{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T07:01:57Z","timestamp":1790060517644,"version":"4.0.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis. Comput. Ind. Biomed. Art"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Prognosis prediction is important for precision treatment in lung cancer. Chest computed tomography (CT) and deep learning are feasible approaches for learning imaging-based prognostic representations. However, prognostic labels are difficult to obtain because survival endpoints require long-term follow-up; thus, labeled data for supervised training is limited, increasing the risk of overfitting. Vision-language pretraining offers an approach to mitigate this problem by leveraging large-scale unlabeled CT data; however, most existing methods are not specifically designed to learn prognosis-related features. We propose ProtoSurv, a prototype-guided learning framework for adapting large-scale pretrained CT representations for lung-cancer prognosis prediction under limited supervision. ProtoSurv first pretrains a CT-report vision-language model using 409,261 chest CT sequences from 104,783 patients. It then uses limited labeled prognosis data to construct class prototypes in the pretrained feature space. These prototypes guide pseudolabel assignment, confidence-based filtering, and feature calibration, allowing the selection and refinement of task-relevant unlabeled samples before downstream prognosis modeling. We evaluated ProtoSurv based on two lung-cancer prognosis tasks: progression-free survival prediction in 507 patients receiving targeted therapy and overall survival prediction in 420 patients receiving (chemo-)radiotherapy. ProtoSurv achieved area under the curve\/concordance index values of 0.765\/0.684 and 0.822\/0.727 for the first and second datasets, respectively, outperforming the conventional clinical models and representative deep learning baselines. These results suggest that the prototype-guided adaptation can improve the use of large-scale unlabeled CT data for prognosis modeling when labeled survival data are limited.<\/jats:p>","DOI":"10.1186\/s42492-026-00233-1","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T06:07:53Z","timestamp":1790057273000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ProtoSurv: prototype-guided adaptation of computed tomography foundation model for lung-cancer prognosis prediction"],"prefix":"10.1186","volume":"9","author":[{"given":"Chengcai","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shitian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haolin","family":"Sang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenghao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Shu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huimao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"issue":"11","key":"233_CR1","doi-asserted-by":"publisher","first-page":"1206","DOI":"10.1016\/S1470-2045(23)00444-8","volume":"24","author":"YT Zhang","year":"2023","unstructured":"Zhang YT, Vaccarella S, Morgan E, Li MM, Etxeberria J, Chokunonga E et al (2023) Global variations in lung cancer incidence by histological subtype in 2020: a population-based study. Lancet Oncol 24(11):1206\u20131218. https:\/\/doi.org\/10.1016\/S1470-2045(23)00444-8","journal-title":"Lancet Oncol"},{"issue":"1","key":"233_CR2","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1002\/cac2.12505","volume":"44","author":"D Miao","year":"2024","unstructured":"Miao D, Zhao J, Han Y, Zhou JQ, Li XZ, Zhang T et al (2024) Management of locally advanced non-small cell lung cancer: state of the art and future directions. Cancer Commun 44(1):23\u201346. https:\/\/doi.org\/10.1002\/cac2.12505","journal-title":"Cancer Commun"},{"issue":"1","key":"233_CR3","doi-asserted-by":"publisher","first-page":"10","DOI":"10.3322\/caac.21871","volume":"75","author":"RL Siegel","year":"2025","unstructured":"Siegel RL, Kratzer TB, Giaquinto AN, Sung H, Jemal A (2025) Cancer statistics, 2025. CA Cancer J Clin 75(1):10\u201345. https:\/\/doi.org\/10.3322\/caac.21871","journal-title":"CA Cancer J Clin"},{"issue":"21","key":"233_CR4","doi-asserted-by":"publisher","first-page":"1935","DOI":"10.1056\/NEJMoa2306434","volume":"389","author":"D Planchard","year":"2023","unstructured":"Planchard D, J\u00e4nne PA, Cheng Y, Yang JCH, Yanagitani N, Kim SW et al (2023) Osimertinib with or without chemotherapy in EGFR-mutated advanced NSCLC. N Engl J Med 389(21):1935\u20131948. https:\/\/doi.org\/10.1056\/NEJMoa2306434","journal-title":"N Engl J Med"},{"issue":"12","key":"233_CR5","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1200\/JCO.21.01308","volume":"40","author":"DR Spigel","year":"2022","unstructured":"Spigel DR, Faivre-Finn C, Gray JE, Vicente D, Planchard D, Paz-Ares L et al (2022) Five-year survival outcomes from the PACIFIC trial: durvalumab after chemoradiotherapy in stage III non-small-cell lung cancer. J Clin Oncol 40(12):1301\u20131311. https:\/\/doi.org\/10.1200\/JCO.21.01308","journal-title":"J Clin Oncol"},{"issue":"12","key":"233_CR6","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/nrclinonc.2017.141","volume":"14","author":"P Lambin","year":"2017","unstructured":"Lambin P, Leijenaar RTH, Deist TM, Peerlings J, de Jong EEC, van Timmeren J et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14(12):749\u2013762. https:\/\/doi.org\/10.1038\/nrclinonc.2017.141","journal-title":"Nat Rev Clin Oncol"},{"issue":"2","key":"233_CR7","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1038\/s41571-021-00560-7","volume":"19","author":"K Bera","year":"2022","unstructured":"Bera K, Braman N, Gupta A, Velcheti V, Madabhushi A (2022) Predicting cancer outcomes with radiomics and artificial intelligence in radiology. Nat Rev Clin Oncol 19(2):132\u2013146. https:\/\/doi.org\/10.1038\/s41571-021-00560-7","journal-title":"Nat Rev Clin Oncol"},{"key":"233_CR8","doi-asserted-by":"publisher","unstructured":"Hricak H, Mayerhoefer ME, Herrmann K, Lewis JS, Pomper MG, Hess CP et al (2025) Advances and challenges in precision imaging. Lancet Oncol 26(1):e34\u2013e45. https:\/\/doi.org\/10.1016\/S1470-2045(24)00395-4","DOI":"10.1016\/S1470-2045(24)00395-4"},{"issue":"3","key":"233_CR9","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/s42256-024-00807-9","volume":"6","author":"S Pai","year":"2024","unstructured":"Pai S, Bontempi D, Hadzic I, Prudente V, Soka\u010d M, Chaunzwa TL et al (2024) Foundation model for cancer imaging biomarkers. Nat Mach Intell 6(3):354\u2013367. https:\/\/doi.org\/10.1038\/s42256-024-00807-9","journal-title":"Nat Mach Intell"},{"key":"233_CR10","doi-asserted-by":"publisher","unstructured":"Saad MB, Hong LZ, Aminu M, Vokes NI, Chen PJ, Salehjahromi M et al (2023) Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study. Lancet Digit Health 5(7):e404\u2013e420. https:\/\/doi.org\/10.1016\/S2589-7500(23)00082-1","DOI":"10.1016\/S2589-7500(23)00082-1"},{"key":"233_CR11","doi-asserted-by":"publisher","unstructured":"Jiang XF, Hoffmeister M, Brenner H, Muti HS, Yuan TW, Foersch S et al (2024) End-to-end prognostication in colorectal cancer by deep learning: a retrospective, multicentre study. Lancet Digit Health 6(1):e33\u2013e43. https:\/\/doi.org\/10.1016\/S2589-7500(23)00208-X","DOI":"10.1016\/S2589-7500(23)00208-X"},{"issue":"9","key":"233_CR12","doi-asserted-by":"publisher","first-page":"100876","DOI":"10.1016\/j.landig.2025.100876","volume":"7","author":"S Voigtlaender","year":"2025","unstructured":"Voigtlaender S, Nelson TA, Karschnia P, Vaios EJ, Kim MM, Lohmann P et al (2025) Value of artificial intelligence in neuro-oncology. Lancet Digit Health 7(9):100876. https:\/\/doi.org\/10.1016\/j.landig.2025.100876","journal-title":"Lancet Digit Health"},{"key":"233_CR13","doi-asserted-by":"publisher","unstructured":"Wang S, Yu H, Gan YC, Wu ZJ, Li EC, Li XH et al (2022) Mining whole-lung information by artificial intelligence for predicting EGFR genotype and targeted therapy response in lung cancer: a multicohort study. Lancet Digit Health 4(5):e309\u2013e319. https:\/\/doi.org\/10.1016\/S2589-7500(22)00024-3","DOI":"10.1016\/S2589-7500(22)00024-3"},{"issue":"1","key":"233_CR14","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1038\/s42256-021-00425-9","volume":"4","author":"HY Zhou","year":"2022","unstructured":"Zhou HY, Chen XY, Zhang YH, Luo RB, Wang LS, Yu YZ (2022) Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports. Nat Mach Intell 4(1):32\u201340. https:\/\/doi.org\/10.1038\/s42256-021-00425-9","journal-title":"Nat Mach Intell"},{"issue":"7956","key":"233_CR15","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","volume":"616","author":"M Moor","year":"2023","unstructured":"Moor M, Banerjee O, Abad ZSH, Krumholz HM, Leskovec J, Topol EJ et al (2023) Foundation models for generalist medical artificial intelligence. Nature 616(7956):259\u2013265. https:\/\/doi.org\/10.1038\/s41586-023-05881-4","journal-title":"Nature"},{"issue":"7","key":"233_CR16","doi-asserted-by":"publisher","first-page":"1636","DOI":"10.1016\/j.cell.2024.02.012","volume":"187","author":"K Verkerk","year":"2024","unstructured":"Verkerk K, Voest EE (2024) Generating and using real-world data: a worthwhile uphill battle. Cell 187(7):1636\u20131650. https:\/\/doi.org\/10.1016\/j.cell.2024.02.012","journal-title":"Cell"},{"issue":"1","key":"233_CR17","doi-asserted-by":"publisher","first-page":"7866","DOI":"10.1038\/s41467-025-62385-7","volume":"16","author":"CY Wu","year":"2025","unstructured":"Wu CY, Zhang XM, Zhang Y, Hui H, Wang YF, Xie WD (2025) Towards generalist foundation model for radiology by leveraging web-scale 2D&3D medical data. Nat Commun 16(1):7866. https:\/\/doi.org\/10.1038\/s41467-025-62385-7","journal-title":"Nat Commun"},{"issue":"1","key":"233_CR18","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1038\/s41746-023-00811-0","volume":"6","author":"SC Huang","year":"2023","unstructured":"Huang SC, Pareek A, Jensen M, Lungren MP, Yeung S, Chaudhari AS (2023) Self-supervised learning for medical image classification: a systematic review and implementation guidelines. npj Digit Med 6(1):74. https:\/\/doi.org\/10.1038\/s41746-023-00811-0","journal-title":"npj Digit Med"},{"key":"233_CR19","doi-asserted-by":"publisher","first-page":"102996","DOI":"10.1016\/j.media.2023.102996","volume":"91","author":"ST Zhang","year":"2024","unstructured":"Zhang ST, Metaxas D (2024) On the challenges and perspectives of foundation models for medical image analysis. Med Image Anal 91:102996. https:\/\/doi.org\/10.1016\/j.media.2023.102996","journal-title":"Med Image Anal"},{"key":"233_CR20","doi-asserted-by":"publisher","first-page":"103023","DOI":"10.1016\/j.media.2023.103023","volume":"91","author":"YT Xie","year":"2024","unstructured":"Xie YT, Zhang JP, Liu LQ, Wang H, Ye YW, Verjans J et al (2024) ReFs: a hybrid pre-training paradigm for 3D medical image segmentation. Med Image Anal 91:103023. https:\/\/doi.org\/10.1016\/j.media.2023.103023","journal-title":"Med Image Anal"},{"key":"233_CR21","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S et al (2021) Learning transferable visual models from natural language supervision. In: Proceedings of the 38th international conference on machine learning, PMLR, Virtual, 18\u201324 July 2021"},{"key":"233_CR22","doi-asserted-by":"publisher","first-page":"103551","DOI":"10.1016\/j.media.2025.103551","volume":"102","author":"ZH Zhao","year":"2025","unstructured":"Zhao ZH, Liu YX, Wu H, Wang M, Li YH, Wang S et al (2025) CLIP in medical imaging: a survey. Med Image Anal 102:103551. https:\/\/doi.org\/10.1016\/j.media.2025.103551","journal-title":"Med Image Anal"},{"issue":"6","key":"233_CR23","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1038\/s41551-025-01516-3","volume":"10","author":"P Neidlinger","year":"2026","unstructured":"Neidlinger P, El Nahhas OSM, Muti HS, Lenz T, Hoffmeister M, Brenner H et al (2026) Benchmarking foundation models as feature extractors for weakly supervised computational pathology. Nat Biomed Eng 10(6):1113\u20131123. https:\/\/doi.org\/10.1038\/s41551-025-01516-3","journal-title":"Nat Biomed Eng"},{"issue":"1","key":"233_CR24","doi-asserted-by":"publisher","first-page":"2366","DOI":"10.1038\/s41467-025-57587-y","volume":"16","author":"ZC Yang","year":"2025","unstructured":"Yang ZC, Wei T, Liang Y, Yuan X, Gao RT, Xia YJ et al (2025) A foundation model for generalizable cancer diagnosis and survival prediction from histopathological images. Nat Commun 16(1):2366. https:\/\/doi.org\/10.1038\/s41467-025-57587-y","journal-title":"Nat Commun"},{"issue":"1","key":"233_CR25","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1038\/s41392-025-02374-w","volume":"10","author":"W Yuan","year":"2025","unstructured":"Yuan W, Chen YJ, Zhu BY, Yang S, Zhang JY, Mao N et al (2025) Pancancer outcome prediction via a unified weakly supervised deep learning model. Signal Transduct Target Ther 10(1):285. https:\/\/doi.org\/10.1038\/s41392-025-02374-w","journal-title":"Signal Transduct Target Ther"},{"key":"233_CR26","doi-asserted-by":"publisher","first-page":"109196","DOI":"10.1016\/j.cmpb.2025.109196","volume":"275","author":"F Ruffini","year":"2026","unstructured":"Ruffini F, Ayll\u00f3n EM, Shen LL, Soda P, Guarrasi V (2026) Benchmarking foundation models and parameter-efficient fine-tuning for prognosis prediction in medical imaging. Comput Methods Programs Biomed 275:109196. https:\/\/doi.org\/10.1016\/j.cmpb.2025.109196","journal-title":"Comput Methods Programs Biomed"},{"key":"233_CR27","doi-asserted-by":"publisher","first-page":"103103","DOI":"10.1016\/j.media.2024.103103","volume":"93","author":"CX Ren","year":"2024","unstructured":"Ren CX, Xu GX, Dai DQ, Lin L, Sun Y, Liu QS (2024) Cross-site prognosis prediction for nasopharyngeal carcinoma from incomplete multi-modal data. Med Image Anal 93:103103. https:\/\/doi.org\/10.1016\/j.media.2024.103103","journal-title":"Med Image Anal"},{"key":"233_CR28","doi-asserted-by":"publisher","unstructured":"Aerts HJWL, Wee L, Rios Velazquez E, Leijenaar RTH, Parmar C, Grossmann P et al (2014) Data from NSCLC-radiomics. The Cancer Imaging Archive. https:\/\/doi.org\/10.7937\/K9\/TCIA.2015.PF0M9REI. Accessed 13 April 2026","DOI":"10.7937\/K9\/TCIA.2015.PF0M9REI."},{"key":"233_CR29","doi-asserted-by":"crossref","unstructured":"Liu Z, Ning J, Cao Y, Wei YX, Zhang Z, Lin S et al (2022) Video swin transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, IEEE, New Orleans, 18\u201324 June 2022","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"233_CR30","unstructured":"Kay W, Carreira J, Simonyan K, Zhang B, Hillier C, Vijayanarasimhan S et al (2017) The kinetics human action video dataset. arXiv preprint arXiv: 1705.06950"},{"issue":"1","key":"233_CR31","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1186\/s41747-020-00173-2","volume":"4","author":"J Hofmanninger","year":"2020","unstructured":"Hofmanninger J, Prayer F, Pan J, R\u00f6hrich S, Prosch H, Langs G (2020) Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem. Eur Radiol Exp 4(1):50. https:\/\/doi.org\/10.1186\/s41747-020-00173-2","journal-title":"Eur Radiol Exp"},{"key":"233_CR32","doi-asserted-by":"crossref","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers), Association for Computational Linguistics, Minneapolis, 2\u20137 June 2019","DOI":"10.18653\/v1\/N19-1423"},{"key":"233_CR33","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, IEEE, Honolulu, 21\u201326 July 2017","DOI":"10.1109\/CVPR.2017.243"},{"key":"233_CR34","unstructured":"Bai F, Du YX, Huang TJ, Meng MQH, Zhao B (2024) M3D: advancing 3D medical image analysis with multi-modal large language models. arXiv preprint arXiv: 2404.00578"}],"container-title":["Visual Computing for Industry, Biomedicine, and Art"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s42492-026-00233-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s42492-026-00233-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s42492-026-00233-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T06:07:58Z","timestamp":1790057278000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s42492-026-00233-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["233"],"URL":"https:\/\/doi.org\/10.1186\/s42492-026-00233-1","relation":{},"ISSN":["2524-4442"],"issn-type":[{"value":"2524-4442","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]},"assertion":[{"value":"11 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests. Jie Tian is the Editor-in-Chief of the journal and he is not involved in the peer review or any decision related to the manuscript.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"21"}}