Skip to main content

Advertisement

SpringerLink
Log in

Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer-augmented diagnostics for radiologists

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

Abstract

Purpose

A wide array of benign and malignant lesions of the pancreas can be cystic and these cystic lesions can have overlapping imaging appearances. The purpose of this study is to compare the diagnostic accuracy of a radiomics-based pancreatic cyst classifier to an experienced academic radiologist.

Methods

In this IRB-approved retrospective single-institution study, patients with surgically resected pancreatic cysts who underwent preoperative abdominal CT from 2003 to 2016 were identified. Pancreatic cyst(s) and background pancreas were manually segmented, and 488 radiomics features were extracted. Random forest classification based on radiomics features, age, and gender was evaluated with fourfold cross-validation. An academic radiologist blinded to the final pathologic diagnosis reviewed each case and provided the most likely diagnosis.

Results

214 patients were included (64 intraductal papillary mucinous neoplasms, 33 mucinous cystic neoplasms, 60 serous cystadenomas, 24 solid pseudopapillary neoplasms, and 33 cystic neuroendocrine tumors). The radiomics-based machine learning approach showed AUC of 0.940 in pancreatic cyst classification, compared with AUC of 0.895 for the radiologist.

Conclusion

Radiomics-based machine learning achieved equivalent performance as an experienced academic radiologist in the classification of pancreatic cysts. The high diagnostic accuracy can potentially maximize the efficiency of healthcare utilization by maximizing detection of high-risk lesions.

Graphical abstract

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. Laffan, T.A., et al., Prevalence of unsuspected pancreatic cysts on MDCT. AJR Am J Roentgenol, 2008. 191(3): p. 802-7.

    Article  PubMed  PubMed Central  Google Scholar 

  2. Zanini, N., et al., Estimation of the prevalence of asymptomatic pancreatic cysts in the population of San Marino. Pancreatology, 2015. 15(4): p. 417-22.

    Article  PubMed  Google Scholar 

  3. Zerboni, G., et al., Systematic review and meta-analysis: Prevalence of incidentally detected pancreatic cystic lesions in asymptomatic individuals. Pancreatology, 2019. 19(1): p. 2-9.

    Article  PubMed  Google Scholar 

  4. Scheiman, J.M., J.H. Hwang, and P. Moayyedi, American gastroenterological association technical review on the diagnosis and management of asymptomatic neoplastic pancreatic cysts. Gastroenterology, 2015. 148(4): p. 824–48 e22.

  5. Elta, G.H., et al., ACG Clinical Guideline: Diagnosis and Management of Pancreatic Cysts. Am J Gastroenterol, 2018. 113(4): p. 464-479.

    Article  PubMed  Google Scholar 

  6. Valsangkar, N.P., et al., 851 resected cystic tumors of the pancreas: a 33-year experience at the Massachusetts General Hospital. Surgery, 2012. 152(3 Suppl 1): p. S4-12.

    Article  PubMed  Google Scholar 

  7. Springer, S., et al., A multimodality test to guide the management of patients with a pancreatic cyst. Sci Transl Med, 2019. 11(501): p. eaav4772.

  8. Javed, A.A., et al., Pancreatic Fistula and Delayed Gastric Emptying After Pancreatectomy: Where do We Stand? Indian J Surg, 2015. 77(5): p. 409-25.

    Article  PubMed  PubMed Central  Google Scholar 

  9. Megibow, A.J., et al., Management of Incidental Pancreatic Cysts: A White Paper of the ACR Incidental Findings Committee. J Am Coll Radiol, 2017. 14(7): p. 911-923.

    Article  PubMed  Google Scholar 

  10. Aerts, H.J., et al., Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun, 2014. 5: p. 4006.

    Article  CAS  PubMed  Google Scholar 

  11. Gillies, R.J., P.E. Kinahan, and H. Hricak, Radiomics: Images Are More than Pictures, They Are Data. Radiology, 2016. 278(2): p. 563-77.

    PubMed  Google Scholar 

  12. Hanania, A.N., et al., Quantitative imaging to evaluate malignant potential of IPMNs. Oncotarget, 2016. 7(52): p. 85776-85784.

    Article  PubMed  PubMed Central  Google Scholar 

  13. Permuth, J.B., et al., Combining radiomic features with a miRNA classifier may improve prediction of malignant pathology for pancreatic intraductal papillary mucinous neoplasms. Oncotarget, 2016. 7(52): p. 85785-85797.

    Article  PubMed  PubMed Central  Google Scholar 

  14. Attiyeh, M.A., et al., Preoperative risk prediction for intraductal papillary mucinous neoplasms by quantitative CT image analysis. HPB (Oxford), 2019. 21(2): p. 212-218.

    Article  Google Scholar 

  15. Chakraborty, J., et al., CT radiomics to predict high-risk intraductal papillary mucinous neoplasms of the pancreas. Med Phys, 2018. 45(11): p. 5019-5029.

    Article  PubMed  Google Scholar 

  16. Polk, S.L., et al., Multiphase computed tomography radiomics of pancreatic intraductal papillary mucinous neoplasms to predict malignancy. World J Gastroenterol, 2020. 26(24): p. 3458-3471.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Jeon, S.K., et al., Assessment of malignant potential in intraductal papillary mucinous neoplasms of the pancreas using MR findings and texture analysis. Eur Radiol, 2021. 31(5): p. 3394-3404.

    Article  PubMed  Google Scholar 

  18. Tobaly, D., et al., CT-Based Radiomics Analysis to Predict Malignancy in Patients with Intraductal Papillary Mucinous Neoplasm (IPMN) of the Pancreas. Cancers (Basel), 2020. 12(11).

  19. Yang, J., et al., Discrimination of Pancreatic Serous Cystadenomas From Mucinous Cystadenomas With CT Textural Features: Based on Machine Learning. Front Oncol, 2019. 9: p. 494.

    Article  PubMed  PubMed Central  Google Scholar 

  20. Wei, R., et al., Computer-Aided Diagnosis of Pancreas Serous Cystic Neoplasms: A Radiomics Method on Preoperative MDCT Images. Technol Cancer Res Treat, 2019. 18: p. 1533033818824339.

    Article  PubMed  PubMed Central  Google Scholar 

  21. Xie, H., et al., Preoperative differentiation of pancreatic mucinous cystic neoplasm from macrocystic serous cystic adenoma using radiomics: Preliminary findings and comparison with radiological model. Eur J Radiol, 2020. 122: p. 108747.

    Article  PubMed  Google Scholar 

  22. Chen, S., et al., Preoperative differentiation of serous cystic neoplasms from mucin-producing pancreatic cystic neoplasms using a CT-based radiomics nomogram. Abdom Radiol (NY), 2021.

  23. Yang, R., et al., CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network. Abdom Radiol (NY), 2022. 47(1): p. 232-241.

    Article  Google Scholar 

  24. Awe, A.M., et al., Machine learning principles applied to CT radiomics to predict mucinous pancreatic cysts. Abdom Radiol (NY), 2022. 47(1): p. 221-231.

    Article  Google Scholar 

  25. Dmitriev, K., et al., Classification of Pancreatic Cysts in Computed Tomography Images Using a Random Forest and Convolutional Neural Network Ensemble. Med Image Comput Comput Assist Interv, 2017. 10435: p. 150-158.

    PubMed  PubMed Central  Google Scholar 

  26. Shen, X., et al., A Contrast-Enhanced Computed Tomography Based Radiomics Approach for Preoperative Differentiation of Pancreatic Cystic Neoplasm Subtypes: A Feasibility Study. Front Oncol, 2020. 10: p. 248.

    Article  PubMed  PubMed Central  Google Scholar 

  27. Park, S., et al., Annotated normal CT data of the abdomen for deep learning: Challenges and strategies for implementation. Diagn Interv Imaging, 2020. 101(1): p. 35-44.

    Article  CAS  PubMed  Google Scholar 

  28. Chu, L.C., et al., Utility of CT Radiomics Features in Differentiation of Pancreatic Ductal Adenocarcinoma From Normal Pancreatic Tissue. AJR Am J Roentgenol, 2019. 213(2): p. 349-357.

    Article  PubMed  Google Scholar 

  29. Peng, H., F. Long, and C. Ding, Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell, 2005. 27(8): p. 1226-38.

    Article  PubMed  Google Scholar 

Download references

Funding

This research was supported by the Lustgarten Foundation.

Author information

Authors and Affiliations

  1. Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, MD, USA

    Linda C. Chu, Seyoun Park, Sahar Soleimani, Daniel F. Fouladi, Shahab Shayesteh, Elliot K. Fishman & Satomi Kawamoto

  2. Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA

    Jin He

  3. Department of Surgery, New York University Grossman School of Medicine, New York, NY, USA

    Ammar A. Javed & Christopher L. Wolfgang

  4. Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins University School of Medicine, Baltimore, MD, USA

    Bert Vogelstein & Kenneth W. Kinzler

  5. Department of Pathology, Sol Goldman Pancreatic Cancer Research Center, Johns Hopkins University School of Medicine, Baltimore, MD, USA

    Ralph H. Hruban

  6. Division of Gastroenterology and Hepatology, Johns Hopkins University School of Medicine, Baltimore, MD, USA

    Elham Afghani & Anne Marie Lennon

Authors
  1. Linda C. Chu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Seyoun Park
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sahar Soleimani
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Daniel F. Fouladi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shahab Shayesteh
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jin He
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ammar A. Javed
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Christopher L. Wolfgang
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Bert Vogelstein
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Kenneth W. Kinzler
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Ralph H. Hruban
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Elham Afghani
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Anne Marie Lennon
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Elliot K. Fishman
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Satomi Kawamoto
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. Material preparation, data collection, and analysis were performed by LC, SP, SS, DF, SS, and SK. The first draft of the manuscript was written by SP and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Linda C. Chu.

Ethics declarations

Conflict of interest

The authors declare no conflicts of interest.

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor 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

Chu, L.C., Park, S., Soleimani, S. et al. Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer-augmented diagnostics for radiologists. Abdom Radiol 47, 4139–4150 (2022). https://doi.org/10.1007/s00261-022-03663-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00261-022-03663-6

Keywords

Search

Navigation