Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Clinical Studies

Deep learning-based prediction of lymph node metastasis and occult tumor cells in gastric cancer using histopathological images: a retrospective study

British Journal of Cancer (2026) Cite this article

Subjects

Abstract

Background

Lymph node metastasis (LNM) is an important prognostic factor but is often underdiagnosed due to limitations in conventional assessment methods. We aimed to develop a deep learning (DL) model to predict LNM status from primary gastric cancer (GC) whole-slide images.

Methods

This retrospective study included 929 patients with GC from three independent cohorts across two centers. A DL model based on Clustering-constrained Attention Multiple Instance Learning was trained and validated to predict LNM from whole-slide images of primary tumors. The ability of the model to predict occult tumor cells (OTCs) in patients initially staged as pN0 and its prognostic value in patients with GC were examined.

Results

The model demonstrated robust LNM predictive performance. Notably, it also predicted OTCs in patients initially staged as pN0. Patients staged as pN0 with OTCs had significantly worse survival outcomes than those staged as pN0 without OTCs (P = 0.003). The score generated by the model was an independent prognostic factor for patients with GC.

Conclusions

Our DL-based model enables accurate prediction of LNM and OTCs from primary GC slides, serving as a valuable tool for guiding personalized clinical strategies and as a novel biomarker for prognostic evaluation in patients with GC.

The alternative text for this image may have been generated using AI.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Predictive performance of the model.
The alternative text for this image may have been generated using AI.
Fig. 2: Model performance in predicting OTCs and lymph node metastasis.
The alternative text for this image may have been generated using AI.
Fig. 3: Prognostic ability of the model.
The alternative text for this image may have been generated using AI.
Fig. 4: Prognostic ability of OTCs in patients staged as pN0.
The alternative text for this image may have been generated using AI.
Fig. 5: Model attention visualization.
The alternative text for this image may have been generated using AI.

Similar content being viewed by others

Data availability

The datasets used in this study are available from the corresponding author upon request. Code availability: All the codes associated with this method were implemented in Python. The source code for preprocessing and feature extraction is available at https://lunit-io.github.io/research/publications/pathology_ssl/. The source code used for training and evaluating the DL models is available at https://github.com/mahmoodlab/CLAM.

References

  1. Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global Cancer Statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2021;71:209–49.

    PubMed  Google Scholar 

  2. Siegel RL, Miller KD, Wagle NS, Jemal A. Cancer statistics, 2023. CA Cancer J Clin. 2023;73:17–48.

    PubMed  Google Scholar 

  3. Ajani JA, D’Amico TA, Bentrem DJ, Chao J, Cooke D, Corvera C, et al. Gastric cancer, Version 2.2022, NCCN Clinical Practice Guidelines in Oncology. J Natl Compr Canc Netw. 2022;20:167–92.

    Article  CAS  PubMed  Google Scholar 

  4. Shi RL, Chen Q, Ding JB, Yang Z, Pan G, Jiang D, et al. Increased number of negative lymph nodes is associated with improved survival outcome in node positive gastric cancer following radical gastrectomy. Oncotarget. 2016;7:35084–91.

    Article  PubMed  PubMed Central  Google Scholar 

  5. Sano T, Coit DG, Kim HH, Roviello F, Kassab P, Wittekind C, et al. Proposal of a new stage grouping of gastric cancer for TNM classification: International Gastric Cancer Association staging project. Gastric Cancer. 2017;20:217–25.

    Article  PubMed  Google Scholar 

  6. de Burlet KJ, van den Hout MFCM, Putter H, Smit VTHBM, Hartgrink HH. Total number of lymph nodes in oncologic resections, is there more to be found? J Gastrointest Surg. 2015;19:943–8.

    Article  PubMed  PubMed Central  Google Scholar 

  7. Seeruttun SR, Xu L, Wang F, Yi X, Fang C, Liu Z, et al. A homogenized approach to classify advanced gastric cancer patients with limited and adequate number of pathologically examined lymph nodes. Cancer Commun (Lond). 2019;39:32.

    Article  PubMed  PubMed Central  Google Scholar 

  8. Arigami T, Uenosono Y, Yanagita S, Nakajo A, Ishigami S, Okumura H, et al. Clinical significance of lymph node micrometastasis in gastric cancer. Ann Surg Oncol. 2013;20:515–21.

    Article  PubMed  Google Scholar 

  9. Lee CM, Cho JM, Jang YJ, Park SS, Park SH, Kim SJ, et al. Should lymph node micrometastasis be considered in node staging for gastric cancer? the significance of lymph node micrometastasis in gastric cancer. Ann Surg Oncol. 2015;22:765–71.

    Article  PubMed  Google Scholar 

  10. Sekiguchi M, Oda I, Taniguchi H, Suzuki H, Morita S, Fukagawa T, et al. Risk stratification and predictive risk-scoring model for lymph node metastasis in early gastric cancer. J Gastroenterol. 2016;51:961–70.

    Article  CAS  PubMed  Google Scholar 

  11. Li Y, Wang D, Li Y, Liu X, Chen D, Yuan C, et al. Clinical significance of lymph node micrometastasis in pN0 gastric cancer patients. Gastroenterol Res Pract. 2021;2021:6854646.

    Article  PubMed  PubMed Central  Google Scholar 

  12. Wang X, Yang X, Cai F, Cai M, Liu Y, Zhang L, et al. The key role of tumor budding in predicting the status of lymph node involvement in early gastric cancer patients: a clinical multicenter validation in China. Ann Surg Oncol. 2024;31:4224–35.

    Article  PubMed  Google Scholar 

  13. Kim JY, Kim CH, Lee Y, Lee JH, Chae YS. Tumour infiltrating lymphocytes are predictors of lymph node metastasis in early gastric cancers. Pathology. 2017;49:589–95.

    Article  CAS  PubMed  Google Scholar 

  14. Chen D, Chen G, Jiang W, Fu M, Liu W, Sui J, et al. Association of the collagen signature in the tumor microenvironment with lymph node metastasis in early gastric cancer. JAMA Surg. 2019;154:e185249.

    Article  PubMed  PubMed Central  Google Scholar 

  15. Kather JN, Pearson AT, Halama N, Jäger D, Krause J, Loosen SH, et al. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat Med. 2019;25:1054–6.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Huang B, Tian S, Zhan N, Ma J, Huang Z, Zhang C, et al. Accurate diagnosis and prognosis prediction of gastric cancer using deep learning on digital pathological images: a retrospective multicentre study. EBiomedicine. 2021;73:103631.

    Article  PubMed  PubMed Central  Google Scholar 

  17. Zheng X, Wang R, Zhang X, Sun Y, Zhang H, Zhao Z, et al. A deep learning model and human-machine fusion for prediction of EBV-associated gastric cancer from histopathology. Nat Commun. 2022;13:2790.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. Flinner N, Gretser S, Quaas A, Bankov K, Stoll A, Heckmann LE, et al. Deep learning based on hematoxylin-eosin staining outperforms immunohistochemistry in predicting molecular subtypes of gastric adenocarcinoma. J Pathol. 2022;257:218–26.

    Article  CAS  PubMed  Google Scholar 

  19. Wei Z, Zhao X, Chen J, Sun Q, Wang Z, Wang Y, et al. Deep learning-based stratification of gastric cancer patients from hematoxylin and eosin-stained whole slide images by predicting molecular features for immunotherapy response. Am J Pathol. 2023;193:1517–27.

    Article  PubMed  Google Scholar 

  20. Brockmoeller S, Echle A, Ghaffari Laleh N, Eiholm S, Malmstrøm ML, Plato Kuhlmann T, et al. Deep learning identifies inflamed fat as a risk factor for lymph node metastasis in early colorectal cancer. J Pathol. 2022;256:269–81.

    Article  CAS  PubMed  Google Scholar 

  21. Krogue JD, Azizi S, Tan F, Flament-Auvigne I, Brown T, Plass M, et al. Predicting lymph node metastasis from primary tumor histology and clinicopathologic factors in colorectal cancer using deep learning. Commun Med (Lond). 2023;3:59.

    Article  PubMed  PubMed Central  Google Scholar 

  22. Zheng Q, Jian J, Wang J, Wang K, Fan J, Xu H, et al. Predicting lymph node metastasis status from primary muscle-invasive bladder cancer histology slides using deep learning: a retrospective multicenter study. Cancers (Basel). 2023;15:3000.

    Article  PubMed  PubMed Central  Google Scholar 

  23. Guo Q, Qu L, Zhu J, Li H, Wu Y, Wang S, et al. Predicting lymph node metastasis from primary cervical squamous cell carcinoma based on deep learning in histopathologic images. Mod Pathol. 2023;36:100316.

    Article  CAS  PubMed  Google Scholar 

  24. Chen S, Xiang J, Wang X, Zhang J, Yang S, Yang W, et al. Deep learning-based pathology signature could reveal lymph node status and act as a novel prognostic marker across multiple cancer types. Br J Cancer. 2023;129:46–53.

    Article  PubMed  PubMed Central  Google Scholar 

  25. Gao F, Jiang L, Guo T, Lin J, Xu W, Yuan L, et al. Deep learning-based pathological prediction of lymph node metastasis for patient with renal cell carcinoma from primary whole slide images. J Transl Med. 2024;22:568.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  26. Muti HS, Röcken C, Behrens HM, Löffler CML, Reitsam NG, Grosser B, et al. Deep learning trained on lymph node status predicts outcome from gastric cancer histopathology: a retrospective multicentric study. Eur J Cancer. 2023;194:113335.

    Article  PubMed  Google Scholar 

  27. Guo Z, Lan J, Wang J, Hu Z, Wu Z, Quan J, et al. Prediction of lymph node metastasis in primary gastric cancer from pathological images and clinical data by multimodal multiscale deep learning. Biomed Signal Process Control. 2023;86:105336.

    Article  Google Scholar 

  28. Zeng YJ, Zhang CD, Dai DQ. Impact of lymph node micrometastasis on gastric carcinoma prognosis: a meta-analysis. World J Gastroenterol. 2015;21:1628–35.

    Article  PubMed  PubMed Central  Google Scholar 

  29. Mpallas KD, Lagopoulos VI, Kamparoudis AG. Prognostic significance of solitary lymphnode metastasis and micrometastasis in gastric cancer. Front Surg. 2018;5:63.

    Article  PubMed  PubMed Central  Google Scholar 

  30. Tavares A, Wen X, Maciel J, Carneiro F, Dinis-Ribeiro M. Occult tumour cells in lymph nodes from gastric cancer patients: should isolated tumour cells also be considered?. Ann Surg Oncol. 2020;27:4204–15.

    Article  CAS  PubMed  Google Scholar 

  31. Wang X, Chen Y, Gao Y, Zhang H, Guan Z, Dong Z, et al. Predicting gastric cancer outcome from resected lymph node histopathology images using deep learning. Nat Commun. 2021;12:1637.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  32. Huang SC, Chen CC, Lan J, Hsieh TY, Chuang HC, Chien MY, et al. Deep neural network trained on gigapixel images improves lymph node metastasis detection in clinical settings. Nat Commun. 2022;13:3347.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  33. WHO Classification of Tumours Editorial Board. WHO classification of tumours: digestive system tumours. 5th ed. Lyon: International Agency for Research on Cancer; 2019.

  34. Amin MB, Edge SB, Greene FL (ed.). AJCC Cancer Staging Manual. 8th ed (Springer, New York, 2017).

  35. Jiang Y, Liang X, Han Z, Wang W, Xi S, Li T, et al. Radiographical assessment of tumour stroma and treatment outcomes using deep learning: a retrospective, multicohort study. Lancet Digit Health. 2021;3:e371–82.

    Article  CAS  PubMed  Google Scholar 

  36. Lu MY, Williamson DFK, Chen TY, Chen RJ, Barbieri M, Mahmood F. Data-efficient and weakly supervised computational pathology on whole-slide images. Nat Biomed Eng. 2021;5:555–70.

    Article  PubMed  PubMed Central  Google Scholar 

  37. Kang M, Song H, Park S, Yoo D, Pereira S. Benchmarking self-supervised learning on diverse pathology datasets, (2023). http://arxiv.org/abs/2212.04690.

  38. Agnes A, Biondi A, Cananzi FM, Rausei S, Reddavid R, Laterza V, et al. Ratio-based staging systems are better than the 7th and 8th editions of the TNM in stratifying the prognosis of gastric cancer patients: a multicenter retrospective study. J Surg Oncol. 2019;119:948–57.

    Article  PubMed  Google Scholar 

  39. Wang W, Yang YJ, Zhang RH, Deng JY, Sun Z, Seeruttun SR, et al. Standardizing the classification of gastric cancer patients with limited and adequate number of retrieved lymph nodes: an externally validated approach using real-world data. Mil Med Res. 2022;9:15.

    PubMed  PubMed Central  Google Scholar 

  40. Zhou Y, Zhang GJ, Wang J, Zheng KY, Fu W. Current status of lymph node micrometastasis in gastric cancer. Oncotarget. 2017;8:51963–9.

    Article  PubMed  PubMed Central  Google Scholar 

  41. Nakajo A, Natsugoe S, Ishigami S, Matsumoto M, Nakashima S, Hokita S, et al. Detection and prediction of micrometastasis in the lymph nodes of patients with pN0 gastric cancer. Ann Surg Oncol. 2001;8:158–62.

    Article  CAS  PubMed  Google Scholar 

  42. Fukagawa T, Sasako M, Mann GB, Sano T, Katai H, Maruyama K, et al. Immunohistochemically detected micrometastases of the lymph nodes in patients with gastric carcinoma. Cancer. 2001;92:753–60.

    Article  CAS  PubMed  Google Scholar 

  43. Jeuck TLA, Wittekind C. Gastric carcinoma: stage migration by immunohistochemically detected lymph node micrometastases. Gastric Cancer. 2015;18:100–8.

    Article  CAS  PubMed  Google Scholar 

  44. Tavares A, Monteiro-Soares M, Viveiros F, Maciel Barbosa J, Dinis-Ribeiro M. Occult tumor cells in lymph nodes of patients with gastric cancer: a systematic review on their prevalence and predictive role. Oncology. 2015;89:245–54.

    Article  CAS  PubMed  Google Scholar 

  45. Wei T, Yuan X, Gao R, Johnston L, Zhou J, Wang Y, et al. Survival prediction of stomach cancer using expression data and deep learning models with histopathological images. Cancer Sci. 2023;114:690–701.

    Article  CAS  PubMed  Google Scholar 

  46. Veldhuizen GP, Röcken C, Behrens HM, Cifci D, Muti HS, Yoshikawa T, et al. Deep learning-based subtyping of gastric cancer histology predicts clinical outcome: a multi-institutional retrospective study. Gastric Cancer. 2023;26:708–20.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  47. Zhao K, Li Z, Yao S, Wang Y, Wu X, Xu Z, et al. Artificial intelligence quantified tumour-stroma ratio is an independent predictor for overall survival in resectable colorectal cancer. EBiomedicine. 2020;61:103054.

    Article  PubMed  PubMed Central  Google Scholar 

  48. Bokhorst JM, Ciompi F, Öztürk SK, Oguz Erdogan AS, Vieth M, Dawson H, et al. Fully automated tumor bud assessment in hematoxylin and eosin-stained whole slide images of colorectal cancer. Mod Pathol. 2023;36:100233.

    Article  CAS  PubMed  Google Scholar 

Download references

Funding

This work was supported by grants from the High-level Hospital Construction Project (grant number: YKY-KF202204 to XWB; grant number: DFJHBF202108 to QLZ); Key R&D Program Projects in Guangdong Province (grant number: 2021B0101420005 to QLZ); the National Natural Science Foundation of China (grant number: 82173033 to QLZ; grant number: 82102712 to YWX); China Postdoctoral Science Foundation (grant number: 2021M690751 to YWX); and Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application (grant number: 2022B1212010011 to QLZ).

Author information

Author notes

  1. These authors contributed equally: Hairui She, Tianqi Xiang, Junjiang Wang.

Authors and Affiliations

  1. Department of Pathology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, 106 Zhongshan 2nd Road, Guangzhou, Guangdong, 510080, China

    Hairui She, Zhihao Lin, Weiye Huang, Hongmei Wu, Yangwei Xu, Qian Wang & Qingling Zhang

  2. Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences, 106 Zhongshan 2nd Road, Guangzhou, Guangdong, 510080, China

    Hairui She, Zhihao Lin, Qian Wang & Qingling Zhang

  3. Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong, 999077, China

    Tianqi Xiang & Xiaomeng Li

  4. Department of Gastrointestinal Surgery, Department of General Surgery, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, 106 Zhongshan 2nd Road, Guangzhou, Guangdong, 510080, China

    Junjiang Wang

  5. Department of Pathology, Nanfang Hospital, School of Basic Medical Sciences, Southern Medical University, 1838 Guangzhou Avenue North, Guangzhou, Guangdong, 510515, China

    Xiaoxia Wu, Huihui Chen, Zhijie Chen & Li Liang

  6. Guangdong Province Key Laboratory of Molecular Tumor Pathology, 1838 Guangzhou Avenue North, Guangzhou, Guangdong, 510515, China

    Xiaoxia Wu, Huihui Chen, Zhijie Chen & Li Liang

  7. Institute of Pathology and Southwest Cancer Center, Southwest Hospital, Third Military Medical University (Army Medical University), and Key Laboratory of Tumor Immunopathology, Ministry of Education of China, 30 Gaotanyan Street, Shapingba District, Chongqing, 400038, China

    Xiuwu Bian

Authors
  1. Hairui She
    View author publications

    Search author on:PubMed Google Scholar

  2. Tianqi Xiang
    View author publications

    Search author on:PubMed Google Scholar

  3. Junjiang Wang
    View author publications

    Search author on:PubMed Google Scholar

  4. Zhihao Lin
    View author publications

    Search author on:PubMed Google Scholar

  5. Weiye Huang
    View author publications

    Search author on:PubMed Google Scholar

  6. Hongmei Wu
    View author publications

    Search author on:PubMed Google Scholar

  7. Yangwei Xu
    View author publications

    Search author on:PubMed Google Scholar

  8. Qian Wang
    View author publications

    Search author on:PubMed Google Scholar

  9. Xiaoxia Wu
    View author publications

    Search author on:PubMed Google Scholar

  10. Huihui Chen
    View author publications

    Search author on:PubMed Google Scholar

  11. Zhijie Chen
    View author publications

    Search author on:PubMed Google Scholar

  12. Li Liang
    View author publications

    Search author on:PubMed Google Scholar

  13. Xiuwu Bian
    View author publications

    Search author on:PubMed Google Scholar

  14. Xiaomeng Li
    View author publications

    Search author on:PubMed Google Scholar

  15. Qingling Zhang
    View author publications

    Search author on:PubMed Google Scholar

Contributions

HRS, TQX, JJW, XML, and QLZ conceived and designed the study. HRS, ZHL, WYH, HMW, YWX, QW, XXW, HHC, ZJC, and LL performed the research and collected the data. TQX and XML developed and validated the deep learning models. HRS and TQX wrote the first draft of the manuscript. JJW, LL, XWB, XML, and QLZ reviewed and edited the manuscript. All authors read and approved the final manuscript.

Corresponding authors

Correspondence to Li Liang, Xiuwu Bian, Xiaomeng Li or Qingling Zhang.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval and consent to participate

This study was approved by the Research Ethics Committee of Guangdong Provincial People’s Hospital (approval number: KY-Z-2022-092-01; approval date: 05.20.2022) and the Research Ethics Committee of Nanfang Hospital of Southern Medical University (approval number: NFEC-2025-092; approval date: 03.07.2025). The study was conducted in accordance with the relevant laws and institutional guidelines and the principles outlined in the Declaration of Helsinki. The requirement for informed consent was waived due to the retrospective nature of the study.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

She, H., Xiang, T., Wang, J. et al. Deep learning-based prediction of lymph node metastasis and occult tumor cells in gastric cancer using histopathological images: a retrospective study. Br J Cancer (2026). https://doi.org/10.1038/s41416-026-03400-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Version of record:

  • DOI: https://doi.org/10.1038/s41416-026-03400-6

Search

Advanced search

Quick links