{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T12:19:48Z","timestamp":1787141988557,"version":"build-2736575974"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T00:00:00Z","timestamp":1776297600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"vor","delay-in-days":40,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["82572319"],"award-info":[{"award-number":["82572319"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["81971653"],"award-info":[{"award-number":["81971653"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["2024M762244"],"award-info":[{"award-number":["2024M762244"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the PostDoctor Research Fund of West China Hospital,Sichuan University","award":["2025HXBH087"],"award-info":[{"award-number":["2025HXBH087"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>\n                      Mantle cell lymphoma (MCL) is a rare, biologically heterogeneous B-cell malignancy with highly variable outcomes. Existing prognostic tools are suboptimal. We developed an interpretable deep learning framework integrating baseline [\n                      <jats:sup>18<\/jats:sup>\n                      F]FDG PET\/CT and electronic health record (EHR) data for individualized risk stratification.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this multicenter study, 187 treatment-na\u00efve MCL patients were analyzed. A mixture-of-experts (MoE) fusion network integrated multimodal representations from PET\/CT and EHR data. Expert modules comprising vision encoders, radiomics extractors, and a medical language model were integrated through an attention-based gating mechanism to construct multimodal radiomic signatures (R-signatures) predictive of progression-free survival (PFS) and overall survival (OS). R-signatures were validated and incorporated with clinical and metabolic factors into multiparametric models. Deep learning model interpretability was evaluated using attention visualization, expert-level contributions and pathologic correlation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      R-signatures robustly discriminated relapse (AUC\u2009=\u20090.893 training, 0.755 validation) and death (AUC\u2009=\u20090.804 and 0.844), and independently predicted adverse outcomes (PFS: HR\u2009=\u200927.70,\n                      <jats:italic>P<\/jats:italic>\n                      \u2009&lt;\u20090.001; OS: HR\u2009=\u20096.86,\n                      <jats:italic>P<\/jats:italic>\n                      \u2009=\u20090.001). Multiparametric models integrating R-signatures with total lesion glycolysis, \u03b22-microglobulin, WBC, and Ki-67 outperformed conventional indices (C-indices: PFS 0.892 training, 0.781 validation; OS 0.877 training, 0.862 validation). Time-dependent ROC analyses consistently showed AUCs approaching or exceeding 0.800. Calibration and decision curve analyses confirmed excellent agreement and superior clinical net benefit. Attention maps localized high-weighted regions to hypermetabolic tumor areas, with higher R-signature values in blastoid and pleomorphic variants versus classical histology (\n                      <jats:italic>P<\/jats:italic>\n                      \u2009=\u20090.028 and\n                      <jats:italic>P<\/jats:italic>\n                      \u2009=\u20090.010).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This interpretable PET\/CT-EHR fusion framework substantially improves prognostic precision in MCL, providing a noninvasive, clinically translatable tool for risk-adapted management.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12916-026-04865-1","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T10:19:06Z","timestamp":1776334746000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Interpretable multimodal PET\/CT-EHR fusion via mixture-of-experts for prognostic stratification in mantle cell lymphoma: a multicenter study"],"prefix":"10.1186","volume":"24","author":[{"given":"Chong","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zitong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zekun","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chongyang","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Teng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Limin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linhao","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,16]]},"reference":[{"key":"4865_CR1","doi-asserted-by":"publisher","first-page":"2495","DOI":"10.1056\/NEJMra2202672","volume":"386","author":"JO Armitage","year":"2022","unstructured":"Armitage JO, Longo DL. Mantle-cell lymphoma. N Engl J Med. 2022;386:2495\u2013506.","journal-title":"N Engl J Med"},{"key":"4865_CR2","doi-asserted-by":"publisher","first-page":"1350","DOI":"10.1182\/bloodadvances.2021005715","volume":"6","author":"A Castellino","year":"2022","unstructured":"Castellino A, Wang Y, Larson MC, Maurer MJ, Link BK, Farooq U, et al. Evolving frontline immunochemotherapy for mantle cell lymphoma and the impact on survival outcomes. Blood Adv. 2022;6:1350\u201360.","journal-title":"Blood Adv"},{"key":"4865_CR3","doi-asserted-by":"crossref","unstructured":"Vose JM, Fu K, Wang L, Mansoor A, Stewart D, Cheng H, et al. Integrative analysis of clinicopathological features defines novel prognostic models for mantle cell lymphoma in the immunochemotherapy era: a report from The North American Mantle Cell Lymphoma Consortium.\u00a0J Hematol Oncol. 2023;16:122. Published 2023 Dec 16.","DOI":"10.1186\/s13045-023-01520-7"},{"key":"4865_CR4","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1182\/blood.2023022352","volume":"145","author":"CE Ryan","year":"2025","unstructured":"Ryan CE, Armand P, LaCasce AS. Frontline management of mantle cell lymphoma. Blood. 2025;145:663\u201372.","journal-title":"Blood"},{"key":"4865_CR5","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1182\/blood-2007-06-095331","volume":"111","author":"E Hoster","year":"2008","unstructured":"Hoster E, Dreyling M, Klapper W, Gisselbrecht C, van Hoof A, Kluin-Nelemans HC, et al. A new prognostic index (MIPI) for patients with advanced-stage mantle cell lymphoma. Blood. 2008;111:558\u201365.","journal-title":"Blood"},{"key":"4865_CR6","doi-asserted-by":"publisher","first-page":"1386","DOI":"10.1200\/JCO.2015.63.8387","volume":"34","author":"E Hoster","year":"2016","unstructured":"Hoster E, Rosenwald A, Berger F, Bernd H-W, Hartmann S, Loddenkemper C, et al. Prognostic Value of Ki-67 Index, Cytology, and Growth Pattern in Mantle-Cell Lymphoma: Results from Randomized Trials of the European Mantle Cell Lymphoma Network. J Clin Oncol. 2016;34:1386\u201394.","journal-title":"J Clin Oncol"},{"key":"4865_CR7","doi-asserted-by":"publisher","first-page":"1118","DOI":"10.6004\/jnccn.2023.0057","volume":"21","author":"AD Zelenetz","year":"2023","unstructured":"Zelenetz AD, Gordon LI, Abramson JS, Advani RH, Andreadis B, Bartlett NL, et al. NCCN guidelines\u00ae insights: B-cell lymphomas, version 6.2023. J Natl Compr Canc Netw. 2023;21:1118\u201331.","journal-title":"J Natl Compr Canc Netw"},{"key":"4865_CR8","doi-asserted-by":"publisher","DOI":"10.1002\/hon.70009","volume":"43","author":"D Albano","year":"2025","unstructured":"Albano D, Bianchetti N, Talin A, Dondi F, Re A, Tucci A, et al. Prognostic Role of Pretreatment Tumor Burden and Dissemination Features From 2-[18F]FDG PET\/CT in Advanced Mantle Cell Lymphoma. Hematol Oncol. 2025;43:e70009.","journal-title":"Hematol Oncol"},{"key":"4865_CR9","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1080\/10428194.2022.2131415","volume":"64","author":"VKJ Vergote","year":"2023","unstructured":"Vergote VKJ, Verhoef G, Janssens A, Woei-A-Jin FJSH, Laenen A, Tousseyn T, et al. [18F]FDG-PET\/CT volumetric parameters can predict outcome in untreated mantle cell lymphoma. Leuk Lymphoma. 2023;64:161\u201370.","journal-title":"Leuk Lymphoma"},{"key":"4865_CR10","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1038\/s42256-023-00633-5","volume":"5","author":"S Steyaert","year":"2023","unstructured":"Steyaert S, Pizurica M, Nagaraj D, Khandelwal P, Hernandez-Boussard T, Gentles AJ, et al. Multimodal data fusion for cancer biomarker discovery with deep learning. Nat Mach Intell. 2023;5:351\u201362.","journal-title":"Nat Mach Intell"},{"key":"4865_CR11","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1016\/j.ccell.2022.09.012","volume":"40","author":"J Lipkova","year":"2022","unstructured":"Lipkova J, Chen RJ, Chen B, Lu MY, Barbieri M, Shao D, et al. Artificial intelligence for multimodal data integration in oncology. Cancer Cell. 2022;40:1095\u2013110.","journal-title":"Cancer Cell"},{"key":"4865_CR12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-26990-6","volume":"12","author":"L Lu","year":"2021","unstructured":"Lu L, Dercle L, Zhao B, Schwartz LH. Deep learning for the prediction of early on-treatment response in metastatic colorectal cancer from serial medical imaging. Nat Commun. 2021;12:6654.","journal-title":"Nat Commun"},{"key":"4865_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2024.105183","volume":"104","author":"L Yao","year":"2024","unstructured":"Yao L, Li S, Tao Q, Mao Y, Dong J, Lu C, et al. Deep learning for colorectal cancer detection in contrast-enhanced CT without bowel preparation: a retrospective, multicentre study. EBioMedicine. 2024;104:105183.","journal-title":"EBioMedicine"},{"key":"4865_CR14","doi-asserted-by":"publisher","DOI":"10.1136\/jitc-2024-009348","volume":"12","author":"G Ye","year":"2024","unstructured":"Ye G, Wu G, Qi Y, Li K, Wang M, Zhang C, et al. Non-invasive multimodal CT deep learning biomarker to predict pathological complete response of non-small cell lung cancer following neoadjuvant immunochemotherapy: a multicenter study. J Immunother Cancer. 2024;12:e009348.","journal-title":"J Immunother Cancer"},{"key":"4865_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2024.102969","volume":"78","author":"X Chen","year":"2024","unstructured":"Chen X, Zhang H, Guo D, Yang S, Liu B, Hao Y, et al. Risk of intraoperative hemorrhage during cesarean scar ectopic pregnancy surgery: development and validation of an interpretable machine learning prediction model. EClinicalMedicine. 2024;78:102969.","journal-title":"EClinicalMedicine"},{"key":"4865_CR16","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-018-0029-1","volume":"1","author":"A Rajkomar","year":"2018","unstructured":"Rajkomar A, Oren E, Chen K, Dai AM, Hajaj N, Hardt M, et al. Scalable and accurate deep learning with electronic health records. NPJ Digit Med. 2018;1:18.","journal-title":"NPJ Digit Med"},{"key":"4865_CR17","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-13504-7","volume":"12","author":"I Twick","year":"2022","unstructured":"Twick I, Zahavi G, Benvenisti H, Rubinstein R, Woods MS, Berkenstadt H, et al. Towards interpretable, medically grounded, EMR-based risk prediction models. Sci Rep. 2022;12:9990.","journal-title":"Sci Rep"},{"key":"4865_CR18","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1038\/s41746-021-00427-2","volume":"4","author":"E Wulczyn","year":"2021","unstructured":"Wulczyn E, Steiner DF, Moran M, Plass M, Reihs R, Tan F, et al. Interpretable survival prediction for colorectal cancer using deep learning. NPJ Digit Med. 2021;4:71.","journal-title":"NPJ Digit Med"},{"key":"4865_CR19","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1038\/s44287-023-00012-7","volume":"1","author":"CD Bahadir","year":"2024","unstructured":"Bahadir CD, Omar M, Rosenthal J, Marchionni L, Liechty B, Pisapia DJ, et al. Artificial intelligence applications in histopathology. Nat Rev Electr Eng. 2024;1:93\u2013108.","journal-title":"Nat Rev Electr Eng"},{"key":"4865_CR20","doi-asserted-by":"crossref","unstructured":"Tang Y, Yang D, Li W, Roth HR, Landman BA, Xu D, et al. Self-supervised pre-training of swin transformers for 3D medical image analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. New Orleans, LA: IEEE; 2022. p. 20730\u201320740.","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"4865_CR21","doi-asserted-by":"crossref","unstructured":"Eertink JJ, Pfaehler EAG, Wiegers SE, van T, Brug d, Lugtenburg PJ, et al. Quantitative Radiomics features in diffuse large B-Cell lymphoma: does Segmentation Method Matter? J Nucl Med. 2022;63:389\u201395.","DOI":"10.2967\/jnumed.121.262117"},{"key":"4865_CR22","first-page":"3876","volume":"2022","author":"Z Wang","year":"2022","unstructured":"Wang Z, Wu Z, Agarwal D, Sun J. MedCLIP: Contrastive Learning from Unpaired Medical Images and Text. Proc Conf Empir Methods Nat Lang Process. 2022;2022:3876\u201387.","journal-title":"Proc Conf Empir Methods Nat Lang Process"},{"key":"4865_CR23","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma J, He Y, Li F, Han L, You C, Wang B. Segment anything in medical images. Nat Commun. 2024;15:654.","journal-title":"Nat Commun"},{"key":"4865_CR24","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00455-y","volume":"4","author":"L Rasmy","year":"2021","unstructured":"Rasmy L, Xiang Y, Xie Z, Tao C, Zhi D. Med-BERT: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction. NPJ Digit Med. 2021;4:86.","journal-title":"NPJ Digit Med"},{"issue":"Suppl 1","key":"4865_CR25","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1002\/hon.3149","volume":"41","author":"E Silkenstedt","year":"2023","unstructured":"Silkenstedt E, Dreyling M. Mantle cell lymphoma-update on molecular biology, prognostication and treatment approaches. Hematol Oncol. 2023;41(Suppl 1):36\u201342.","journal-title":"Hematol Oncol"},{"key":"4865_CR26","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. Predicting cancer outcomes with radiomics and artificial intelligence in radiology. Nat Rev Clin Oncol. 2022;19:132\u201346.","journal-title":"Nat Rev Clin Oncol"},{"key":"4865_CR27","doi-asserted-by":"publisher","first-page":"2760","DOI":"10.1007\/s00259-019-04420-6","volume":"46","author":"ME Mayerhoefer","year":"2019","unstructured":"Mayerhoefer ME, Riedl CC, Kumar A, Gibbs P, Weber M, Tal I, et al. Radiomic features of glucose metabolism enable prediction of outcome in mantle cell lymphoma. Eur J Nucl Med Mol Imaging. 2019;46:2760\u20139.","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"4865_CR28","doi-asserted-by":"publisher","DOI":"10.3390\/cancers12051138","volume":"12","author":"ME Mayerhoefer","year":"2020","unstructured":"Mayerhoefer ME, Riedl CC, Kumar A, Dogan A, Gibbs P, Weber M, et al. [18F]FDG-PET\/CT radiomics for prediction of bone marrow involvement in mantle cell lymphoma: a retrospective study in 97 patients. Cancers (Basel). 2020;12:1138.","journal-title":"Cancers (Basel)"},{"key":"4865_CR29","doi-asserted-by":"publisher","first-page":"18177","DOI":"10.1038\/s41598-023-45215-y","volume":"13","author":"C Bodet-Milin","year":"2023","unstructured":"Bodet-Milin C, Morvant C, Carlier T, Frecon G, Tournilhac O, Safar V, et al. Performance of baseline FDG-PET\/CT radiomics for prediction of bone marrow minimal residual disease status in the LyMa-101 trial. Sci Rep. 2023;13:18177.","journal-title":"Sci Rep"}],"container-title":["BMC Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12916-026-04865-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12916-026-04865-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12916-026-04865-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T01:15:15Z","timestamp":1779758115000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12916-026-04865-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,16]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["4865"],"URL":"https:\/\/doi.org\/10.1186\/s12916-026-04865-1","relation":{},"ISSN":["1741-7015"],"issn-type":[{"value":"1741-7015","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,16]]},"assertion":[{"value":"24 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study protocol was conducted in accordance with ethical guidelines (Declaration of Helsinki and Istanbul) and approved by the Institutional Ethics Committee of the involved centers (Approval in 2024, No. 1384). Informed consent was waived due to the retrospective nature of this study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"330"}}