{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T12:43:18Z","timestamp":1793882598505,"version":"4.7.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T00:00:00Z","timestamp":1766534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T00:00:00Z","timestamp":1766534400000},"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":["J Transl Med"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Gastric cancer (GC) is one of the leading causes of cancer-related deaths globally, with a 5-year survival rate of less than 40%. While immune checkpoint inhibitors have provided promising therapeutic options for advanced GC, only a small proportion of patients benefit. In this study, we developed a deep learning model using whole-slide images to predict prognoses and sensitivity to immune checkpoint inhibitors in GC patients by predicting a novel marker.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Formalin-fixed, paraffin-embedded whole-slide images from 292 patients in the Cancer Genome Atlas-Stomach Adenocarcinoma cohort were analyzed. Tumor regions were identified using a ResNet50-based tumor detection model and validated in HiESD dataset. Tiles classified as malignant were extracted for subsequent analysis. Risk score prediction models were developed using convolutional neural networks, clustering-constrained attention multiple-instance learning (CLAM), and dual-stream multiple-instance learning (DSMIL). Attention heatmap visualization was used to interpret tumor microenvironment (TME) features and a multi-model classification framework utilizing a support vector machine (SVM) was developed to assess the impact of clinical variables in model performances. The results were evaluated using the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, and F1 score.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The tumor detection model achieved an AUROC of 0.99 on the training set, 0.92 on the test set, and 0.87 on external test set. Among risk score prediction models, DSMIL demonstrated the highest performance, with an AUROC of 0.73 and accuracy of 0.73 on the training set and AUROC of 0.70 and accuracy of 0.68 on the internal test set. High-risk patients exhibited worse survival outcomes and lower immunotherapy response rates compared with low-risk patients. Feature attribution analysis using attention heatmaps confirmed that the model prioritized TME components, specifically regions with dense lymphocytic infiltration. The muti-modal analysis showed that the image features alone were superior to the model combining image features with clinicopathological data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Deep learning models leveraging whole-slide images show potential in predicting prognoses and immunotherapy responses in GC. By integrating tumor-specific and tumor microenvironmental features, this approach offers a scalable, objective tool for personalized treatment planning, improving precision oncology strategies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12967-025-07416-z","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T10:27:11Z","timestamp":1766572031000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Translational deep learning models for risk stratification to predict prognosis and immunotherapy response in gastric cancer using digital pathology"],"prefix":"10.1186","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4945-1334","authenticated-orcid":false,"given":"Mai Hanh","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huy-Hoang","family":"Do-Huu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Phuc-Tan","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ngoc Dung","family":"Tran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nguyen Thuy","family":"Linh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hieu","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4896-7926","authenticated-orcid":false,"given":"Nguyen Quoc Khanh","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,24]]},"reference":[{"issue":"12","key":"7416_CR1","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.3748\/wjg.v28.i12.1187","volume":"28","author":"M Ilic","year":"2022","unstructured":"Ilic M, Ilic I. Epidemiology of stomach cancer. World J Gastroenterol. 2022;28(12):1187.","journal-title":"World J Gastroenterol"},{"issue":"15","key":"7416_CR2","doi-asserted-by":"publisher","first-page":"e7365","DOI":"10.1002\/cam4.7365","volume":"13","author":"K Hemminki","year":"2024","unstructured":"Hemminki K, et al. Survival improvements in esophageal and gastric cancers in the nordic countries favor younger patients. Cancer Med. 2024;13(15):e7365.","journal-title":"Cancer Med"},{"issue":"8","key":"7416_CR3","doi-asserted-by":"publisher","first-page":"779","DOI":"10.3748\/wjg.v30.i8.779","volume":"30","author":"JK Triantafillidis","year":"2024","unstructured":"Triantafillidis JK, Konstadoulakis MM, Papalois AE. Immunotherapy of gastric cancer: present status and future perspectives. World J Gastroenterol. 2024;30(8):779.","journal-title":"World J Gastroenterol"},{"key":"7416_CR4","first-page":"p","volume":"189277","author":"J Song","year":"2025","unstructured":"Song J, et al. Advancements in immunotherapy for gastric cancer: unveiling the potential of immune checkpoint inhibitors and emerging strategies. Biochim Et Biophys Acta (BBA)-Reviews Cancer. 2025;189277:p.","journal-title":"Biochim Et Biophys Acta (BBA)-Reviews Cancer"},{"issue":"1","key":"7416_CR5","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s13045-024-01578-x","volume":"17","author":"X Chong","year":"2024","unstructured":"Chong X, et al. Recent developments in immunotherapy for Gastrointestinal tract cancers. J Hematol Oncol. 2024;17(1):65.","journal-title":"J Hematol Oncol"},{"key":"7416_CR6","doi-asserted-by":"publisher","first-page":"934249","DOI":"10.3389\/fonc.2022.934249","volume":"12","author":"J Shen","year":"2022","unstructured":"Shen J, Wang Z. Recent advances in the progress of immune checkpoint inhibitors in the treatment of advanced gastric cancer: A review. Front Oncol. 2022;12:934249.","journal-title":"Front Oncol"},{"issue":"5","key":"7416_CR7","doi-asserted-by":"publisher","first-page":"e180013","DOI":"10.1001\/jamaoncol.2018.0013","volume":"4","author":"CS Fuchs","year":"2018","unstructured":"Fuchs CS, et al. Safety and efficacy of pembrolizumab monotherapy in patients with previously treated advanced gastric and gastroesophageal junction cancer: phase 2 clinical KEYNOTE-059 trial. JAMA Oncol. 2018;4(5):e180013\u2013180013.","journal-title":"JAMA Oncol"},{"issue":"10142","key":"7416_CR8","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/S0140-6736(18)31257-1","volume":"392","author":"K Shitara","year":"2018","unstructured":"Shitara K, et al. Pembrolizumab versus Paclitaxel for previously treated, advanced gastric or gastro-oesophageal junction cancer (KEYNOTE-061): a randomised, open-label, controlled, phase 3 trial. Lancet. 2018;392(10142):123\u201333.","journal-title":"Lancet"},{"key":"7416_CR9","doi-asserted-by":"publisher","first-page":"100718","DOI":"10.1016\/j.drup.2020.100718","volume":"53","author":"E P\u00e9rez-Ruiz","year":"2020","unstructured":"P\u00e9rez-Ruiz E, et al. Cancer immunotherapy resistance based on immune checkpoints inhibitors: Targets, biomarkers, and remedies. Drug Resist Updates. 2020;53:100718.","journal-title":"Drug Resist Updates"},{"issue":"7","key":"7416_CR10","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1016\/j.trecan.2020.02.003","volume":"6","author":"J Cao","year":"2020","unstructured":"Cao J, Yan Q. Cancer Epigenetics, tumor Immunity, and immunotherapy. Trends Cancer. 2020;6(7):580\u201392.","journal-title":"Trends Cancer"},{"issue":"4","key":"7416_CR11","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1007\/s10278-020-00351-z","volume":"33","author":"N Kumar","year":"2020","unstructured":"Kumar N, Gupta R, Gupta S. Whole slide imaging (WSI) in pathology: current perspectives and future directions. J Digit Imaging. 2020;33(4):1034\u201340.","journal-title":"J Digit Imaging"},{"issue":"10","key":"7416_CR12","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.1016\/j.ajpath.2023.06.004","volume":"193","author":"Z Wei","year":"2023","unstructured":"Wei Z, et al. Deep Learning\u2013Based stratification of gastric cancer patients from hematoxylin and Eosin\u2013Stained whole slide images by predicting molecular features for immunotherapy response. Am J Pathol. 2023;193(10):1517\u201327.","journal-title":"Am J Pathol"},{"issue":"1","key":"7416_CR13","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1186\/s12967-024-05262-z","volume":"22","author":"Y Liu","year":"2024","unstructured":"Liu Y, et al. Deep learning based digital pathology for predicting treatment response to first-line PD-1 Blockade in advanced gastric cancer. J Translational Med. 2024;22(1):438.","journal-title":"J Translational Med"},{"key":"7416_CR14","doi-asserted-by":"publisher","first-page":"890922","DOI":"10.3389\/fimmu.2022.890922","volume":"13","author":"Y Chen","year":"2022","unstructured":"Chen Y, et al. Tumor microenvironment characterization for assessment of recurrence and survival outcome in gastric cancer to predict chemotherapy and immunotherapy response. Front Immunol. 2022;13:890922.","journal-title":"Front Immunol"},{"key":"7416_CR15","doi-asserted-by":"publisher","first-page":"961637","DOI":"10.3389\/fonc.2022.961637","volume":"12","author":"G Chen","year":"2022","unstructured":"Chen G, et al. Role of hypoxia in the tumor microenvironment and targeted therapy. Front Oncol. 2022;12:961637.","journal-title":"Front Oncol"},{"key":"7416_CR16","doi-asserted-by":"crossref","unstructured":"Abou Khouzam R, et al. Hypoxia as a potential inducer of immune tolerance, tumor plasticity and a driver of tumor mutational burden: impact on cancer immunotherapy. Semin Cancer Biol. 2023.","DOI":"10.1016\/j.semcancer.2023.11.008"},{"issue":"1","key":"7416_CR17","doi-asserted-by":"publisher","first-page":"e203","DOI":"10.1002\/mco2.203","volume":"4","author":"Y Zhuang","year":"2023","unstructured":"Zhuang Y, et al. Hypoxia signaling in cancer: implications for therapeutic interventions. MedComm. 2023;4(1):e203.","journal-title":"MedComm"},{"issue":"7","key":"7416_CR18","doi-asserted-by":"publisher","first-page":"p552","DOI":"10.3390\/cimb47070552","volume":"47","author":"MH Nguyen","year":"2025","unstructured":"Nguyen MH, et al. A novel Hypoxia-Immune signature for gastric cancer prognosis and immunotherapy: insights from bulk and Single-Cell RNA-Seq. Curr Issues Mol Biol. 2025;47(7):p552.","journal-title":"Curr Issues Mol Biol"},{"issue":"1","key":"7416_CR19","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1158\/2767-9764.CRC-23-0287","volume":"4","author":"M Ligero","year":"2024","unstructured":"Ligero M, et al. Weakly supervised deep learning predicts immunotherapy response in solid tumors based on PD-L1 expression. Cancer Res Commun. 2024;4(1):92\u2013102.","journal-title":"Cancer Res Commun"},{"issue":"1","key":"7416_CR20","doi-asserted-by":"publisher","first-page":"22636","DOI":"10.1038\/s41598-021-02168-4","volume":"11","author":"M Hinata","year":"2021","unstructured":"Hinata M, Ushiku T. Detecting immunotherapy-sensitive subtype in gastric cancer using histologic image-based deep learning. Sci Rep. 2021;11(1):22636.","journal-title":"Sci Rep"},{"issue":"8","key":"7416_CR21","doi-asserted-by":"publisher","first-page":"100208","DOI":"10.1016\/j.modpat.2023.100208","volume":"36","author":"B Li","year":"2023","unstructured":"Li B, et al. Outcome-Supervised deep learning on pathologic whole slide images for survival prediction of immunotherapy in patients with Non\u2013Small cell lung cancer. Mod Pathol. 2023;36(8):100208.","journal-title":"Mod Pathol"},{"issue":"8","key":"7416_CR22","doi-asserted-by":"publisher","first-page":"1506","DOI":"10.3390\/cancers16081506","volume":"16","author":"AA Ahmed","year":"2024","unstructured":"Ahmed AA, et al. Development and validation of a deep learning model for histopathological slide analysis in lung cancer diagnosis. Cancers. 2024;16(8):1506.","journal-title":"Cancers"},{"issue":"1","key":"7416_CR23","doi-asserted-by":"publisher","first-page":"1326","DOI":"10.1038\/s41597-025-05679-1","volume":"12","author":"C Wang","year":"2025","unstructured":"Wang C, et al. A fully annotated pathology slide dataset for early gastric cancer and precancerous lesions. Sci Data. 2025;12(1):1326.","journal-title":"Sci Data"},{"issue":"6","key":"7416_CR24","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","volume":"5","author":"MY Lu","year":"2021","unstructured":"Lu MY, et al. Data-efficient and weakly supervised computational pathology on whole-slide images. Nat Biomedical Eng. 2021;5(6):555\u201370.","journal-title":"Nat Biomedical Eng"},{"key":"7416_CR25","doi-asserted-by":"crossref","unstructured":"Li B, Li Y, Eliceiri KW. Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning. In: Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition; 2021.","DOI":"10.1109\/CVPR46437.2021.01409"},{"key":"7416_CR26","doi-asserted-by":"publisher","first-page":"8239","DOI":"10.2147\/OTT.S152514","volume":"11","author":"K Togasaki","year":"2018","unstructured":"Togasaki K, et al. Clinical efficacy of immune checkpoint inhibitors in the treatment of unresectable advanced or recurrent gastric cancer: an evidence-based review of therapies. Onco Targets Ther. 2018;11:8239\u201350.","journal-title":"Onco Targets Ther"},{"issue":"1","key":"7416_CR27","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1038\/s41392-022-01136-2","volume":"7","author":"D-R Wang","year":"2022","unstructured":"Wang D-R, Wu X-L, Sun Y-L. Therapeutic targets and biomarkers of tumor immunotherapy: response versus non-response. Signal Transduct Target Therapy. 2022;7(1):331.","journal-title":"Signal Transduct Target Therapy"},{"issue":"1","key":"7416_CR28","doi-asserted-by":"publisher","first-page":"2426758","DOI":"10.1080\/07853890.2024.2426758","volume":"56","author":"Q Sun","year":"2024","unstructured":"Sun Q, et al. Integrating transcriptomic data and digital pathology for NRG-based prediction of prognosis and therapy response in gastric cancer. Ann Med. 2024;56(1):2426758.","journal-title":"Ann Med"},{"issue":"40","key":"7416_CR29","doi-asserted-by":"publisher","first-page":"e30927","DOI":"10.1097\/MD.0000000000030927","volume":"101","author":"G Zhang","year":"2022","unstructured":"Zhang G, et al. Prognosis and tumor immune microenvironment of patients with gastric cancer by a novel senescence-related signature. Medicine. 2022;101(40):e30927.","journal-title":"Medicine"},{"key":"7416_CR30","doi-asserted-by":"crossref","unstructured":"Huang B, et al. Accurate diagnosis and prognosis prediction of gastric cancer using deep learning on digital pathological images: a retrospective multicentre study. EBioMedicine. 2021;73.","DOI":"10.1016\/j.ebiom.2021.103631"},{"issue":"6","key":"7416_CR31","first-page":"e70004","volume":"10","author":"JH Park","year":"2024","unstructured":"Park JH, et al. Deep learning-based analysis of EGFR mutation prevalence in lung adenocarcinoma H&E whole slide images. J Pathology: Clin Res. 2024;10(6):e70004.","journal-title":"J Pathology: Clin Res"},{"issue":"3","key":"7416_CR32","doi-asserted-by":"publisher","first-page":"752","DOI":"10.3390\/cancers15030752","volume":"15","author":"W Ren","year":"2023","unstructured":"Ren W, et al. Deep learning-based classification and targeted gene alteration prediction from pleural effusion cell block whole-slide images. Cancers. 2023;15(3):752.","journal-title":"Cancers"},{"issue":"1","key":"7416_CR33","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1038\/s41523-023-00577-4","volume":"9","author":"S Choi","year":"2023","unstructured":"Choi S, et al. Deep learning model improves tumor-infiltrating lymphocyte evaluation and therapeutic response prediction in breast cancer. NPJ Breast Cancer. 2023;9(1):71.","journal-title":"NPJ Breast Cancer"},{"issue":"2","key":"7416_CR34","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.gassur.2023.12.002","volume":"28","author":"MA Pereira","year":"2024","unstructured":"Pereira MA, et al. Prognostic implications of tumor-infiltrating lymphocytes within the tumor microenvironment in gastric cancer. J Gastrointest Surg. 2024;28(2):151\u20137.","journal-title":"J Gastrointest Surg"},{"key":"7416_CR35","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.ejca.2018.03.026","volume":"96","author":"KKH Goey","year":"2018","unstructured":"Goey KKH, et al. Reporting of patient characteristics and stratification factors in phase 3 trials investigating first-line systemic treatment of metastatic colorectal cancer: A systematic review. Eur J Cancer. 2018;96:115\u201324.","journal-title":"Eur J Cancer"}],"container-title":["Journal of Translational Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12967-025-07416-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12967-025-07416-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12967-025-07416-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:43:11Z","timestamp":1781624591000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12967-025-07416-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,24]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["7416"],"URL":"https:\/\/doi.org\/10.1186\/s12967-025-07416-z","relation":{},"ISSN":["1479-5876"],"issn-type":[{"value":"1479-5876","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,24]]},"assertion":[{"value":"9 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Written informed consent was obtained from all participants, and all procedures were conducted in compliance with applicable guidelines and regulations.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no conflicts of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"1419"}}