Skip to main content
SpringerLink
Log in

Deep learning radiomics of dual-energy computed tomography for predicting lymph node metastases of pancreatic ductal adenocarcinoma

  • Original Article
  • Published:
European Journal of Nuclear Medicine and Molecular Imaging Aims and scope Submit manuscript

Abstract

Purpose

Diagnosis of lymph node metastasis (LNM) is critical for patients with pancreatic ductal adenocarcinoma (PDAC). We aimed to build deep learning radiomics (DLR) models of dual-energy computed tomography (DECT) to classify LNM status of PDAC and to stratify the overall survival before treatment.

Methods

From August 2016 to October 2020, 148 PDAC patients underwent regional lymph node dissection and scanned preoperatively DECT were enrolled. The virtual monoenergetic image at 40 keV was reconstructed from 100 and 150 keV of DECT. By setting January 1, 2021, as the cut-off date, 113 patients were assigned into the primary set, and 35 were in the test set. DLR models using VMI 40 keV, 100 keV, 150 keV, and 100 + 150 keV images were developed and compared. The best model was integrated with key clinical features selected by multivariate Cox regression analysis to achieve the most accurate prediction.

Results

DLR based on 100 + 150 keV DECT yields the best performance in predicting LNM status with the AUC of 0.87 (95% confidence interval [CI]: 0.85–0.89) in the test cohort. After integrating key clinical features (CT-reported T stage, LN status, glutamyl transpeptadase, and glucose), the AUC was improved to 0.92 (95% CI: 0.91–0.94). Patients at high risk of LNM portended significantly worse overall survival than those at low risk after surgery (P = 0.012).

Conclusions

The DLR model showed outstanding performance for predicting LNM in PADC and hold promise of improving clinical decision-making.

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

Similar content being viewed by others

Code availability

The code of this study is publicly accessible at http://www.radiomics.net.cn/owncloud/index.php/s/7DQTr9qLiFbEJup.

References

  1. Sung H, Ferlay J, Siegel RL, 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(3):209–49. https://doi.org/10.3322/caac.21660.

    Article  PubMed  Google Scholar 

  2. Rahib L, Smith BD, Aizenberg R, Rosenzweig AB, Fleshman JM, Matrisian LM. Projecting cancer incidence and deaths to 2030: the unexpected burden of thyroid, liver, and pancreas cancers in the United States. Cancer Res. 2014;74:2913–21.

    CAS  PubMed  Google Scholar 

  3. Brown ZJ, Cloyd JM. Surgery for pancreatic cancer: recent progress and future directions. Hepatobiliary Surg Nutr. 2021;10:376–8.

    PubMed  PubMed Central  Google Scholar 

  4. Durán H, Olivares S, Ielpo B, et al. Prognostic value of lymph node status for actual long-term survival in resected pancreatic cancer. Surg Technol Int. 2020;37:79–84.

    PubMed  Google Scholar 

  5. Potjer TP. Pancreatic cancer surveillance and its ongoing challenges: is it time to refine our eligibility criteria? Gut. 2021 Jun 18:gutjnl-2021-324739. https://doi.org/10.1136/gutjnl-2021-324739

  6. Perlmutter BC, Hossain MS, Naples R, et al. Survival impact based on hepatic artery lymph node status in pancreatic adenocarcinoma: a study of patients receiving modern chemotherapy. J Surg Oncol. 2021;123:399–406.

    PubMed  Google Scholar 

  7. Takahashi H, Ohigashi H, Ishikawa O, et al. Perineural invasion and lymph node involvement as indicators of surgical outcome and pattern of recurrence in the setting of preoperative gemcitabine-based chemoradiation therapy for resectable pancreatic cancer. Ann Surg. 2012;255:95–102.

    PubMed  Google Scholar 

  8. Masuda T, Dann AM, Elliott IA, et al. A comprehensive assessment of accurate lymph node staging and preoperative detection in resected pancreatic cancer. J Gastrointest Surg. 2018;22:295–302.

    PubMed  Google Scholar 

  9. Kumon RE, Repaka A, Atkinson M, et al. Lymph node characterization in vivo using endoscopic ultrasound spectrum analysis with electronic array echo endoscopes. Endoscopy. 2012;44:618–21.

    CAS  PubMed  PubMed Central  Google Scholar 

  10. Nanashima A, Sakamoto I, Hayashi T, et al. Preoperative diagnosis of lymph node metastasis in biliary and pancreatic carcinomas: evaluation of the combination of multi-detector CT and serum CA19-9 level. Dig Dis Sci. 2010;55:3617–26.

    PubMed  Google Scholar 

  11. Zhang Z, Procissi D, Li W, et al. High resolution MRI for non-invasive mouse lymph node mapping. J Immunol Methods. 2013;400–401:23–9.

    PubMed  Google Scholar 

  12. Wang S, Shi H, Yang F, Teng X, Jiang B. The value of 18F-FDG PET/CT and carbohydrate antigen 19–9 in predicting lymph node micrometastases of pancreatic cancer. Abdom Radiol (NY). 2019;44:4057–62.

    Google Scholar 

  13. Masui T, Sato A, Nakano K, et al. Predictive value of the Ki67 index for lymph node metastasis of small non-functioning pancreatic neuroendocrine neoplasms. Surg Today. 2019;49:593–600.

    PubMed  Google Scholar 

  14. Xiang ZJ, Hu T, Wang Y, Wang H, Xu L, Cui N. Neutrophil-lymphocyte ratio (NLR) was associated with prognosis and immunomodulatory in patients with pancreatic ductal adenocarcinoma (PDAC). Biosci Rep. 2020 Jun 26;40(6):BSR20201190.https://doi.org/10.1042/BSR20201190

  15. Wang SC, Parekh JR, Porembka MR, et al. A pilot study evaluating serum MMP7 as a preoperative prognostic marker for pancreatic ductal adenocarcinoma patients. J Gastrointest Surg. 2016;20:899–904.

    PubMed  PubMed Central  Google Scholar 

  16. Andrianifahanana M, Moniaux N, Schmied BM, et al. Mucin (MUC) gene expression in human pancreatic adenocarcinoma and chronic pancreatitis: a potential role of MUC4 as a tumor marker of diagnostic significance. Clin Cancer Res. 2001;7:4033–40.

    CAS  PubMed  Google Scholar 

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

    CAS  PubMed  Google Scholar 

  18. Dong D, Fang MJ, Tang L, et al. Deep learning radiomic nomogram can predict the number of lymph node metastasis in locally advanced gastric cancer: an international multicenter study. Ann Oncol. 2020;31:912–20.

    CAS  PubMed  Google Scholar 

  19. Huang YQ, Liang CH, He L, et al. Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol. 2016;34:2157–64.

    PubMed  Google Scholar 

  20. Li Q, Fan X, Luo TY, Lv FJ, Huang XT. Differentiating malignant and benign necrotic lung lesions using kVp-switching dual-energy spectral computed tomography. BMC Med Imaging. 2021;21:81.

    PubMed  PubMed Central  Google Scholar 

  21. Wang X, Liu D, Zeng X, et al. Dual-energy CT quantitative parameters for the differentiation of benign from malignant lesions and the prediction of histopathological and molecular subtypes in breast cancer. Quant Imaging Med Surg. 2021;11:1946–57.

    PubMed  PubMed Central  Google Scholar 

  22. Morgan DE. The role of dual-energy computed tomography in assessment of abdominal oncology and beyond. Radiol Clin North Am. 2018;56:565–85.

    PubMed  Google Scholar 

  23. Nair JR, DeBlois F, Ong T, et al. Dual-energy CT: balance between iodine attenuation and artifact reduction for the evaluation of head and neck cancer. J Comput Assist Tomogr. 2017;41:931–6.

    PubMed  Google Scholar 

  24. Kim J-E, Nam N-E, Shim J-S, Jung Y-H, Cho B-H, Hwang JJ. Transfer learning via deep neural networks for implant fixture system classification using periapical radiographs. J Clin Med. 2020;9(4):1117. https://doi.org/10.3390/jcm9041117.

    Article  PubMed Central  Google Scholar 

  25. Russakovsky O, Deng J, Su H, et al. Imagenet large scale visual recognition challenge[J]. International journal of computer vision, 2015, 115(3): 211–52. https://doi.org/10.1007/s11263-015-0816-y

  26. Zhang Z, Mo L, Huang C, Xu P, written on behalf of AME Big-Data Clinical Trial Collaborative Group. Binary logistic regression modeling with TensorFlowTM. Ann Transl Med. 2019;7:591.

    PubMed  PubMed Central  Google Scholar 

  27. Gutiérrez M. Data, data flows, and model specifications for linking multi-level contribution margin accounting with multi-level fixed-charge problems. Data Brief. 2021;35:106931.

    PubMed  PubMed Central  Google Scholar 

  28. Liu Z, Li Z, Qu J, et al. Radiomics of multiparametric MRI for pretreatment prediction of pathologic complete response to neoadjuvant chemotherapy in breast cancer: a multicenter study. Clin Cancer Res. 2019;25:3538–47.

    CAS  PubMed  Google Scholar 

  29. Beer L, Toepker M, Ba-Ssalamah A, et al. Objective and subjective comparison of virtual monoenergetic vs. polychromatic images in patients with pancreatic ductal adenocarcinoma. Eur Radiol. 2019;29:3617–25.

    PubMed  PubMed Central  Google Scholar 

  30. Xu D, Wang J, Liu T, et al. Quantitative definitions of pain, CA19-9, and tumor size as high-risk features of resectable pancreatic cancer: a single-center retrospective cohort study. Gland Surg. 2021;10:770–9.

    PubMed  PubMed Central  Google Scholar 

  31. Tanaka M, Heckler M, Mihaljevic AL, et al. Systematic review and metaanalysis of lymph node metastases of resected pancreatic neuroendocrine tumors. Ann Surg Oncol. 2021;28:1614–24.

    PubMed  Google Scholar 

  32. Cui Y, Wu J, Zong M, et al. Proteomic profiling in pancreatic cancer with and without lymph node metastasis. Int J Cancer. 2009;124:1614–21.

    CAS  PubMed  Google Scholar 

  33. Zou Y, Zheng M, Qi Z, et al. Dual-energy computed tomography could reliably differentiate metastatic from non-metastatic lymph nodes of less than 0.5 cm in patients with papillary thyroid carcinoma. Quant Imaging Med Surg. 2021;11:1354–67.

    PubMed  PubMed Central  Google Scholar 

  34. Li J, Dong D, Fang M, et al. Dual-energy CT-based deep learning radiomics can improve lymph node metastasis risk prediction for gastric cancer. Eur Radiol. 2020;30:2324–33.

    PubMed  Google Scholar 

  35. Forghani R, Chatterjee A, Reinhold C, et al. Head and neck squamous cell carcinoma: prediction of cervical lymph node metastasis by dual-energy CT texture analysis with machine learning. Eur Radiol. 2019;29:6172–81.

    PubMed  Google Scholar 

  36. Tawfik AM, Razek AA, Kerl JM, Nour-Eldin NE, Bauer R, Vogl TJ. Comparison of dual-energy CT-derived iodine content and iodine overlay of normal, inflammatory and metastatic squamous cell carcinoma cervical lymph nodes. Eur Radiol. 2014;24:574–80.

    PubMed  Google Scholar 

  37. Zhang X, Zheng C, Yang Z, et al. Axillary sentinel lymph nodes in breast cancer: quantitative evaluation at dual-energy CT. Radiology. 2018;289:337–46.

    PubMed  Google Scholar 

  38. Li K, Yao Q, Xiao J, et al. Contrast-enhanced CT radiomics for predicting lymph node metastasis in pancreatic ductal adenocarcinoma: a pilot study. Cancer Imaging. 2020;20:12.

    PubMed  PubMed Central  Google Scholar 

  39. Bian Y, Guo S, Jiang H, et al. Relationship between radiomics and risk of lymph node metastasis in pancreatic ductal adenocarcinoma. Pancreas. 2019;48:1195–203.

    CAS  PubMed  PubMed Central  Google Scholar 

  40. Gao J, Han F, Jin Y, Wang X, Zhang J. A radiomics nomogram for the preoperative prediction of lymph node metastasis in pancreatic ductal adenocarcinoma. Front Oncol. 2020;10:1654.

    PubMed  PubMed Central  Google Scholar 

  41. Xie T, Wang X, Li M, Tong T, Yu X, Zhou Z. Pancreatic ductal adenocarcinoma: a radiomics nomogram outperforms clinical model and TNM staging for survival estimation after curative resection. Eur Radiol. 2020;30:2513–24.

    PubMed  Google Scholar 

  42. Sala E, Ursprung S. Artificial intelligence in radiology: the computer’s helping hand needs guidance. Radiol Artif Intell. 2020;2:e200207.

    PubMed  PubMed Central  Google Scholar 

  43. Philbrick KA, Yoshida K, Inoue D, et al. What does deep learning see? Insights from a classifier trained to predict contrast enhancement phase from CT images. AJR Am J Roentgenol. 2018;211:1184–93.

    PubMed  Google Scholar 

  44. Panwar H, Gupta PK, Siddiqui MK, Morales-Menendez R, Bhardwaj P, Singh V. A deep learning and grad-CAM based color visualization approach for fast detection of COVID-19 cases using chest X-ray and CT-scan images. Chaos Solitons Fractals. 2020;140:110190.

    PubMed  PubMed Central  Google Scholar 

  45. Takahashi H, Akita H, Tomokuni A, et al. Preoperative gemcitabine-based chemoradiation therapy for borderline resectable pancreatic cancer: impact of venous and arterial involvement status on surgical outcome and pattern of recurrence. Ann Surg. 2016;264:1091–7.

    PubMed  Google Scholar 

  46. Ravikumar R, Fusai G. Preoperative gemcitabine-based chemoradiation therapy for resectable and borderline resectable pancreatic cancer. Ann Surg. 2015;262:e103.

    PubMed  Google Scholar 

  47. Takahashi H, Ohigashi H, Gotoh K, et al. Preoperative gemcitabine-based chemoradiation therapy for resectable and borderline resectable pancreatic cancer. Ann Surg. 2013;258:1040–50.

    PubMed  Google Scholar 

Download references

Acknowledgements

The authors would like to acknowledge the instrumental and technical support of Multimodal Biomedical Imaging Experimental Platform, Institute of Automation, Chinese Academy of Sciences.

Funding

This study was funded by Ministry of Science and Technology of China under Grant No. 2017YFA0205200, National Natural Science Foundation of China under Grant Nos. 62027901, 81227901, and 81930053, the Youth Innovation Promotion Association CAS under Grant No. Y202040, and the Project of High-Level Talents Team Introduction in Zhuhai City (Zhuhai HLHPTP201703). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Author information

Author notes

  1. Chao An, Dongyang Li, Sheng Li, and Wangzhong Li contributed equally to this paper.

Authors and Affiliations

  1. Department of Minimal Invasive Intervention, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-Sen University Cancer Center, Guangzhou, 510060, China

    Chao An

  2. Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Engineering Medicine, Beihang University, Beijing, 100191, China

    Chao An, Dongyang Li & Jie Tian

  3. CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China

    Dongyang Li, Tong Tong, Kun Wang & Jie Tian

  4. Department of Radiology, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-Sen University Cancer Center, Guangzhou, 510060, China

    Sheng Li, Lizhi Liu, Dongping Jiang, Linling Jiang, Guangying Ruan & Shuiqing Zhuo

  5. Department of Nasopharyngeal Carcinoma, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-Sen University Cancer Center, Guangzhou, 510060, China

    Wangzhong Li

  6. School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China

    Tong Tong, Kun Wang & Jie Tian

  7. Department of Ultrasound, Beijing Chao Yang Hospital, Capital Medical University, Beijing, 100010, China

    Ning Hai

  8. Department of Interventional Therapy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 17 Panjiayuan Nanli, Chaoyang District, Beijing, 100021, China

    Yan Fu

Authors
  1. Chao An
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dongyang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sheng Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wangzhong Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Tong Tong
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Lizhi Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Dongping Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Linling Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Guangying Ruan
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Ning Hai
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Yan Fu
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Kun Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Shuiqing Zhuo
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Jie Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conception and design: Chao An, Kun Wang, Suiqing Zhuo, J. Tian; development of methodology: Kun Wang; acquisition of data (provided animals, acquired and managed patients, provided facilities, etc.): Chao An, Sheng Li, Lizhi Liu, Dongping Jiang, Suiqing Zhuo, Ning Hai, Linling Jiang, Guangying Ruan; analysis and interpretation of data (e.g., statistical analysis, biostatistics, and computational analysis): Chao An, Dongyang Li, Wangzhong Li, Tong Tong, Kun Wang, J. Tian; writing, review, and/or revision of the manuscript: Chao An, Dongyang Li, Kun Wang, Yan Fu, J. Tian; administrative, technical, or material support (i.e., reporting or organizing data and constructing databases): J. Tian; study supervision: Kun Wang, Suiqing Zhuo.

Corresponding authors

Correspondence to Kun Wang, Shuiqing Zhuo or Jie Tian.

Ethics declarations

Ethics approval

This retrospective study was approved by the Institutional Review Board of Sun Yat-sen University Cancer Center (B2019-012–01) and was conducted following the principles of the Declaration of Helsinki. The requirement for written informed consent was waived because of the retrospective nature of the study. The key raw data of this study were uploaded to the Research Data Deposit database (www.researchdata.org.cn. RDD2021002019).

Consent to participate

Yes.

Consent to publication

Yes.

Conflict of interest

The authors declare no competing interests.

Open access

This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution, and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creative.commonsh.org/licenses/by/4.0/.

Additional information

Publisher's note

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

This article is part of the Topical Collection on Advanced Image Analyses (Radiomics and Artificial Intelligence)

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 3149 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

An, C., Li, D., Li, S. et al. Deep learning radiomics of dual-energy computed tomography for predicting lymph node metastases of pancreatic ductal adenocarcinoma. Eur J Nucl Med Mol Imaging 49, 1187–1199 (2022). https://doi.org/10.1007/s00259-021-05573-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00259-021-05573-z

Keywords

Search

Navigation