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 pathology signature could reveal lymph node status and act as a novel prognostic marker across multiple cancer types

British Journal of Cancer volume 129, pages 46–53 (2023)Cite this article

Subjects

Abstract

Background

Identifying lymph node metastasis (LNM) relies mainly on indirect radiology. Current studies omitted the quantified associations with traits beyond cancer types, failing to provide generalisation performance across various tumour types.

Methods

4400 whole slide images across 11 cancer types were collected for training, cross-verification, and external validation of the pan-cancer lymph node metastasis (PC-LNM) model. We proposed an attention-based weakly supervised neural network based on self-supervised cancer-invariant features for the prediction task.

Results

PC-LNM achieved a test area under the curve (AUC) of 0.732 (95% confidence interval: 0.717–0.746, P < 0.0001) in fivefold cross-validation of multiple cancer types, which also demonstrated good generalisation in the external validation cohort with AUC of 0.699 (95% confidence interval: 0.658–0.737, P < 0.0001). The interpretability results derived from PC-LNM revealed that the regions with the highest attention scores identified by the model generally correspond to tumours with poorly differentiated morphologies. PC-LNM achieved superior performance over previously reported methods and could also act as an independent prognostic factor for patients across multiple tumour types.

Discussion

We presented an automated pan-cancer model for predicting the LNM status from primary tumour histology, which could act as a novel prognostic marker across multiple cancer types.

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

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

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

Fig. 1: The analysis pipeline and the neural network architecture of this study.
Fig. 2: The overall performance of the PC-LNM.
Fig. 3: Interpretability of the deep learning-based pathological model.
Fig. 4: Prognosis prediction through the PC-LNM.

Similar content being viewed by others

Data availability

Data supporting the findings of this study are available within the supplementary information and are also available from the authors upon reasonable request.

References

  1. Siegel RL, Miller KD, Fuchs HE, Jemal A. Cancer statistics, 2022. CA Cancer J Clin. 2022;72:7–33.

    Article  PubMed  Google Scholar 

  2. Kawada K, Taketo MM. Significance and mechanism of lymph node metastasis in cancer progression. Cancer Res. 2011;71:1214–8.

    Article  CAS  PubMed  Google Scholar 

  3. Giuliano AE, Hunt KK, Ballman KV, Beitsch PD, Whitworth PW, et al. Axillary dissection vs no axillary dissection in women with invasive breast cancer and sentinel node metastasis: a randomized clinical trial. J Am Med Assoc. 2011;305:569–75.

    Article  CAS  Google Scholar 

  4. Holten-Rossing H, Talman MM, Jylling AMB, Laenkholm AV, Kristensson M, Vainer B. Application of automated image analysis reduces the workload of manual screening of sentinel lymph node biopsies in breast cancer. Histopathology. 2017;71:866–73.

    Article  PubMed  Google Scholar 

  5. Fujimoto N, He Y, D’Addio M, Tacconi C, Detmar M, Dieterich LC. Single-cell mapping reveals new markers and functions of lymphatic endothelial cells in lymph nodes. PLoS Biol. 2020;18:e3000704.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Núñez NG, Tosello Boari J, Ramos RN, Richer W, Cagnard N, Anderfuhren CD, et al. Tumor invasion in draining lymph nodes is associated with Treg accumulation in breast cancer patients. Nat Commun. 2020;11:3272.

    Article  PubMed  PubMed Central  Google Scholar 

  7. Nishiwada S, Sho M, Banwait JK, Yamamura K, Akahori T, Nakamura K, et al. A microRNA signature identifies pancreatic ductal adenocarcinoma patients at risk for lymph node metastases. Gastroenterology. 2020;159:562–74.

    Article  CAS  PubMed  Google Scholar 

  8. Barisoni L, Lafata KJ, Hewitt SM, Madabhushi A, Balis UGJ. Digital pathology and computational image analysis in nephropathology. Nat Rev Nephrol. 2020;16:669–85.

    Article  PubMed  PubMed Central  Google Scholar 

  9. Yu F, Jung AW, Torne RV, Gonzalez S, Vhringer H, Shmatko A, et al. Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis. Nat Cancer. 2020;1:800–10.

    Article  Google Scholar 

  10. Wang X, Fang Y, Yang S, Zhu D, Wang M, Zhang J, et al. A hybrid network for automatic hepatocellular carcinoma segmentation in H&E-stained whole slide images. Med Image Anal. 2021;68:101914.

    Article  PubMed  Google Scholar 

  11. 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 

  12. Coudray N, Ocampo PS, Sakellaropoulos T, Narula N, Snuderl M, Fenyö D, et al. Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat Med. 2018;24:1559–67.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Yamashita R, Long J, Longacre T, Peng L, Berry G, Martin B, et al. Deep learning model for the prediction of microsatellite instability in colorectal cancer: a diagnostic study. Lancet Oncol. 2021;22:132–41.

    Article  PubMed  Google Scholar 

  14. Lu MY, Chen TY, Williamson DFK, Zhao M, Shady M, Lipkova J, et al. AI-based pathology predicts origins for cancers of unknown primary. Nature. 2021;594:106–10.

    Article  CAS  PubMed  Google Scholar 

  15. Hu Y, Su F, Dong K, Wang X, Zhao X, Jiang Y, et al. Deep learning system for lymph node quantification and metastatic cancer identification from whole-slide pathology images. Gastric Cancer. 2021;24:868–77.

    Article  PubMed  Google Scholar 

  16. Pham HHN, Futakuchi M, Bychkov A, Furukawa T, Kuroda K, Fukuoka J. Detection of lung cancer lymph node metastases from whole-slide histopathologic images using a two-step deep learning approach. Am J Pathol. 2019;189:2428–39.

    Article  CAS  PubMed  Google Scholar 

  17. Ehteshami Bejnordi B, Veta M, Johannes van Diest P, van Ginneken B, Karssemeijer N, Litjens G, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. J Am Med Assoc. 2017;318:2199–210.

    Article  Google Scholar 

  18. Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, et al. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imaging. 2013;26:1045–57.

    Article  PubMed  PubMed Central  Google Scholar 

  19. Weinstein JN, Collisson EA, Mills GB, Shaw KR, Ozenberger BA, Ellrott K, et al. The Cancer Genome Atlas Pan-Cancer analysis project. Nat Genet. 2013;45:1113–20.

    Article  PubMed  PubMed Central  Google Scholar 

  20. Huang KL, Mashl RJ, Wu Y, Ritter DI, Wang J, Oh C, et al. Pathogenic germline variants in 10,389 adult cancers. Cell. 2018;173:355–70.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  21. Ciga O, Xu T, Martel AL. Self supervised contrastive learning for digital histopathology. Mach Learn Appl. 2022;100198:1–14.

    Google Scholar 

  22. Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et al. Swin transformer: hierarchical vision transformer using shifted windows. arXiv [Preprint] 2021. Available from: https://doi.org/10.48550/arXiv.2103.14030.

  23. Wang X, Yang S, Zhang J, Wang M, Zhang J, Yang W, et al. Transformer-based unsupervised contrastive learning for histopathological image classification. Med Image Anal. 2022;81:102559.

    Article  PubMed  Google Scholar 

  24. DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44:837–45.

    Article  CAS  PubMed  Google Scholar 

  25. Shao Z, Bian H, Chen Y, Wang Y, Zhang J, Ji X, et al. TransMIL: transformer based correlated multiple instance learning for whole slide image classification. arXiv [Preprint] 2021. Available from: https://doi.org/10.48550/arXiv.2106.00908.

  26. Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2018;68:394–424.

    Article  PubMed  Google Scholar 

  27. Lykke J, Roikjaer O, Jess P, Rosenberg J. Identification of risk factors associated with stage III disease in nonmetastatic colon cancer: results from a Prospective National Cohort Study. Ann Coloproctol. 2020;36:316–22.

    Article  PubMed  PubMed Central  Google Scholar 

  28. Hanna AN, Sinnamon AJ, Roses RE, Kelz RR, Elder DE, Xu X, et al. Relationship between age and likelihood of lymph node metastases in patients with intermediate thickness melanoma (1.01-4.00 mm): a National Cancer Database study. J Am Acad Dermatol. 2019;80:433–40.

    Article  PubMed  Google Scholar 

  29. Glimelius B, Tiret E, Cervantes A, Arnold D. Rectal cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. Ann Oncol. 2013;24:vi81–8.

    Article  PubMed  Google Scholar 

  30. Senkus E, Kyriakides S, Ohno S, Penault-Llorca F, Poortmans P, Rutgers E, et al. Primary breast cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. Ann Oncol. 2015;26:v8–30.

    Article  PubMed  Google Scholar 

  31. Brinker TJ, Kiehl L, Schmitt M, Jutzi TB, Krieghoff-Henning EI, Krahl D, et al. Deep learning approach to predict sentinel lymph node status directly from routine histology of primary melanoma tumours. Eur J Cancer. 2021;154:227–34.

    Article  PubMed  Google Scholar 

  32. 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 

  33. Kwak MS, Lee HH, Yang JM, Cha JM, Jeon JW, Yoon JY, et al. Deep convolutional neural network-based lymph node metastasis prediction for colon cancer using histopathological images. Front Oncol. 2020;10:619803.

    Article  PubMed  Google Scholar 

  34. Zhao Y, Yang F, Fang Y, Liu H, Zhou N, Zhang J, et al. Predicting lymph node metastasis using histopathological images based on multiple instance learning with deep graph convolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. p. 4837–46.

  35. Wang L, Jiao Y, Qiao Y, Zeng N, Yu R. A novel approach combined transfer learning and deep learning to predict TMB from histology image. Pattern Recognit Lett. 2020;135:244–8.

    Article  Google Scholar 

Download references

Acknowledgements

We appreciate the technical support for the professional pathology assessments in the comparison analysis from the department of Pathology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine. Partial data used in this publication were retrieved from the National Cancer Institute Clinical Proteomic Tumour Analysis Consortium, the Cancer Genome Atlas, and the Cancer Imaging Archive used in this study.

Funding

This work was supported by the National Natural Science Foundation of China (81972393). The funding sources had no role in the design of the study; collection, analysis or interpretation of the data; writing of the report; the decision to submit for publication.

Author information

Author notes

  1. These authors contributed equally: Siteng Chen, Jinxi Xiang, Xiyue Wang.

Authors and Affiliations

  1. Department of Urology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, 200135, Shanghai, China

    Siteng Chen & Junhua Zheng

  2. Tencent AI Lab, 518057, Shenzhen, China

    Jinxi Xiang, Jun Zhang, Sen Yang, Wei Yang & Xiao Han

  3. College of Computer Science, Sichuan University, 610065, Chengdu, China

    Xiyue Wang

Authors
  1. Siteng Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jinxi Xiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiyue Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jun Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Sen Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Wei Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Junhua Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Xiao Han
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

JHZ, XH and JZ participated in the study conception and design, reviewed the paper and approved the final draft for submission. SC, JX and XW participated in the data collection, data analysis, wrote and approved the final draft for submission. SY and WY participated in data collection, reviewed the paper and approved the final draft for submission.

Corresponding authors

Correspondence to Jun Zhang, Junhua Zheng or Xiao Han.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval and consent to participate

No further ethical approval was required since all the slice images from the CPTAC cohort and the TCGA cohort were publicly available for research purposes.

Consent for publication

Not applicable.

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

Chen, S., Xiang, J., Wang, X. 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 129, 46–53 (2023). https://doi.org/10.1038/s41416-023-02262-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41416-023-02262-6

This article is cited by

Search

Advanced search

Quick links