Skip to main content

Advertisement

SpringerLink
Log in

Machine learning for MRI radiomics: a study predicting tumor-infiltrating lymphocytes in patients with pancreatic ductal adenocarcinoma

  • Pancreas
  • Published:
Abdominal Radiology Aims and scope Submit manuscript

Abstract

Objective

To develop and validate a machine learning classifier based on magnetic resonance imaging (MRI), for the preoperative prediction of tumor-infiltrating lymphocytes (TILs) in patients with pancreatic ductal adenocarcinoma (PDAC).

Materials and methods

In this retrospective study, 156 patients with PDAC underwent MR scan and surgical resection. The expression of CD4, CD8 and CD20 was detected and quantified using immunohistochemistry, and TILs score was achieved by Cox regression model. All patients were divided into TILs score-low and TILs score-high groups. The least absolute shrinkage and selection operator method and the extreme gradient boosting (XGBoost) were used to select the features and to construct a prediction model. The performance of the models was assessed using the training cohort (116 patients) and the validation cohort (40 patients), and decision curve analysis (DCA) was applied for clinical use.

Results

The XGBoost prediction model showed good discrimination in the training (AUC 0.86; 95% CI 0.79–0.93) and validation sets (AUC 0.79; 95% CI 0.64–0.93). The sensitivity, specificity, and accuracy for the training set were 86.67%, 75.00%, and 0.81, respectively, whereas those for the validation set were 84.21%, 66.67%, and 0.75, respectively. Decision curve analysis indicated the clinical usefulness of the XGBoost classifier.

Conclusion

The model constructed by XGBoost could predict PDAC TILs and may aid clinical decision making for immune therapy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Siegel RL, Miller KD, Jemal A (2019) Cancer statistics, 2019. CA Cancer J Clin 69:7-34. doi:https://doi.org/10.3322/caac.21551

    Article  PubMed  Google Scholar 

  2. Burris HA, 3rd, Moore MJ, Andersen J, et al. (1997) Improvements in survival and clinical benefit with gemcitabine as first-line therapy for patients with advanced pancreas cancer: a randomized trial. J Clin Oncol 15:2403-2413. doi:https://doi.org/10.1200/JCO.1997.15.6.2403

    Article  CAS  PubMed  Google Scholar 

  3. Von Hoff DD, Ervin T, Arena FP, et al. (2013) Increased survival in pancreatic cancer with nab-paclitaxel plus gemcitabine. N Engl J Med 369:1691-1703. doi:https://doi.org/10.1056/NEJMoa1304369

    Article  CAS  Google Scholar 

  4. Conroy T, Desseigne F, Ychou M, et al. (2011) FOLFIRINOX versus gemcitabine for metastatic pancreatic cancer. N Engl J Med 364:1817-1825. doi:https://doi.org/10.1056/NEJMoa1011923

    Article  CAS  PubMed  Google Scholar 

  5. Emens LA, Ascierto PA, Darcy PK, et al. (2017) Cancer immunotherapy: Opportunities and challenges in the rapidly evolving clinical landscape. Eur J Cancer 81:116-129. doi:https://doi.org/10.1016/j.ejca.2017.01.035

    Article  CAS  PubMed  Google Scholar 

  6. Brahmer JR, Tykodi SS, Chow LQ, et al. (2012) Safety and activity of anti-PD-L1 antibody in patients with advanced cancer. N Engl J Med 366:2455-2465. doi:https://doi.org/10.1056/NEJMoa1200694

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Sharma P, Callahan MK, Bono P, et al. (2016) Nivolumab monotherapy in recurrent metastatic urothelial carcinoma (CheckMate 032): a multicentre, open-label, two-stage, multi-arm, phase 1/2 trial. Lancet Oncol 17:1590-1598. doi:https://doi.org/10.1016/S1470-2045(16)30496-X

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  8. Motzer RJ, Escudier B, McDermott DF, et al. (2015) Nivolumab versus Everolimus in Advanced Renal-Cell Carcinoma. N Engl J Med 373:1803-1813. doi:https://doi.org/10.1056/NEJMoa1510665

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  9. Robert C, Long GV, Brady B, et al. (2015) Nivolumab in previously untreated melanoma without BRAF mutation. N Engl J Med 372:320-330. doi:https://doi.org/10.1056/NEJMoa1412082

    Article  CAS  PubMed  Google Scholar 

  10. Borghaei H, Paz-Ares L, Horn L, et al. (2015) Nivolumab versus Docetaxel in Advanced Nonsquamous Non-Small-Cell Lung Cancer. N Engl J Med 373:1627-1639. doi:https://doi.org/10.1056/NEJMoa1507643

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Sunami Y, Kleeff J (2019) Immunotherapy of pancreatic cancer. Prog Mol Biol Transl Sci 164:189-216. doi:https://doi.org/10.1016/bs.pmbts.2019.03.006

    Article  CAS  PubMed  Google Scholar 

  12. Jamieson NB, Mohamed M, Oien KA, et al. (2012) The relationship between tumor inflammatory cell infiltrate and outcome in patients with pancreatic ductal adenocarcinoma. Ann Surg Oncol 19:3581-3590. doi:https://doi.org/10.1245/s10434-012-2370-y

    Article  PubMed  Google Scholar 

  13. Miksch RC, Schoenberg MB, Weniger M, et al. (2019) Prognostic Impact of Tumor-Infiltrating Lymphocytes and Neutrophils on Survival of Patients with Upfront Resection of Pancreatic Cancer. Cancers (Basel) 1110.3390/cancers11010039

    Article  Google Scholar 

  14. Tahkola K, Mecklin JP, Wirta EV, et al. (2018) High immune cell score predicts improved survival in pancreatic cancer. Virchows Arch 472:653-665. doi:https://doi.org/10.1007/s00428-018-2297-1

    Article  CAS  PubMed  Google Scholar 

  15. Lambin P, Rios-Velazquez E, Leijenaar R, et al. (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48:441-446. doi:https://doi.org/10.1016/j.ejca.2011.11.036

    Article  PubMed  PubMed Central  Google Scholar 

  16. Kumar V, Gu Y, Basu S, et al. (2012) Radiomics: the process and the challenges. Magn Reson Imaging 30:1234-1248. doi:https://doi.org/10.1016/j.mri.2012.06.010

    Article  PubMed  PubMed Central  Google Scholar 

  17. Park HJ, Lee SS, Park B, et al. (2019) Radiomics Analysis of Gadoxetic Acid-enhanced MRI for Staging Liver Fibrosis. Radiology 290:380-387. doi:https://doi.org/10.1148/radiol.2018181197

    Article  PubMed  Google Scholar 

  18. Wei W, Liu Z, Rong Y, et al. (2019) A Computed Tomography-Based Radiomic Prognostic Marker of Advanced High-Grade Serous Ovarian Cancer Recurrence: A Multicenter Study. Front Oncol 9:255. doi:https://doi.org/10.3389/fonc.2019.00255

    Article  PubMed  PubMed Central  Google Scholar 

  19. Braman N, Prasanna P, Whitney J, et al. (2019) Association of Peritumoral Radiomics With Tumor Biology and Pathologic Response to Preoperative Targeted Therapy for HER2 (ERBB2)-Positive Breast Cancer. JAMA Netw Open 2:e192561. doi:https://doi.org/10.1001/jamanetworkopen.2019.2561

    Article  PubMed  PubMed Central  Google Scholar 

  20. Sun R, Limkin EJ, Vakalopoulou M, et al. (2018) A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1 immunotherapy: an imaging biomarker, retrospective multicohort study. Lancet Oncol 19:1180-1191. doi:https://doi.org/10.1016/S1470-2045(18)30413-3

    Article  CAS  PubMed  Google Scholar 

  21. Wu J, Li X, Teng X, et al. (2018) Magnetic resonance imaging and molecular features associated with tumor-infiltrating lymphocytes in breast cancer. Breast Cancer Res 20:101. doi:https://doi.org/10.1186/s13058-018-1039-2

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  22. Tang C, Hobbs B, Amer A, et al. (2018) Development of an Immune-Pathology Informed Radiomics Model for Non-Small Cell Lung Cancer. Scientific reports 8:1922. doi:https://doi.org/10.1038/s41598-018-20471-5

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  23. Verbeke FCCS (2013) Pathology of the Pancreas: A Practical Approach

    Google Scholar 

  24. Amin MB, Edge SB, Greene FL, et al. (2017) AJCC Cancer Staging manual, 8 edn. Springer, New York

    Book  Google Scholar 

  25. Watanabe H, Okada M, Kaji Y, et al. (2009) New response evaluation criteria in solid tumours-revised RECIST guideline (version 1.1). Gan To Kagaku Ryoho 36:2495-2501.

    PubMed  Google Scholar 

  26. van Griethuysen JJM, Fedorov A, Parmar C, et al. (2017) Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res 77:e104-e107. doi:https://doi.org/10.1158/0008-5472.CAN-17-0339

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  27. Camp RL, Dolled-Filhart M, Rimm DL (2004) X-tile: a new bio-informatics tool for biomarker assessment and outcome-based cut-point optimization. Clin Cancer Res 10:7252-7259. doi:https://doi.org/10.1158/1078-0432.CCR-04-0713

    Article  CAS  PubMed  Google Scholar 

  28. Fukunaga A, Miyamoto M, Cho Y, et al. (2004) CD8+ tumor-infiltrating lymphocytes together with CD4+ tumor-infiltrating lymphocytes and dendritic cells improve the prognosis of patients with pancreatic adenocarcinoma. Pancreas 28:e26-31. doi:https://doi.org/10.1097/00006676-200401000-00023

    Article  PubMed  Google Scholar 

  29. Ino Y, Yamazaki-Itoh R, Shimada K, et al. (2013) Immune cell infiltration as an indicator of the immune microenvironment of pancreatic cancer. Br J Cancer 108:914-923. doi:https://doi.org/10.1038/bjc.2013.32

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Jiang Y, Wang H, Wu J, et al. (2020) Noninvasive imaging evaluation of tumor immune microenvironment to predict outcomes in gastric cancer. Ann Oncol. https://doi.org/10.1016/j.annonc.2020.03.295

    Article  PubMed  Google Scholar 

  31. Liao H, Zhang Z, Chen J, et al. (2019) Preoperative Radiomic Approach to Evaluate Tumor-Infiltrating CD8(+) T Cells in Hepatocellular Carcinoma Patients Using Contrast-Enhanced Computed Tomography. Ann Surg Oncol 26:4537-4547. doi:https://doi.org/10.1245/s10434-019-07815-9

    Article  PubMed  Google Scholar 

  32. Yoon HJ, Kang J, Park H, et al. (2020) Deciphering the tumor microenvironment through radiomics in non-small cell lung cancer: Correlation with immune profiles. PloS one 15:e0231227. doi:https://doi.org/10.1371/journal.pone.0231227

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  33. Zhang X, Liu S, Zhao X, et al. (2020) Magnetic resonance imaging-based radiomic features for extrapolating infiltration levels of immune cells in lower-grade gliomas. Strahlenther Onkol 196:913-921. doi:https://doi.org/10.1007/s00066-020-01584-1

    Article  PubMed  Google Scholar 

  34. Mazzaschi G, Milanese G, Pagano P, et al. (2020) Integrated CT imaging and tissue immune features disclose a radio-immune signature with high prognostic impact on surgically resected NSCLC. Lung Cancer 144:30-39. doi:https://doi.org/10.1016/j.lungcan.2020.04.006

    Article  PubMed  Google Scholar 

  35. Collins GS, Reitsma JB, Altman DG, et al. (2015) Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BJOG 122:434-443. doi:https://doi.org/10.1111/1471-0528.13244

    Article  CAS  PubMed  Google Scholar 

  36. Vickers AJ, Elkin EB (2006) Decision curve analysis: a novel method for evaluating prediction models. Med Decis Making 26:565-574. doi:https://doi.org/10.1177/0272989X06295361

    Article  Google Scholar 

Download references

Funding

This work was supported in part by the National Science Foundation for Scientists of China (81871352, 82003107), Clinical Research Plan of SHDC (SHDC2020CR4073), 234 Platform Discipline Consolidation Foundation Project (2019YPT001), Shanghai Science and Technology Innovation Action Plan Medical Innovation Research Project (20Y11912500), and Shanghai Committee of Science and Technology (21ZR1478500).

Author information

Authors and Affiliations

  1. Department of Radiology, Changhai Hospital, Navy Medical University, Shanghai, 200434, China

    Yun Bian, Yinghao Meng, Fang Liu, Kai Cao, Hao Zhang, Xu Fang, Jing Li, Jieyu Yu, Xiaochen Feng, Qi Li, Li Wang, Jianping Lu & Chengwei Shao

  2. Department of Pathology, Changhai Hospital, Navy Medical University, Shanghai, China

    Yan Fang Liu & Hui Jiang

  3. Department of Radiology, Changhai Hospital, 168 Changhai Road, Shanghai, 200433, China

    Chengwei Shao

Authors
  1. Yun Bian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yan Fang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hui Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yinghao Meng
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Fang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kai Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Hao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Xu Fang
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Jing Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Jieyu Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Xiaochen Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Qi Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Li Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Jianping Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Chengwei Shao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chengwei Shao.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bian, Y., Liu, Y.F., Jiang, H. et al. Machine learning for MRI radiomics: a study predicting tumor-infiltrating lymphocytes in patients with pancreatic ductal adenocarcinoma. Abdom Radiol 46, 4800–4816 (2021). https://doi.org/10.1007/s00261-021-03159-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00261-021-03159-9

Keywords

Search

Navigation