{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T05:03:56Z","timestamp":1784610236359,"version":"3.55.0"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Adaptive radiotherapy requires early prediction of treatment response and survival, yet the optimal use of longitudinal cone-beam computed tomography (CBCT) imaging and modeling strategy for small cohorts remains unclear.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To develop a multitask deep learning framework for simultaneous treatment response classification and progression-free survival (PFS) prediction using planning computed tomography (CT), dose, and sequential CBCT, and to evaluate the impact of including different numbers of early CBCT time points on prediction performance within an incremental analysis framework.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 142 lung cancer patients were retrospectively analyzed. A lightweight network with cross-modal attention fusion and dual task heads for treatment response classification and Cox-based survival prediction was trained end-to-end and benchmarked against 12 baseline methods via 5-fold cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Using only the first on-treatment CBCT, the model achieved an area under the receiver operating characteristic curve (AUC) of 0.858 \u00b1 0.078 and a concordance index (C-index) of 0.672 \u00b1 0.058, outperforming all baselines. Ablation analysis confirmed the contributions of attention fusion and multitask training. Additional CBCT scans degraded classification performance, likely due to increased dimensionality relative to the cohort size.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The first on-treatment CBCT provided the strongest early predictive signal for treatment response classification in this cohort; adding subsequent scans degraded classification performance and produced only a marginal change in survival concordance under the current study setting.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1833763","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T04:19:19Z","timestamp":1784607559000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multitask learning for early treatment response and survival prediction in lung cancer radiotherapy using sequential CBCT imaging"],"prefix":"10.3389","volume":"16","author":[{"given":"Yumei","family":"Li","sequence":"first","affiliation":[{"name":"The Second Affiliated Hospital of Guangxi University of Traditional Chinese Medicine","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhouji","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Radiotherapy, Guangxi Zhuang Autonomous Region Ethnic Hospital","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenlong","family":"Luo","sequence":"additional","affiliation":[{"name":"Affiliated Hengyang Hospital of Hunan Normal University & Hengyang Central Hospital","place":["Hengyang, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yejun","family":"Gong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computing and Stochastic Mathematics, School of Mathematics and Statistics, Hunan Normal University","place":["Changsha, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Zhang","sequence":"additional","affiliation":[{"name":"Affiliated Hengyang Hospital of Hunan Normal University & Hengyang Central Hospital","place":["Hengyang, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Affiliated Hengyang Hospital of Hunan Normal University & Hengyang Central Hospital","place":["Hengyang, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Affiliated Hengyang Hospital of Hunan Normal University & Hengyang Central Hospital","place":["Hengyang, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA: A Cancer J For Clin"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1056\/nejmoa1809697","article-title":"Overall survival with durvalumab after chemoradiotherapy in stage III NSCLC","volume":"379","author":"Antonia","year":"2018","journal-title":"N Engl J Med"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/s1470-2045(14)71207-0","article-title":"Standard-dose versus high-dose conformal radiotherapy with concurrent and consolidation carboplatin plus paclitaxel with or without cetuximab for patients with stage IIIA or IIIB non-small-cell lung cancer (RTOG 0617): a randomised, two-by-two factorial phase 3 study","volume":"16","author":"Bradley","year":"2015","journal-title":"Lancet Oncol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.jtho.2015.09.009","article-title":"The IASLC lung cancer staging project: proposals for revision of the TNM stage groupings in the forthcoming (eighth) edition of the TNM classification for lung cancer","volume":"11","author":"Goldstraw","year":"2016","journal-title":"J Thorac Oncol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1038\/nrclinonc.2017.141","article-title":"Radiomics: the bridge between medical imaging and personalized medicine","volume":"14","author":"Lambin","year":"2017","journal-title":"Nat Rev Clin Oncol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"4006","DOI":"10.1038\/ncomms5006","article-title":"Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach","volume":"5","author":"Aerts","year":"2014","journal-title":"Nat Commun"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1002711","article-title":"Deep learning for lung cancer prognostication: A retrospective multicohort radiomics study","volume":"15","author":"Hosny","year":"2018","journal-title":"PloS Med"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/s00066-020-01625-9","article-title":"Radiomics and deep learning in lung cancer","volume":"196","author":"Avanzo","year":"2020","journal-title":"Strahlenther Onkol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1038\/s41598-017-00665-z","article-title":"Delta-radiomics features for the prediction of patient outcomes in nonsmall cell lung cancer","volume":"7","author":"Fave","year":"2017","journal-title":"Sci Rep"},{"key":"B10","doi-asserted-by":"publisher","first-page":"11225","DOI":"10.21037\/tlcr-24-7","article-title":"Predictive value of delta-radiomic features for prognosis of advanced NSCLC patients undergoing ICI therapy","volume":"14","author":"Han","year":"2024","journal-title":"Sci Rep"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2025.1541376","article-title":"Predicting the immune therapy response of advanced non-small cell lung cancer using delta radiomics","volume":"12","author":"Xie","year":"2025","journal-title":"Front Med"},{"key":"B12","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1186\/s13014-023-02340-2","article-title":"Review of cone beam computed tomography based online adaptive radiotherapy: current trend and future direction","volume":"18","author":"Liu","year":"2023","journal-title":"Radiat Oncol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2017.04.016","article-title":"Survival prediction of non-small cell lung cancer patients using radiomics analyses of cone-beam CT images","volume":"123","author":"van Timmeren","year":"2017","journal-title":"Radiother Oncol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"012001","DOI":"10.1088\/2057-1976\/ae308b","article-title":"Patient outcome prognosis for external beam radiation therapy using CBCT-based radiomics: a systematic review","volume":"12","author":"Chang","year":"2026","journal-title":"Biomed Phys Eng Express"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1622060","article-title":"Recent technical advancements and clinical applications of MR-guided radiotherapy in lung cancer treatment","volume":"15","author":"Ma","year":"2025","journal-title":"Front Oncol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"14650","DOI":"10.1038\/s41598-017-14548-w","article-title":"The value of CBCT-based tumor density and volume variations in prediction of early response to chemoradiation therapy in advanced NSCLC","volume":"7","author":"Wen","year":"2017","journal-title":"Sci Rep"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2014.11.030","article-title":"Lung texture in serial thoracic computed tomography scans: correlation of radiomicsbased features with radiation therapy dose and radiation pneumonitis development","volume":"91","author":"Cunliffe","year":"2015","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1097\/md.0000000000010632","article-title":"Early tumor shrinkage served as a prognostic factor for patients with stage III non-small cell lung cancer treated with concurrent chemoradiotherapy","volume":"97","author":"Wei","year":"2018","journal-title":"Med (Baltimore)"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph18063241","article-title":"A pilot study examining the prognostic utility of tumor shrinkage on cone-beam computed tomography (CBCT) for stage III locally advanced non-small cell lung cancer patients treated with definitive chemoradiation","volume":"18","author":"Kang","year":"2021","journal-title":"Int J Environ Res Public Health"},{"key":"B20","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1186\/s12874-018-0482-1","article-title":"DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network","volume":"18","author":"Katzman","year":"2018","journal-title":"BMC Med Res Methodol"},{"key":"B21","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1038\/s41746-025-01903-9","article-title":"Multimodal deep learning model for prognostic prediction in cervical cancer receiving definitive radiotherapy: a multi-center study","volume":"8","author":"Wang","year":"2025","journal-title":"NPJ Digital Med"},{"key":"B22","doi-asserted-by":"publisher","first-page":"11085","DOI":"10.1038\/s41598-024-60781-5","article-title":"Prediction of treatment response after stereotactic radiosurgery of brain metastasis using deep learning and radiomics on longitudinal MRI data","volume":"14","author":"Cho","year":"2024","journal-title":"Sci Rep"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1201\/9781315119694-20","article-title":"Deep-CR MTLR: a multi-modal approach for cancer survival prediction with competing risks","volume":"146","author":"Kim","year":"2021","journal-title":"Proc Mach Learn Res"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3181791","article-title":"DeepMTS: deep multi-task learning for survival prediction in patients with advanced nasopharyngeal carcinoma using pretreatment PET\/CT","volume":"26","author":"Meng","year":"2023","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-026-12322-z","article-title":"A comprehensive multi-task deep learning model for kidney cancer: histological subtyping, clinical staging, and anatomical complexity grading","volume":"36","author":"Lv","year":"2026","journal-title":"Eur Radio"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3390\/onco5030034","article-title":"Multi-task deep learning for simultaneous classification and segmentation in cancer imaging","volume":"15","author":"Rhanoui","year":"2025","journal-title":"Diagnostics"},{"key":"B27","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1186\/s12911-025-03050-3","article-title":"Multitask deep learning model based on multimodal data for predicting recurrence and survival in cancer","volume":"25","author":"Ma","year":"2025","journal-title":"BMC Med Inf Decis Making"},{"key":"B28","article-title":"Layer normalization","volume-title":"Arxiv Preprint Arxiv:1607.06450","author":"Ba","year":"2016"},{"key":"B29","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2023.3286656","article-title":"Prognosis forecast of re-irradiation for recurrent nasopharyngeal carcinoma based on deep learning multi-modal information fusion","volume":"27","author":"Lu","year":"2023","journal-title":"IEEE J BioMed Health Inf"},{"key":"B31","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1038\/s41746-025-01712-0","article-title":"Multimodal fusion model for prognostic prediction and radiotherapy response assessment in head and neck squamous cell carcinoma","volume":"8","author":"Tian","year":"2025","journal-title":"NPJ Digital Med"},{"key":"B32","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-72086-4_43","article-title":"M2Fusion: multi-time multimodal fusion for prediction of pathological complete response in breast cancer","author":"Zhang","year":"2024"},{"key":"B33","doi-asserted-by":"publisher","first-page":"19055","DOI":"10.1038\/s41598-024-70055-9","article-title":"Multimodal MRI-based deep-radiomics model predicts response in cervical cancer treated with neoadjuvant chemoradiotherapy","volume":"14","author":"Cai","year":"2024","journal-title":"Sci Rep"},{"key":"B34","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/978-1-4612-4380-9_37","article-title":"Regression models and life-tables","volume":"34","author":"Cox","year":"1972","journal-title":"J R Stat Society: Ser B (Methodological)"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v039.i05","article-title":"Regularization paths for Cox\u2019s proportional hazards model via coordinate descent","volume":"39","author":"Simon","year":"2011","journal-title":"J Stat Software"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1201\/9781003493679-19","article-title":"Random survival forests","volume":"2","author":"Ishwaran","year":"2008","journal-title":"Ann Appl Stat"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/kxj011","article-title":"Survival ensembles","volume":"7","author":"Hothorn","year":"2006","journal-title":"Biostatistics"},{"key":"B38","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1364\/BOE.541570","article-title":"MultiDeepsurv: survival analysis of gastric cancer based on deep learning multimodal fusion models","volume":"16","author":"Mao","year":"2024","journal-title":"Biomedical Optics Express"},{"key":"B39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10489-024-05794-3","article-title":"Deep-SEA: a deep learning based patient specific multi-modality postcancer survival estimation architecture","volume":"54","author":"Ahmad","year":"2024","journal-title":"Appl Intell"},{"key":"B40","article-title":"RobSurv: Vector Quantization-Based Multi-Modal Learning for Robust Cancer Survival Prediction","volume-title":"arXiv","author":"Farooq","year":"2025"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1833763\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T04:19:20Z","timestamp":1784607560000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1833763\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":40,"alternative-id":["10.3389\/fonc.2026.1833763"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1833763","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,21]]},"article-number":"1833763"}}