"10.4103\/jmp.JMP_38_18","type":"journal-article","article-title":"A dose falloff gradient study in RapidArc planning of lung stereotactic body radiation therapy","volume":"43","author":"Narayanasamy","year":"2018","journal-title":"J. Med. Phys."},{"key":"pmbae95abbib31","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.phro.2020.08.003","type":"journal-article","article-title":"In vivo dosimetry in external beam photon radiotherapy: requirements and future directions for research, development, and clinical practice","volume":"15","author":"Olaciregui-Ruiz","year":"2020","journal-title":"Phys. Imaging Radiat. Oncol."},{"key":"pmbae95abbib32","doi-asserted-by":"publisher","first-page":"9","DOI":"10.21037\/tro-24-10","type":"journal-article","article-title":"A narrative review: dose calculation algorithms used in external beam radiotherapy planning systems","volume":"9","author":"Pandu","year":"2025","journal-title":"Ther. Radiol. Oncol."},{"key":"pmbae95abbib33","first-page":"pp 85","author":"Shi","year":"2023","type":"conference-proceedings"},{"key":"pmbae95abbib34","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","type":"journal-article","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"pmbae95abbib35","doi-asserted-by":"publisher","first-page":"e199","DOI":"10.1016\/j.prro.2012.11.013","type":"journal-article","article-title":"Initial experience with TrueBeam trajectory log files for radiation therapy delivery verification","volume":"3","author":"Sun","year":"2013","journal-title":"Pract. Radiat. Oncol."},{"key":"pmbae95abbib36","doi-asserted-by":"publisher","first-page":"14","DOI":"10.4103\/abr.abr_180_25","type":"journal-article","article-title":"Dose Prediction Deep Learning-Based Model for VMAT of Prostate Cancer Applying Magnetic Resonance Image (MRI) in Versa HD Linear Accelerator","volume":"15","author":"Taheri","year":"2026","journal-title":"Adv. Biomed. Res."},{"key":"pmbae95abbib37","first-page":"pp 753","author":"Tan","year":"2021","type":"conference-proceedings"},{"key":"pmbae95abbib38","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103045","type":"journal-article","article-title":"Beam-wise dose composition learning for head and neck cancer dose prediction in radiotherapy","volume":"92","author":"Teng","year":"2024","journal-title":"Med. Image Anal."},{"key":"pmbae95abbib39","doi-asserted-by":"publisher","first-page":"4130","DOI":"10.1118\/1.2358333","type":"journal-article","article-title":"Testing of the analytical anisotropic algorithm for photon dose calculation","volume":"33","author":"Van Esch","year":"2006","journal-title":"Med. Phys."},{"key":"pmbae95abbib40","doi-asserted-by":"publisher","first-page":"6945","DOI":"10.1118\/1.4935199","type":"journal-article","article-title":"Validation of a method for in vivo 3D dose reconstruction for IMRT and VMAT treatments using on-treatment EPID images and a model-based forward-calculation algorithm","volume":"42","author":"Van Uytven","year":"2015","journal-title":"Med. Phys."},{"key":"pmbae95abbib41","doi-asserted-by":"publisher","first-page":"5753","DOI":"10.1109\/TCSVT.2024.3366664","type":"journal-article","article-title":"Toward robust LiDAR-camera fusion in BEV space via mutual deformable attention and temporal aggregation","volume":"34","author":"Wang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"pmbae95abbib42","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1038\/s41746-026-02572-y","type":"journal-article","article-title":"Integrating large language models for enhanced predictive analytics in healthcare","volume":"9","author":"Wang","year":"2026","journal-title":"npj Digit. Med."},{"key":"pmbae95abbib43","doi-asserted-by":"publisher","DOI":"10.1161\/CIRC.150.suppl_1.4119869","type":"journal-article","article-title":"Automatic assignment of CAD-RADS categories in coronary CTA reports using large language model","volume":"150","author":"Wang","year":"2024","journal-title":"Circulation"},{"key":"pmbae95abbib44","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1038\/s44387-025-00015-9","type":"journal-article","article-title":"Vision-language foundation model for 3D medical imaging","volume":"1","author":"Wu","year":"2025","journal-title":"npj Artif. Intell."},{"key":"pmbae95abbib45","doi-asserted-by":"publisher","DOI":"10.1088\/3049-477X\/adcb4b","type":"journal-article","article-title":"Geometry-encoded deep learning (GeoDL) framework for real-time 3D dose verification for online adaptive radiotherapy","volume":"1","author":"Yan","year":"2025","journal-title":"Mach. Learn.: Health"},{"key":"pmbae95abbib46","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.isprsjprs.2023.08.013","type":"journal-article","article-title":"Generating evidential BEV maps in continuous driving space","volume":"204","author":"Yuan","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"pmbae95abbib47","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/adb371","type":"journal-article","article-title":"Medical image segmentation assisted with clinical inputs via language encoder in a deep learning framework","volume":"6","author":"Zhao","year":"2025","journal-title":"Mach. Learn.: Sci. Technol."}],"container-title":["Physics in Medicine & Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae95ab","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae95ab\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae95ab","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae95ab\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae95ab\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae95ab\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae95ab\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae95ab\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T09:14:28Z","timestamp":1787044468000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae95ab"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,18]]},"references-count":47,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8,18]]},"published-print":{"date-parts":[[2026,8,28]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ae95ab","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,18]]},"assertion":[{"value":"Reconstructing delivered dose in real time: a beam physics-embedded, language-model-driven approach","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-04-03","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-08-05","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-08-18","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}