{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,21]],"date-time":"2026-11-21T13:36:25Z","timestamp":1795268185893,"version":"4.10.3"},"reference-count":60,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"2","content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"abstract":"<jats:p>Artificial intelligence is increasingly shaping the evolution of proton therapy, with applications spanning imaging, treatment planning, quality assurance, adaptive workflows, and outcome modeling. Unlike conventional task-specific algorithms, modern AI methods, including machine learning and deep learning, enable integration of heterogeneous data and capture complex relationships across the clinical workflow. These capabilities are particularly relevant in proton therapy, where sensitivity to range uncertainty, anatomic variation, and biological heterogeneity presents persistent clinical and operational challenges. This review summarizes current and emerging AI applications in proton therapy, including image reconstruction and synthesis, segmentation, dose prediction, robustness and uncertainty management, biological optimization, and adaptive treatment strategies. We also discuss the expanding role of AI in quality assurance and workflow coordination, emphasizing the distinction between task-level automation and workflow-level intelligence. Finally, we address broader considerations related to clinical validation, safety, interpretability, economic value, and access, which will be critical for translating AI-enabled proton therapy into routine clinical practice.<\/jats:p>","DOI":"10.1097\/ppo.0000000000000821","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T15:00:19Z","timestamp":1774450819000},"update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":1,"title":["Artificial Intelligence in Proton Therapy"],"prefix":"10.1097","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4815-0537","authenticated-orcid":false,"given":"Heng","family":"Li","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University Baltimore, MD"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Radiation Physics, MD Anderson Cancer Center, Houston, TX"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Doris Keziah","family":"Ndassi","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University Baltimore, MD"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sizhuo","family":"Meng","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University Baltimore, MD"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xun","family":"Jia","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University Baltimore, MD"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2026,3]]},"reference":[{"key":"R1-20260325","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1007\/s12032-020-01374-w","article-title":"Artificial Intelligence in radiotherapy: state of the art and future directions","volume":"37","author":"Francolini","year":"2020","journal-title":"Medical Oncology"},{"key":"R2-20260325","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1016\/j.radonc.2018.05.030","article-title":"Artificial intelligence in radiation oncology: a specialty-wide disruptive transformation?","volume":"129","author":"Thompson","year":"2018","journal-title":"Radiotherapy and Oncology"},{"key":"R3-20260325","doi-asserted-by":"crossref","first-page":"05TR01","DOI":"10.1088\/1361-6560\/ab6f51","article-title":"An introduction to deep learning in medical physics: advantages, potential, and challenges","volume":"65","author":"Shen","year":"2020","journal-title":"Phys Med Biol"},{"key":"R4-20260325","first-page":"021001","article-title":"Synergizing medical imaging and radiotherapy with deep learning","volume":"1","author":"Shan","year":"2020","journal-title":"Machine Learning: Science and Technology"},{"key":"R5-20260325","doi-asserted-by":"crossref","first-page":"e929","DOI":"10.1002\/mp.14320","article-title":"Auto-segmentation of organs at risk for head and neck radiotherapy planning: from atlas-based to deep learning methods","volume":"47","author":"Vrtovec","year":"2020","journal-title":"Medical physics"},{"key":"R6-20260325","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.oraloncology.2018.10.026","article-title":"The application of artificial intelligence in the IMRT planning process for head and neck cancer","volume":"87","author":"Kearney","year":"2018","journal-title":"Oral Oncology"},{"key":"R7-20260325","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1016\/j.ijrobp.2019.07.049","article-title":"Machine learning for patient-specific quality assurance of VMAT: prediction and classification accuracy","volume":"105","author":"Li","year":"2019","journal-title":"International Journal of Radiation Oncology* Biology* Physics"},{"key":"R8-20260325","doi-asserted-by":"crossref","first-page":"20220239","DOI":"10.1259\/bjr.20220239","article-title":"Current status and future developments in predicting outcomes in radiation oncology","volume":"95","author":"Niraula","year":"2022","journal-title":"The British Journal of Radiology"},{"key":"R9-20260325","doi-asserted-by":"crossref","first-page":"e2100393","DOI":"10.1200\/GO.21.00393","article-title":"Using artificial intelligence for optimization of the processes and resource utilization in radiotherapy","volume":"8","author":"Krishnamurthy","year":"2022","journal-title":"JCO Global Oncology"},{"key":"R10-20260325","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.addr.2016.11.006","article-title":"Proton therapy\u2013present and future","volume":"109","author":"Mohan","year":"2017","journal-title":"Advanced drug delivery reviews"},{"key":"R11-20260325","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/S0167-8140(99)00036-5","article-title":"A treatment planning inter-comparison of proton and intensity modulated photon radiotherapy","volume":"51","author":"Lomax","year":"1999","journal-title":"Radiotherapy and oncology"},{"key":"R12-20260325","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1002\/pro6.1149","article-title":"A review of proton therapy\u2013current status and future directions.","volume":"6","author":"Mohan","year":"2022","journal-title":"Precision radiation oncology"},{"key":"R13-20260325","doi-asserted-by":"crossref","first-page":"22TR02","DOI":"10.1088\/1361-6560\/aae659","article-title":"Robust radiotherapy planning","volume":"63","author":"Unkelbach","year":"2018","journal-title":"Physics in Medicine & Biology"},{"key":"R14-20260325","doi-asserted-by":"crossref","first-page":"977","DOI":"10.3389\/fonc.2019.00977","article-title":"Deep learning: a review for the radiation oncologist","volume":"9","author":"Boldrini","year":"2019","journal-title":"Front Oncol"},{"key":"R15-20260325","doi-asserted-by":"crossref","first-page":"4416","DOI":"10.1002\/mp.14347","article-title":"Cone-beam CT-derived relative stopping power map generation via deep learning for proton radiotherapy","volume":"47","author":"Harms","year":"2020","journal-title":"Med Phys"},{"key":"R16-20260325","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"R17-20260325","doi-asserted-by":"crossref","first-page":"e000759","DOI":"10.1136\/bmjonc-2025-000759","article-title":"Large language models in oncology: a review","volume":"4","author":"Chen","year":"2025","journal-title":"BMJ oncology"},{"key":"R18-20260325","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1016\/j.jacr.2023.05.003","article-title":"Evaluating GPT as an Adjunct for Radiologic Decision Making: GPT-4 Versus GPT-3.5 in a Breast Imaging Pilot.","volume":"20","author":"Rao","year":"2023","journal-title":"J Am Coll Radiol."},{"key":"R19-20260325","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1038\/s42256-021-00337-8","article-title":"End-to-end privacy preserving deep learning on multi-institutional medical imaging","volume":"3","author":"Kaissis","year":"2021","journal-title":"Nat Mach Intell"},{"key":"R20-20260325","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1038\/s42256-020-0186-1","article-title":"Secure, privacy-preserving and federated machine learning in medical imaging","volume":"2","author":"Kaissis","year":"2020","journal-title":"Nat Mach Intell"},{"key":"R21-20260325","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1088\/0031-9155\/53\/4\/015","article-title":"Intensity modulated proton therapy and its sensitivity to treatment uncertainties 2: the potential effects of inter-fraction and inter-field motions","volume":"53","author":"Lomax","year":"2008","journal-title":"Phys Med Biol"},{"key":"R22-20260325","doi-asserted-by":"crossref","first-page":"095002","DOI":"10.1088\/1361-6560\/ab7d54","article-title":"Comparison of CBCT based synthetic CT methods suitable for proton dose calculations in adaptive proton therapy","volume":"65","author":"Thummerer","year":"2020","journal-title":"Phys Med Biol"},{"key":"R23-20260325","doi-asserted-by":"crossref","first-page":"185001","DOI":"10.1088\/1361-6560\/aada6d","article-title":"Dose evaluation of fast synthetic-CT generation using a generative adversarial network for general pelvis MR-only radiotherapy","volume":"63","author":"Maspero","year":"2018","journal-title":"Phys Med Biol"},{"key":"R24-20260325","doi-asserted-by":"crossref","first-page":"1495","DOI":"10.1109\/TMI.2022.3231461","article-title":"Four-dimensional cone beam CT imaging using a single routine scan via deep learning","volume":"42","author":"Yang","year":"2022","journal-title":"IEEE Trans Med Imaging"},{"key":"R25-20260325","doi-asserted-by":"crossref","first-page":"2605","DOI":"10.1109\/TMI.2025.3541242","article-title":"Ultra-sparse-view cone-beam CT reconstruction based strictly-structure-preserved deep neural network in image-guided radiation therapy","volume":"44","author":"Song","year":"2025","journal-title":"IEEE Trans Med Imaging"},{"key":"R26-20260325","doi-asserted-by":"crossref","first-page":"R99","DOI":"10.1088\/0031-9155\/57\/11\/R99","article-title":"Range uncertainties in proton therapy and the role of Monte Carlo simulations","volume":"57","author":"Paganetti","year":"2012","journal-title":"Phys Med Biol"},{"key":"R27-20260325","doi-asserted-by":"crossref","first-page":"1579","DOI":"10.1088\/0031-9155\/43\/6\/016","article-title":"The precision of proton range calculations in proton radiotherapy treatment planning: experimental verification of the relation between CT-HU and proton stopping power","volume":"43","author":"Schaffner","year":"1998","journal-title":"Phys Med Biol"},{"key":"R28-20260325","doi-asserted-by":"crossref","first-page":"519","DOI":"10.4103\/jmp.jmp_120_24","article-title":"Machine learning approach and model for predicting proton stopping power ratio and other parameters using computed tomography images","volume":"49","author":"Chika","year":"2024","journal-title":"J Med Phys"},{"key":"R29-20260325","doi-asserted-by":"crossref","first-page":"215016","DOI":"10.1088\/1361-6560\/abab57","article-title":"Convolutional neural network based proton stopping-power-ratio estimation with dual-energy CT: a feasibility study","volume":"65","author":"Lee","year":"2020","journal-title":"Phys Med Biol"},{"key":"R30-20260325","doi-asserted-by":"crossref","first-page":"46","DOI":"10.14338\/IJPT-D-20-00020.1","article-title":"Learning-based stopping power mapping on dual-energy CT for proton radiation therapy","volume":"7","author":"Wang","year":"2021","journal-title":"Int J Part Ther"},{"key":"R31-20260325","doi-asserted-by":"crossref","first-page":"115010","DOI":"10.1088\/1361-6560\/ac6ebc","article-title":"Dual-energy CT based mass density and relative stopping power estimation for proton therapy using physics-informed deep learning","volume":"67","author":"Chang","year":"2022","journal-title":"Phys Med Biol"},{"key":"R32-20260325","doi-asserted-by":"crossref","first-page":"065014","DOI":"10.1088\/1361-6560\/abe736","article-title":"Synthetic dual-energy CT for MRI-only based proton therapy treatment planning using label-GAN","volume":"66","author":"Liu","year":"2021","journal-title":"Physics in Medicine & Biology"},{"key":"R33-20260325","doi-asserted-by":"crossref","first-page":"145015","DOI":"10.1088\/1361-6560\/ab25bc","article-title":"MRI-based treatment planning for proton radiotherapy: dosimetric validation of a deep learning-based liver synthetic CT generation method","volume":"64","author":"Liu","year":"2019","journal-title":"Physics in Medicine & Biology"},{"key":"R34-20260325","doi-asserted-by":"crossref","first-page":"112545","DOI":"10.1016\/j.radphyschem.2025.112545","article-title":"Direct creation of the relative stopping power maps from MRI images using a cycleGAN deep-learning network for proton therapy","volume":"229","author":"Omidi","year":"2025","journal-title":"Radiation Physics and Chemistry"},{"key":"R35-20260325","doi-asserted-by":"crossref","first-page":"1278180","DOI":"10.3389\/fonc.2023.1278180","article-title":"Single energy CT-based mass density and relative stopping power estimation for proton therapy using deep learning method","volume":"13","author":"Gao","year":"2023","journal-title":"Front Oncol."},{"key":"R36-20260325","first-page":"19213","article-title":"AI in Proton Therapy Treatment Planning: A Review","volume":"2510","author":"Ding","year":"2025","journal-title":"arXiv"},{"key":"R37-20260325","doi-asserted-by":"crossref","first-page":"7417","DOI":"10.1002\/mp.16043","article-title":"Three-dimensional dose and LETD prediction in proton therapy using artificial neural networks","volume":"49","author":"Pirlepesov","year":"2022","journal-title":"Medical physics"},{"key":"R38-20260325","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.radonc.2020.11.026","article-title":"Deep learning prediction of proton and photon dose distributions for paediatric abdominal tumours","volume":"156","author":"Guerreiro","year":"2021","journal-title":"Radiotherapy and Oncology"},{"key":"R39-20260325","doi-asserted-by":"crossref","first-page":"62","DOI":"10.14338\/IJPT-20-00088.1","article-title":"Assessment of knowledge-based planning for prostate intensity modulated proton therapy","volume":"8","author":"Xu","year":"2021","journal-title":"International journal of particle therapy"},{"key":"R40-20260325","doi-asserted-by":"crossref","first-page":"737901","DOI":"10.3389\/fonc.2021.737901","article-title":"Knowledge-based planning for robustly optimized intensity-modulated proton therapy of head and neck cancer patients","volume":"11","author":"Xu","year":"2021","journal-title":"Frontiers in oncology"},{"key":"R41-20260325","doi-asserted-by":"crossref","first-page":"215007","DOI":"10.1088\/1361-6560\/aba164","article-title":"Fast spot-scanning proton dose calculation method with uncertainty quantification using a three-dimensional convolutional neural network","volume":"65","author":"Nomura","year":"2020","journal-title":"Physics in Medicine & Biology"},{"key":"R42-20260325","doi-asserted-by":"crossref","first-page":"4941","DOI":"10.1002\/mp.17794","article-title":"Proton dose calculation with transformer: transforming spot map to dose","volume":"52","author":"Tang","year":"2025","journal-title":"Medical physics"},{"key":"R43-20260325","doi-asserted-by":"crossref","first-page":"R419","DOI":"10.1088\/0031-9155\/59\/22\/R419","article-title":"Relative biological effectiveness (RBE) values for proton beam therapy. Variations as a function of biological endpoint, dose, and linear energy transfer","volume":"59","author":"Paganetti","year":"2014","journal-title":"Phys Med Biol"},{"key":"R44-20260325","doi-asserted-by":"crossref","first-page":"115058","DOI":"10.1088\/1361-6560\/ad4844","article-title":"Deep learning based linear energy transfer calculation for proton therapy","volume":"69","author":"Tang","year":"2024","journal-title":"Physics in Medicine & Biology"},{"key":"R45-20260325","doi-asserted-by":"crossref","first-page":"025004","DOI":"10.1088\/1361-6560\/ad154b","article-title":"Deep learning-based synthetic dose-weighted LET map generation for intensity modulated proton therapy","volume":"69","author":"Gao","year":"2024","journal-title":"Physics in Medicine & Biology"},{"key":"R46-20260325","doi-asserted-by":"crossref","first-page":"6201","DOI":"10.1002\/mp.16431","article-title":"Patient selection for proton therapy using Normal Tissue Complication Probability with deep learning dose prediction for oropharyngeal cancer","volume":"50","author":"Huet-Dastarac","year":"2023","journal-title":"Medical Physics"},{"key":"R47-20260325","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/j.radonc.2021.02.034","article-title":"Model based patient pre-selection for intensity-modulated proton therapy (IMPT) using automated treatment planning and machine learning","volume":"158","author":"Kouwenberg","year":"2021","journal-title":"Radiotherapy and Oncology"},{"key":"R48-20260325","doi-asserted-by":"crossref","first-page":"E668","DOI":"10.1016\/j.ijrobp.2016.06.2300","article-title":"Implementation of a machine learning\u2013based automatic contour quality assurance tool for online adaptive radiation therapy of prostate cancer","volume":"96","author":"Zhang","year":"2016","journal-title":"International Journal of Radiation Oncology, Biology, Physics"},{"key":"R49-20260325","doi-asserted-by":"crossref","first-page":"e13647","DOI":"10.1002\/acm2.13647","article-title":"Automatic contouring QA method using a deep learning\u2013based autocontouring system","volume":"23","author":"Rhee","year":"2022","journal-title":"Journal of applied clinical medical physics"},{"key":"R50-20260325","doi-asserted-by":"crossref","first-page":"e384","DOI":"10.1016\/S2589-7500(22)00003-6","article-title":"The medical algorithmic audit","volume":"4","author":"Liu","year":"2022","journal-title":"The Lancet Digital Health"},{"key":"R53-20260325","doi-asserted-by":"crossref","first-page":"822","DOI":"10.1016\/j.ijrobp.2024.09.032","article-title":"Online adaptive proton therapy facilitated by artificial intelligence-based autosegmentation in pencil beam scanning proton therapy","volume":"121","author":"Feng","year":"2025","journal-title":"International Journal of Radiation Oncology* Biology* Physics"},{"key":"R54-20260325","doi-asserted-by":"crossref","first-page":"110650","DOI":"10.1016\/j.radonc.2024.110650","article-title":"Deep learning-based multiple-CT optimization: an adaptive treatment planning approach to account for anatomical changes in intensity-modulated proton therapy for head and neck cancers","volume":"202","author":"Liu","year":"2025","journal-title":"Radiotherapy and Oncology"},{"key":"R55-20260325","doi-asserted-by":"crossref","first-page":"025010","DOI":"10.1088\/1361-6560\/ada684","article-title":"Exploration of an adaptive proton therapy strategy using CBCT with the concept of digital twins","volume":"70","author":"Chang","year":"2025","journal-title":"Physics in Medicine & Biology"},{"key":"R56-20260325","doi-asserted-by":"crossref","first-page":"e70231","DOI":"10.1002\/acm2.70231","article-title":"Digital twin creation of a proton therapy treatment environment with hybrid LiDAR and RGB 3D camera","volume":"26","author":"Dougherty","year":"2025","journal-title":"Journal of Applied Clinical Medical Physics"},{"key":"R57-20260325","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1042\/ETLS20210246","article-title":"Artificial intelligence, machine learning, and deep learning for clinical outcome prediction","volume":"5","author":"Pettit","year":"2021","journal-title":"Emerging topics in life sciences"},{"key":"R58-20260325","doi-asserted-by":"crossref","first-page":"10732748241286749","DOI":"10.1177\/10732748241286749","article-title":"Improving prediction of complications post-proton therapy in lung cancer using large language models and meta-analysis","volume":"31","author":"Chao","year":"2024","journal-title":"Cancer Control"},{"key":"R59-20260325","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1146\/annurev-nucl-121423-100719","article-title":"Machine learning for design and control of particle accelerators: a look backward and forward","volume":"74","author":"Edelen","year":"2024","journal-title":"Annu Rev Nucl Part Sci"},{"key":"R60-20260325","doi-asserted-by":"crossref","first-page":"054601","DOI":"10.1103\/PhysRevAccelBeams.27.054601","article-title":"Bridging the gap between machine learning and particle accelerator physics with high-speed, differentiable simulations","volume":"27","author":"Kaiser","year":"2024","journal-title":"Phys Rev Accel Beams"},{"key":"R61-20260325","doi-asserted-by":"crossref","first-page":"e13406","DOI":"10.1111\/exsy.13406","article-title":"Artificial intelligence governance: Ethical considerations and implications for social responsibility","volume":"41","author":"Camilleri","year":"2024","journal-title":"Expert systems"},{"key":"R62-20260325","doi-asserted-by":"crossref","first-page":"102055","DOI":"10.1016\/j.artmed.2021.102055","article-title":"Ethical evaluation of artificial intelligence applications in radiotherapy using the Four Topics Approach","volume":"115","author":"Erkal","year":"2021","journal-title":"Artificial Intelligence in Medicine"}],"container-title":["The Cancer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/PPO.0000000000000821","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T15:00:25Z","timestamp":1774450825000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/PPO.0000000000000821"}},"subtitle":["What Works, What Does Not, and What Is Next"],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":60,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1097\/ppo.0000000000000821","relation":{},"ISSN":["1540-336X"],"issn-type":[{"value":"1540-336X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"2026-01-23","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-28","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}