Radiomics allows for detection of benign and malignant histopathology in patients with metastatic testicular germ cell tumors prior to post-chemotherapy retroperitoneal lymph node dissection

Abstract

Objectives

To evaluate whether a computed tomography (CT) radiomicsbased machine learning classifier can predict histopathology of lymph nodes (LNs) after post-chemotherapy LN dissection (pcRPLND) in patients with metastatic non-seminomatous testicular germ cell tumors (NSTGCTs).

Methods

Eighty patients with retroperitoneal LN metastases and contrast-enhanced CT were included into this retrospective study. Resected LNs were histopathologically classified into “benign” (necrosis/fibrosis) or “malignant” (viable tumor/teratoma). On CT imaging, 204 corresponding LNs were segmented and 97 radiomic features per LN were extracted after standardized image processing. The dataset was split into training, test, and validation sets. After stepwise feature reduction based on reproducibility, variable importance, and correlation analyses, a gradient-boosted tree was trained and tuned on the selected most important features using the training and test datasets. Model validation was performed on the independent validation dataset.

Results

The trained machine learning classifier achieved a classification accuracy of 0.81 in the validation dataset with a misclassification of 8 of 36 benign LNs as malignant and 4 of 25 malignant LNs as benign (sensitivity 88%, specificity 72%, negative predictive value 88%). In contrast, a model containing only the LN volume resulted in a classification accuracy of 0.68 with 64% sensitivity and 68% specificity.

Conclusions

CT radiomics represents an exciting new tool for improved prediction of the presence of malignant histopathology in retroperitoneal LN metastases from NSTGCTs, aiming at reducing overtreatment in this group of young patients. Thus, the presented approach should be combined with established clinical biomarkers and further validated in larger, prospective clinical trials.

Key Points

• Patients with metastatic non-seminomatous testicular germ cell tumors undergoing post-chemotherapy retroperitoneal lymph node dissection of residual lesions show overtreatment in up to 50%.

• We assessed whether a CT radiomics–based machine learning classifier can predict histopathology of lymph nodes after post-chemotherapy lymph node dissection.

• The trained machine learning classifier achieved a classification accuracy of 0.81 in the validation dataset with a sensitivity of 88% and a specificity of 78%, thus allowing for prediction of the presence of viable tumor or teratoma in retroperitoneal lymph node metastases.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Abbreviations

AFP:

Alpha-fetoprotein

AUC:

Area under the curve

BEP:

Bleomycin-, etoposide-, and cisplatin-based polychemotherapy

CT:

Computed tomography

DICOM:

Digital Imaging and Communications in Medicine

hCG:

Human chorionic gonadotropin

LDH:

Lactate dehydrogenase

LNs:

Lymph nodes

NSTGCT:

Non-seminomatous testicular germ cell tumor

pcRPLND:

Post-chemotherapy retroperitoneal lymph node dissection

PET-CT:

Positron emission computed tomography

ROC:

Receiver operating curve

ROI:

Region of interest

RPLND:

Retroperitoneal lymph node dissection

STARD:

Standards for Reporting Diagnostic

TGCT:

Testicular germ cell tumor

References

  1. 1.

    Rosen A, JayramG DM, Eggener SE (2011) Global trends in testicular cancer incidence and mortality. Eur Urol 60(2):374–379

    Article  Google Scholar 

  2. 2.

    Klepp O, Flodgren P, Maartman-Moe H et al (1990) Early clinical stages (CS1, CS1Mk+ and CS2A) of non-seminomatous testis cancer. Value of pre- and postorchiectomy serum tumor marker information in prediction of retroperitoneal lymph node metastases. Swedish-Norwegian Testicular Cancer Project (SWENOTECA). Ann Oncol 1(4):281–288

    CAS  Article  Google Scholar 

  3. 3.

    Albers P, AlbrechtW AF et al (2015) Guidelines on testicular cancer: 2015 update. Eur Urol 68(6):1054–1068

    Article  Google Scholar 

  4. 4.

    Kuczyk M, Machtens S, Stief C, Jonas U (1999) Management of the post-chemotherapy residual mass in patients with advanced stage non-seminomatous germ cell tumors (NSGCT). Int J Cancer 83(6):852–855

    CAS  Article  Google Scholar 

  5. 5.

    Oechsle K, Hartmann M, Brenner W et al (2008) 18FFluorodeoxyglucose positron emission tomography in nonseminomatous germ cell tumors after chemotherapy: the German multicenter positron emission tomography study group. J Clin Oncol 26(36):5930–5935

    Article  Google Scholar 

  6. 6.

    EAU Guidelines Office (2019) EAUguidelines on testicular cancer. Edn. presented at the EAU Annual Congress Barcelona, Arnhem, The Netherlands

  7. 7.

    Heidenreich A, Haidl F, Paffenholz P, Pape C, Neumann U, Pfister D (2017) Surgicalmanagement of complex residual masses following systemic chemotherapy for metastatic testicular germ cell tumours. Ann Oncol 28(2):362–367

    CAS  Article  Google Scholar 

  8. 8.

    Winter C, Pfister D, Busch J, Bingöl C, Ranft U, Schrader M et al (2012) Residual tumor size and IGCCCG risk classification predict additional vascular procedures in patients with germ cell tumors and residual tumor resection: a multicenter analysis of the German Testicular Cancer Study Group. Eur Urol 61(2):403–409

    Article  Google Scholar 

  9. 9.

    Nini A, Konieczny M, Winter C, Lusch A, Krauspe R, Albers P (2018) Surgical management and outcomes of patients with bone metastases in germ cell tumors: a case series. Urol Oncol 36(2):82.e1–82.e5

    Article  Google Scholar 

  10. 10.

    Leão R, Nayan M, Punjani N, Jewett MAS, Fadaak K, Garisto J et al (2018) A new model to predict benign histology in residual retroperitoneal masses after chemotherapy in nonseminoma. Eur Urol Focus 4(6):995–1001

    Article  Google Scholar 

  11. 11.

    Steyerberg EW, Gerl A, Fossá SD, Sleijfer DT, de Wit R, Kirkels WJ et al (1998) Validity of predictions of residual retroperitoneal mass histology in nonseminomatous testicular cancer. J Clin Oncol 16(1):269–274

    CAS  Article  Google Scholar 

  12. 12.

    Vergouwe Y, Steyerberg EW, Foster RS, Sleijfer DT, Fosså SD, Gerl A et al (2007) Predicting retroperitoneal histology in postchemotherapy testicular germ cell cancer: a model update and multicentre validation with more than 1000 patients. Eur Urol 51(2):424–432

    Article  Google Scholar 

  13. 13.

    Obermeyer Z, Emanuel EJ (2016) Predicting the future - big data, machine learning, and clinical medicine. N Engl J Med 375(13):1216–1219

    Article  Google Scholar 

  14. 14.

    Lambin P, Leijenaar RTH, Deist TM, Peerlings J, de Jong EEC, van Timmeren J et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14(12):749–762

    Article  Google Scholar 

  15. 15.

    Ng F, Ganeshan B, Kozarski R, Miles KA, Goh V (2013) Assessment of primary colorectal cancer heterogeneity by using whole-tumor texture analysis: contrast-enhanced CT texture as a biomarker of 5-year survival. Radiology 266(1):177–184

    Article  Google Scholar 

  16. 16.

    Wu S, Zheng J, Li Y, Yu H, Shi S, Xie W et al (2017) A radiomics nomogramfor the preoperative prediction of lymph nodemetastasis in bladder cancer. Clin Cancer Res 23(22):6904–6911

    CAS  Article  Google Scholar 

  17. 17.

    Huang Y-Q, Liang C-H, He L, Tian J, Liang C-S, Chen X et al (2016) Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol 34(18):2157–2164

    Article  Google Scholar 

  18. 18.

    Fedorov A, Beichel R, Kalpathy-Cramer J, Finet J, Fillion-Robin JC, Pujol S et al (2012) 3D Slicer as an image computing platform for the Quantitative Imaging Network. Magn Reson Imaging 30(9):1323–1341

    Article  Google Scholar 

  19. 19.

    Nioche C, Orlhac F, Boughdad S, Reuzé S, Goya-Outi J, Robert C et al (2018) LIFEx: a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity. Cancer Res 78(16):4786–4789

    CAS  Article  Google Scholar 

  20. 20.

    Collewet G, Strzelecki M, Mariette F (2004) Influence of MRI acquisition protocols and image intensity normalization methods on texture classification. Magn Reson Imaging 22(1):81–91

    CAS  Article  Google Scholar 

  21. 21.

    van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V et al (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77(21):e104–e107

    Article  Google Scholar 

  22. 22.

    Zwanenburg A, Leger S, Vallières M, Löck S (2016) Image biomarker standardisation initiative. Accessible online http://arxiv.org/pdf/1612.07003v9

  23. 23.

    R Core Team. R: a language and environment for statistical computing. Vienna, Austria

  24. 24.

    Studio Team R (2015) RStudio: integrated development environment for R. RStudio, Inc., Boston

    Google Scholar 

  25. 25.

    Baessler B, Mannil M, Oebel S et al (2018) Subacute and chronic left ventricular myocardial scar: accuracy of texture analysis on nonenhanced cine MR images. Radiology. 286(1):103–112

    Article  Google Scholar 

  26. 26.

    Baessler B, Luecke C, Lurz J et al (2018) Cardiac MRI texture analysis of T1 and T2 maps in patients with infarctlike acute myocarditis. Radiology. 289(2):357–365

    Article  Google Scholar 

  27. 27.

    Lewin J, Dufort P, Halankar J, O’Malley M, JewettMAS HRJ et al (2018) Applying radiomics to predict pathology of postchemotherapy retroperitoneal nodal masses in germ cell tumors. JCO Clin Cancer Informat 2:1–12

    Article  Google Scholar 

  28. 28.

    Leão R, van Agthoven T, Figueiredo A, Jewett MAS, Fadaak K, Sweet J et al (2018) Serum miRNA predicts viable disease after chemotherapy in patients with testicular nonseminoma germ cell tumor. J Urol 200(1):126–135

    Article  Google Scholar 

  29. 29.

    AndersenMB HSW, Ganeshan B, Thygesen J, TorpMadsen HH, Rasmussen F (2016) CT texture analysis can help differentiate between malignant and benign lymph nodes in the mediastinum in patients suspected for lung cancer. Acta Radiol 57(6):669–676

    Article  Google Scholar 

  30. 30.

    Bayanati H, Thornhill ER, Souza CA, Sethi-Virmani V, Gupta A, Maziak D et al (2015) Quantitative CT texture and shape analysis: can it differentiate benign and malignant mediastinal lymph nodes in patients with primary lung cancer? Eur Radiol 25(2):480–487

    Article  Google Scholar 

  31. 31.

    Tan X, Ma Z, Yan L, Ye W, Liu Z, Liang C (2019) Radiomics nomogram outperforms size criteria in discriminating lymph node metastasis in resectable esophageal squamous cell carcinoma. Eur Radiol 29(1):392–400

    Article  Google Scholar 

  32. 32.

    Albers P, Weissbach L, Krege S, Kliesch S, Hartmann M, Heidenreich A et al (2004) Prediction of necrosis after chemotherapy of advanced germ cell tumors: results of a prospective multicenter trial of the German Testicular Cancer Study Group. J Urol 171(5):1835–1838

    Article  Google Scholar 

  33. 33.

    Paffenholz P, Nestler T, Hoier S et al (2019) Independent validation of two models to predict necrosis/fibrosis in post chemotherapy residual retroperitoneal masses of patients with advanced testicular cancer. Eur Urol Suppl 18–827

Download references

Funding

The authors state that this work has not received any funding.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Bettina Baessler.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Bettina Baeßler.

Conflict of interest

The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

One of the authors has significant statistical expertise.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• Retrospective

• Diagnostic or prognostic study

• Performed at one institution

Additional information

Publisher’s note

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

Electronic supplementary material

R packages used for statistical analysis

ESM 1

(DOCX 21 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Baessler, B., Nestler, T., Pinto dos Santos, D. et al. Radiomics allows for detection of benign and malignant histopathology in patients with metastatic testicular germ cell tumors prior to post-chemotherapy retroperitoneal lymph node dissection. Eur Radiol 30, 2334–2345 (2020). https://doi.org/10.1007/s00330-019-06495-z

Download citation

Keywords

  • Tomography
  • Lymph nodes
  • Testicular neoplasms