{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T11:05:47Z","timestamp":1789211147364,"version":"build-2803163510"},"reference-count":49,"publisher":"BMJ","issue":"9","license":[{"start":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000},"content-version":"unspecified","delay-in-days":10,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"the 1.3.5 Project for Disciplines of Excellence, West China Hospital, Sichuan University","award":["2023-245"],"award-info":[{"award-number":["2023-245"]}]},{"name":"Sichuan Science and Technology Department Key Research and Development Project","award":["2024YFFK0065"],"award-info":[{"award-number":["2024YFFK0065"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFB3308501"],"award-info":[{"award-number":["2023YFB3308501"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFB3311700"],"award-info":[{"award-number":["2024YFB3311700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program","award":["2025ZNSFSC1764"],"award-info":[{"award-number":["2025ZNSFSC1764"]}]},{"name":"Sichuan Science and Technology Program","award":["2026NSFSC1939"],"award-info":[{"award-number":["2026NSFSC1939"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["82604040"],"award-info":[{"award-number":["82604040"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["J Immunother Cancer"],"accepted":{"date-parts":[[2026,8,17]]},"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Pancreatic ductal adenocarcinoma (PDAC) remains one of the most lethal malignancies. Tertiary lymphoid structures (TLS) have emerged as key components of the tumor immune microenvironment, associated with improved survival and enhanced immunotherapy response. However, non-invasive detection of TLS remains a significant clinical challenge.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This multicenter study aimed to develop and validate a deep learning-based CT model to noninvasively predict TLS status and evaluate its prognostic and predictive value across surgical, non-surgical, and prospective immunochemotherapy cohorts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>We enrolled 223 surgically resected patients with PDAC from two centers for model development and 82 non-surgical patients for clinical validation. A ResNet50-based deep learning network (DLN) was trained to predict TLS status from preoperative contrast-enhanced CT. The locked model was evaluated in 44 patients from a prospective immunochemotherapy trial (ChiCTR2000032293), with pathology-anchored verification, outcome assessment, and spatial immune profiling via cyclic multiplex tyramide signal amplification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The DLN achieved area under the curves (AUCs) of 0.987, 0.937, and 0.853 in training, internal, and external validation cohorts. In the non-surgical cohort (n=82), DLN-predicted TLS-positive patients had significantly longer overall survival (OS; median 19 vs 7 months; HR=3.611, p&lt;0.0001). In the prospective cohort, pathology-anchored verification yielded an AUC of 0.929 (specificity=1.000). DLN-high patients demonstrated superior objective response rate (90.0% vs 26.5%, p=0.001), progression-free survival (PFS) (median 13.1 vs 5.3 months, p&lt;0.001), and OS (median 17.6 vs 8.7 months, p&lt;0.001). The DLN score independently predicted OS (HR=0.052, p&lt;0.001) and PFS (HR=0.079, p&lt;0.001) in multivariable analysis. The DLN score was orthogonal to programmed death-ligand 1 (PD-L1) expression (rho=0.011, p=0.946) but correlated with dendritic cell-T helper cell spatial interactions (p=0.037) and T helper-B cell spatial co-localization (rho=0.307, p=0.043)\u2014two hallmarks of functional TLS architecture\u2014and inversely with tumor cell density (rho=\u22120.399, p=0.007).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This DLN-based CT model reliably predicts TLS status in PDAC with prospectively validated prognostic and predictive value in immunochemotherapy, biological grounding in TLS-associated spatial immune architecture, and orthogonal predictive value to PD-L1, supporting a complementary biomarker strategy for immunotherapy patient selection.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/jitc-2026-015705","type":"journal-article","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T10:15:13Z","timestamp":1789208113000},"page":"e015705","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning-based CT model for non-invasive prediction of tertiary lymphoid structures in pancreatic cancer: a multicenter study with prospective validation in an immunochemotherapy cohort"],"prefix":"10.1136","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6351-4250","authenticated-orcid":false,"given":"Haopeng","family":"Yu","sequence":"first","affiliation":[{"name":"Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoying","family":"Li","sequence":"additional","affiliation":[{"name":"Health and Management Center, General Practice Medical Center, West China Hospital of Sichuan University, Chengdu, Sichuan, China"},{"name":"Division of Abdominal Tumor, Department of Medical Oncology, Cancer Center, Laboratory of Abdominal Tumor Immunology and Microenvironment, State Key Laboratory of Biotherapy, West China Hospital of Sichuan University, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China"},{"name":"Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China"},{"name":"Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital of Sichuan University, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China"},{"name":"Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital of Sichuan University, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingjie","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China"},{"name":"Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital of Sichuan University, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixing","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2755-7258","authenticated-orcid":false,"given":"Dan","family":"Cao","sequence":"additional","affiliation":[{"name":"Division of Abdominal Tumor, Department of Medical Oncology, Cancer Center, Laboratory of Abdominal Tumor Immunology and Microenvironment, State Key Laboratory of Biotherapy, West China Hospital of Sichuan University, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"2026091203150801000_14.9.e015705.1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21820"},{"key":"2026091203150801000_14.9.e015705.2","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-020-17226-0","article-title":"\u03baB-Ras and Ral GTPases regulate acinar to ductal metaplasia during pancreatic adenocarcinoma development and pancreatitis","volume":"11","author":"Beel","year":"2020","journal-title":"Nat Commun"},{"key":"2026091203150801000_14.9.e015705.3","doi-asserted-by":"crossref","DOI":"10.1126\/science.abf9419","article-title":"Tertiary lymphoid structures in cancer","volume":"375","author":"Schumacher","year":"2022","journal-title":"Science"},{"key":"2026091203150801000_14.9.e015705.4","doi-asserted-by":"publisher","DOI":"10.1038\/s41423-020-0457-0"},{"key":"2026091203150801000_14.9.e015705.5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1922-8"},{"key":"2026091203150801000_14.9.e015705.6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1914-8"},{"key":"2026091203150801000_14.9.e015705.7","doi-asserted-by":"publisher","DOI":"10.1038\/s41568-019-0144-6"},{"key":"2026091203150801000_14.9.e015705.8","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2022-328697"},{"key":"2026091203150801000_14.9.e015705.9","doi-asserted-by":"crossref","first-page":"794","DOI":"10.1038\/s43018-021-00232-6","article-title":"Mature tertiary lymphoid structures predict immune checkpoint inhibitor efficacy in solid tumors independently of PD-L1 expression","volume":"2","author":"Vanhersecke","year":"2021","journal-title":"Nat Cancer"},{"key":"2026091203150801000_14.9.e015705.10","doi-asserted-by":"crossref","DOI":"10.1136\/jitc-2023-006698","article-title":"Characterization of intratumoral tertiary lymphoid structures in pancreatic ductal adenocarcinoma: cellular properties and prognostic significance","volume":"11","author":"Zou","year":"2023","journal-title":"J Immunother Cancer"},{"key":"2026091203150801000_14.9.e015705.11","doi-asserted-by":"crossref","DOI":"10.1080\/2162402X.2021.1900635","article-title":"Germinal center reactions in tertiary lymphoid structures associate with neoantigen burden, humoral immunity and long-term survivorship in pancreatic cancer","volume":"10","author":"J Gunderson","year":"2021","journal-title":"Oncoimmunology"},{"key":"2026091203150801000_14.9.e015705.12","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/978-1-4939-8709-2_5","article-title":"A Quantitative Pathology Approach to Analyze the Development of Human Cancer-Associated Tertiary Lymphoid Structures","volume":"1845","author":"Sili\u0146a","year":"2018","journal-title":"Methods Mol Biol"},{"key":"2026091203150801000_14.9.e015705.13","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1631\/jzus.B2200605","article-title":"Detection and quantitative analysis of tumor-associated tertiary lymphoid structures","volume":"24","author":"Yang","year":"2023","journal-title":"J Zhejiang Univ Sci B"},{"key":"2026091203150801000_14.9.e015705.14","doi-asserted-by":"publisher","DOI":"10.1038\/s41379-019-0291-z"},{"key":"2026091203150801000_14.9.e015705.15","doi-asserted-by":"crossref","DOI":"10.3389\/fimmu.2021.674375","article-title":"Therapeutic Induction of Tertiary Lymphoid Structures in Cancer Through Stromal Remodeling","volume":"12","author":"Johansson-Percival","year":"2021","journal-title":"Front Immunol"},{"key":"2026091203150801000_14.9.e015705.16","doi-asserted-by":"publisher","DOI":"10.1016\/j.it.2015.12.001"},{"key":"2026091203150801000_14.9.e015705.17","doi-asserted-by":"publisher","DOI":"10.1038\/ni.3290"},{"key":"2026091203150801000_14.9.e015705.18","doi-asserted-by":"crossref","first-page":"e33","DOI":"10.1016\/S2589-7500(23)00208-X","article-title":"End-to-end prognostication in colorectal cancer by deep learning: a retrospective, multicentre study","volume":"6","author":"Jiang","year":"2024","journal-title":"Lancet Digit Health"},{"key":"2026091203150801000_14.9.e015705.19","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1016\/S0140-6736(19)32998-8","article-title":"Deep learning for prediction of colorectal cancer outcome: a discovery and validation study","volume":"395","author":"Skrede","year":"2020","journal-title":"Lancet"},{"key":"2026091203150801000_14.9.e015705.20","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-01174-9"},{"key":"2026091203150801000_14.9.e015705.21","doi-asserted-by":"crossref","DOI":"10.1126\/scitranslmed.abo4802","article-title":"Improving breast cancer diagnostics with deep learning for MRI","volume":"14","author":"Witowski","year":"2022","journal-title":"Sci Transl Med"},{"key":"2026091203150801000_14.9.e015705.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-019-0447-x"},{"key":"2026091203150801000_14.9.e015705.23","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.22.01345"},{"key":"2026091203150801000_14.9.e015705.24","doi-asserted-by":"publisher","DOI":"10.1177\/0003134820982557"},{"key":"2026091203150801000_14.9.e015705.25","doi-asserted-by":"crossref","first-page":"e68","DOI":"10.1097\/SLA.0000000000005465","article-title":"Deep Learning for Fully Automated Prediction of Overall Survival in Patients Undergoing Resection for Pancreatic Cancer: A Retrospective Multicenter Study","volume":"278","author":"Yao","year":"2023","journal-title":"Ann Surg"},{"key":"2026091203150801000_14.9.e015705.26","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-024-67757-5","article-title":"Deep learning predicts the 1-year prognosis of pancreatic cancer patients using positive peritoneal washing cytology","volume":"14","author":"Noguchi","year":"2024","journal-title":"Sci Rep"},{"key":"2026091203150801000_14.9.e015705.27","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.220152"},{"key":"2026091203150801000_14.9.e015705.28","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02332-5"},{"key":"2026091203150801000_14.9.e015705.29","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02640-w"},{"key":"2026091203150801000_14.9.e015705.30","doi-asserted-by":"crossref","first-page":"110309","DOI":"10.1016\/j.ejrad.2022.110309","article-title":"Preoperative prediction of intra-tumoral tertiary lymphoid structures based on CT in hepatocellular cancer","volume":"151","author":"Li","year":"2022","journal-title":"Eur J Radiol"},{"key":"2026091203150801000_14.9.e015705.31","doi-asserted-by":"crossref","first-page":"3206","DOI":"10.1007\/s00330-024-11255-9","article-title":"A novel hybrid model for predicting tertiary lymphoid structures and targeted immunotherapy outcomes in hepatocellular carcinoma: a multicenter retrospective study","volume":"35","author":"Li","year":"2025","journal-title":"Eur Radiol"},{"key":"2026091203150801000_14.9.e015705.32","doi-asserted-by":"crossref","DOI":"10.1136\/jitc-2024-011126","article-title":"Transfer learning radiomic model predicts intratumoral tertiary lymphoid structures in hepatocellular carcinoma: a multicenter study","volume":"13","author":"Long","year":"2025","journal-title":"J Immunother Cancer"},{"key":"2026091203150801000_14.9.e015705.33","doi-asserted-by":"crossref","first-page":"1206","DOI":"10.1002\/jmri.28900","article-title":"Analysis of the Correlation and Prognostic Significance of Tertiary Lymphoid Structures in Breast Cancer: A Radiomics\u2010Clinical Integration Approach","volume":"59","author":"Li","year":"2024","journal-title":"J Magn Reson Imaging"},{"key":"2026091203150801000_14.9.e015705.34","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1002\/jmri.29128","article-title":"Association Between MRI Radiomics and Intratumoral Tertiary Lymphoid Structures in Intrahepatic Cholangiocarcinoma and Its Prognostic Significance","volume":"60","author":"Xu","year":"2024","journal-title":"J Magn Reson Imaging"},{"key":"2026091203150801000_14.9.e015705.35","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1186\/s40644-024-00813-5","article-title":"Preoperative assessment of tertiary lymphoid structures in stage I lung adenocarcinoma using CT radiomics: a multicenter retrospective cohort study","volume":"24","author":"Zhao","year":"2024","journal-title":"Cancer Imaging"},{"key":"2026091203150801000_14.9.e015705.36","doi-asserted-by":"crossref","DOI":"10.1186\/s13244-025-01906-w","article-title":"Determining the status of tertiary lymphoid structures in invasive pulmonary adenocarcinoma based on chest CT radiomic features","volume":"16","author":"Yu","year":"2025","journal-title":"Insights Imaging"},{"key":"2026091203150801000_14.9.e015705.37","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1038\/s41392-024-02031-8","article-title":"Spatial interactions of immune cells as potential predictors to efficacy of toripalimab plus chemotherapy in locally advanced or metastatic pancreatic ductal adenocarcinoma: a phase Ib\/II trial","volume":"9","author":"Cheng","year":"2024","journal-title":"Sig Transduct Target Ther"},{"key":"2026091203150801000_14.9.e015705.38","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1097\/JP9.0000000000000148","article-title":"Computed tomography-based delta radiomics of tumor core_edge combination for systemic treatment response evaluation in pancreatic cancer","volume":"7","author":"Li","year":"2024","journal-title":"Journal of Pancreatology"},{"key":"2026091203150801000_14.9.e015705.39","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1097\/JP9.0000000000000156","article-title":"Modern radiological assessment after neoadjuvant therapy in pancreatic cancer: an overview","volume":"7","author":"Steingr\u00fcber","year":"2024","journal-title":"Journal of Pancreatology"},{"key":"2026091203150801000_14.9.e015705.40","doi-asserted-by":"crossref","first-page":"21385","DOI":"10.1021\/acsnano.5c01280","article-title":"Cognate Nanovaccine Promotes Tertiary Lymphoid Structures Function and Strengthens Immune Cell Cross-Talk by Targeting Exhausted T Cells in Nonimmunogenic Cancers","volume":"19","author":"Chen","year":"2025","journal-title":"ACS Nano"},{"key":"2026091203150801000_14.9.e015705.41","doi-asserted-by":"publisher","DOI":"10.1158\/2326-6066.CIR-24-0299"},{"key":"2026091203150801000_14.9.e015705.42","doi-asserted-by":"publisher","DOI":"10.1038\/bjc.2015.145"},{"key":"2026091203150801000_14.9.e015705.43","doi-asserted-by":"publisher","DOI":"10.1158\/2326-6066.CIR-14-0027"},{"key":"2026091203150801000_14.9.e015705.44","doi-asserted-by":"crossref","first-page":"1543","DOI":"10.1016\/j.jcmgh.2021.06.023","article-title":"Pancreatic Cancer Chemotherapy Is Potentiated by Induction of Tertiary Lymphoid Structures in Mice","volume":"12","author":"Delvecchio","year":"2021","journal-title":"Cell Mol Gastroenterol Hepatol"},{"key":"2026091203150801000_14.9.e015705.45","doi-asserted-by":"crossref","first-page":"1222719","DOI":"10.3389\/fimmu.2023.1222719","article-title":"Tertiary lymphoid structures in pancreatic cancer: a new target for immunotherapy","volume":"14","author":"Zou","year":"2023","journal-title":"Front Immunol"},{"key":"2026091203150801000_14.9.e015705.46","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-35615-5"},{"key":"2026091203150801000_14.9.e015705.47","doi-asserted-by":"crossref","DOI":"10.1007\/s00262-025-04205-x","article-title":"Assessment of tertiary lymphoid structures via 18F-FDG PET\/CT scan in patients with pancreatic adenocarcinoma","volume":"74","author":"Yan","year":"2025","journal-title":"Cancer Immunol Immunother"},{"key":"2026091203150801000_14.9.e015705.48","doi-asserted-by":"crossref","first-page":"1076","DOI":"10.1038\/s41586-024-08426-5","article-title":"IL-33-activated ILC2s induce tertiary lymphoid structures in pancreatic cancer","volume":"638","author":"Amisaki","year":"2025","journal-title":"Nature"},{"key":"2026091203150801000_14.9.e015705.49","doi-asserted-by":"publisher","DOI":"10.1158\/2326-6066.Cir-25-0387"}],"container-title":["Journal for ImmunoTherapy of Cancer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/jitc-2026-015705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T10:15:18Z","timestamp":1789208118000},"score":1,"resource":{"primary":{"URL":"https:\/\/jitc.bmj.com\/lookup\/doi\/10.1136\/jitc-2026-015705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":49,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,12]]},"published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1136\/jitc-2026-015705"],"URL":"https:\/\/doi.org\/10.1136\/jitc-2026-015705","relation":{},"ISSN":["2051-1426"],"issn-type":[{"value":"2051-1426","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}