Abstract
Objectives
To build preoperative prediction models with and without MRI for regional lymph node metastasis (r-LNM, pelvic and/or para-aortic LNM (PENM/PANM)) and for PANM in endometrial cancer using established risk factors.
Methods
In this retrospective two-center study, 364 patients with endometrial cancer were included: 253 in the model development and 111 in the external validation. For r-LNM and PANM, respectively, best subset regression with ten-time fivefold cross validation was conducted using ten established risk factors (4 clinical and 6 imaging factors). Models with the top 10 percentile of area under the curve (AUC) and with the fewest variables in the model development were subjected to the external validation (11 and 4 candidates, respectively, for r-LNM and PANM). Then, the models with the highest AUC were selected as the final models. Models without MRI findings were developed similarly, assuming the cases where MRI was not available.
Results
The final r-LNM model consisted of pelvic lymph node (PEN) ≥ 6 mm, deep myometrial invasion (DMI) on MRI, CA125, para-aortic lymph node (PAN) ≥ 6 mm, and biopsy; PANM model consisted of DMI, PAN, PEN, and CA125 (in order of correlation coefficient β values). The AUCs were 0.85 (95%CI: 0.77–0.92) and 0.86 (0.75–0.94) for the external validation, respectively. The model without MRI for r-LNM and PANM showed AUC of 0.79 (0.68–0.89) and 0.87 (0.76–0.96), respectively.
Conclusions
The prediction models created by best subset regression with cross validation showed high diagnostic performance for predicting LNM in endometrial cancer, which may avoid unnecessary lymphadenectomies.
Clinical relevance statement
The prediction risks of lymph node metastasis (LNM) and para-aortic LNM can be easily obtained for all patients with endometrial cancer by inputting the conventional clinical information into our models. They help in the decision-making for optimal lymphadenectomy and personalized treatment.
Key Points
•Diagnostic performance of lymph node metastases (LNM) in endometrial cancer is low based on size criteria and can be improved by combining with other clinical information.
•The optimized logistic regression model for regional LNM consists of lymph node ≥ 6 mm, deep myometrial invasion, cancer antigen-125, and biopsy, showing high diagnostic performance.
•Our model predicts the preoperative risk of LNM, which may avoid unnecessary lymphadenectomies.
Similar content being viewed by others
Abbreviations
- AUC:
-
Area under the curve
- BVS:
-
Bivariate variable selection method
- CA:
-
Cancer antigen
- CE-MRI:
-
Contrast-enhanced MRI
- CI:
-
Confidence interval
- CSI:
-
Cervical stromal invasion
- DMI:
-
Deep myometrial invasion
- EC:
-
Endometrial cancer
- FDG PET-CT:
-
Fluorine-18–2-deoxy-d-glucose PET-CT
- FIGO:
-
International Federation of Gynecology and Obstetrics
- FN:
-
False negative
- LN(M):
-
Lymph node (metastasis)
- NPV:
-
Negative predictive value
- PAN(M):
-
Para-aortic lymph node (metastasis)
- PEN(M):
-
Pelvic lymph node (metastasis)
- PPV:
-
Positive predictive value
- r-LNM:
-
Regional lymph node metastasis
- ROC-AUC:
-
Receiver operating characteristic curve area under the curve
- SLN:
-
Sentinel lymph node
- VIF:
-
Variance inflation factors
References
Sung H, Ferlay J, Siegel RL et al (2020) Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin. https://doi.org/10.3322/caac.21660
Beddy P, O’Neill AC, Yamamoto AK, Addley HC, Reinhold C, Sala E (2012) FIGO staging system for endometrial cancer: added benefits of MR imaging. Radiographics. https://doi.org/10.1148/rg.321115045
Benedetti PP, Basile S, Maneschi F et al (2008) Systematic pelvic lymphadenectomy vs. no lymphadenectomy in early stage endometrial carcinoma: randomized clinical trial. J Natl Cancer Inst. https://doi.org/10.1093/jnci/djn397
ASTEC study group (2009) Efficacy of systematic pelvic lymphadenectomy in endometrial cancer (MRC ASTEC trial): a randomised study. Lancet. https://doi.org/10.1016/S0140-6736(08)61766-3
Frost JA, Webster KE, Bryant A, Morrison J (2017) Lymphadenectomy for the management of endometrial cancer. Cochrane Database Syst Rev. https://doi.org/10.1002/14651858.CD007585.pub4
Todo Y, Takeshita S, Okamoto K, Yamashiro K, Kato H (2017) Implications of para-aortic lymph node metastasis in patients with endometrial cancer without pelvic lymph node metastasis. J Gynecol Oncol. https://doi.org/10.3802/jgo.2017.28.e59
Todo Y, Sakuragi N, Nishida R et al (2003) Combined use of magnetic resonance imaging, CA 125 assay, histologic type, and histologic grade in the prediction of lymph node metastasis in endometrial carcinoma. Am J Obstet Gynecol. https://doi.org/10.1067/mob.2003.318
Imai K, Kato H, Katayama K et al (2016) A preoperative risk-scoring system to predict lymph node metastasis in endometrial cancer and stratify patients for lymphadenectomy. Gynecol Oncol. https://doi.org/10.1016/j.ygyno.2016.06.004
Haldorsen IS, Salvesen HB (2012) Staging of endometrial carcinomas with MRI using traditional and novel MRI techniques. Clin Radiol. https://doi.org/10.1016/j.crad.2011.02.018
Manfredi R, Mirk P, Maresca G et al (2004) Local-regional staging of endometrial carcinoma: role of MR imaging in surgical planning. Radiology. https://doi.org/10.1148/radiol.2312021184
Lee JY, Jung DC, Park SH et al (2010) Preoperative prediction model of lymph node metastasis in endometrial cancer. Int J Gynecol Cancer. https://doi.org/10.1111/IGC.0b013e3181f44f5a
Kang S, Kang WD, Chung HH et al (2012) Preoperative identification of a low-risk group for lymph node metastasis in endometrial cancer: a Korean gynecologic oncology group study. J Clin Oncol. https://doi.org/10.1200/JCO.2011.38.2416
Sadowski EA, Robbins JB, Guite K et al (2015) Preoperative Pelvic MRI and Serum Cancer Antigen-125: Selecting Women With Grade 1 Endometrial Cancer for Lymphadenectomy. AJR Am J Roentgenol. https://doi.org/10.2214/AJR.14.13746
Kang S, Nam JH, Bae DS et al (2017) Preoperative assessment of lymph node metastasis in endometrial cancer: A Korean Gynecologic Oncology Group study. Cancer. https://doi.org/10.1002/cncr.30349
Koskas M, Genin AS, Graesslin O et al (2014) Evaluation of a method of predicting lymph node metastasis in endometrial cancer based on five pre-operative characteristics. Eur J Obstet Gynecol Reprod Biol. https://doi.org/10.1016/j.ejogrb.2013.10.028
Koskas M, Fournier M, Vanderstraeten A et al (2016) Evaluation of models to predict lymph node metastasis in endometrial cancer: A multicentre study. Eur J Cancer. https://doi.org/10.1016/j.ejca.2016.03.079
Otani S, Himoto Y, Nishio M et al (2022) Radiomic machine learning for pretreatment assessment of prognostic risk factors for endometrial cancer and its effects on radiologists’ decisions of deep myometrial invasion. Magn Reson Imaging. https://doi.org/10.1016/j.mri.2021.10.024
Takeshima N, Shimizu Y, Umezawa S et al (1994) Combined assay of serum levels of CA125 and CA19-9 in endometrial carcinoma. Gynecol Oncol. https://doi.org/10.1006/gyno.1994.1217
Lin G, Ho KC, Wang JJ et al (2008) Detection of lymph node metastasis in cervical and uterine cancers by diffusion-weighted magnetic resonance imaging at 3T. J Magn Reson Imaging. https://doi.org/10.1002/jmri.21412
King JE (2016) Running a Best-Subsets Logistic Regression: An Alternative to Stepwise Methods. Educ Psychol Meas. https://doi.org/10.1177/0013164403063003003
Zhang Z (2016) Variable selection with stepwise and best subset approaches. Ann Transl Med. https://doi.org/10.21037/atm.2016.03.35
Akaike H (1974) A new look at the statistical model identification. IEEE Trans Autom Control. https://doi.org/10.1109/tac.1974.1100705
Simundic AM (2009) (2009) Measures of Diagnostic Accuracy: Basic Definitions. EJIFCC 19(4):203–211
Vickers AJ, Elkin EB (2006) Decision curve analysis: a novel method for evaluating prediction models. Med Decis Making. https://doi.org/10.1177/0272989X06295361
Vickers AJ, van Calster B, Steyerberg EW (2019) A simple, step-by-step guide to interpreting decision curve analysis. Diagn Progn Res. https://doi.org/10.1186/s41512-019-0064-7
Nougaret S, Horta M, Sala E et al (2019) Endometrial Cancer MRI staging: Updated Guidelines of the European Society of Urogenital Radiology. Eur Radiol. https://doi.org/10.1007/s00330-018-5515-y
Expert Panel on GYN and OB Imaging (2020) ACR Appropriateness Criteria® Pretreatment Evaluation and Follow-Up of Endometrial Cancer. J Am Coll Radiol. https://doi.org/10.1016/j.jacr.2020.09.001
National Comprehensive Cancer Network (2023) Available via. https://www.nccn.org/guidelines/guidelines-detail?categoy=1&id=1473. Accessed 1 March 2023
Lakhman Y, Katz SS, Goldman DA et al (2016) Diagnostic Performance of Computed Tomography for Preoperative Staging of Patients with Non-endometrioid Carcinomas of the Uterine Corpus. Ann Surg Oncol. https://doi.org/10.1245/s10434-015-4410-x
Connor JP, Andrews JI, Anderson B, Buller RE (2000) Computed tomography in endometrial carcinoma. Obstet Gynecol. https://doi.org/10.1016/s0029-7844(99)00626-2
Kitajima K, Suzuki K, Senda M et al (2011) Preoperative nodal staging of uterine cancer: is contrast-enhanced PET/CT more accurate than non-enhanced PET/CT or enhanced CT alone? Ann Nucl Med. https://doi.org/10.1007/s12149-011-0496-9
Park JY, Kim EN, Kim DY et al (2008) Comparison of the validity of magnetic resonance imaging and positron emission tomography/computed tomography in the preoperative evaluation of patients with uterine corpus cancer. Gynecol Oncol. https://doi.org/10.1016/j.ygyno.2007.11.044
Kim HJ, Cho A, Yun M, Kim YT, Kang WJ (2016) Comparison of FDG PET/CT and MRI in lymph node staging of endometrial cancer. Ann Nucl Med. https://doi.org/10.1007/s12149-015-1037-8
Abu FM, Saleh H, Rawlins H, Duncan T, Nieto J (2011) The use of MRI for selecting patients with endometrial cancer and significant comorbidities for vaginal hysterectomy. Arch Gynecol Obstet. https://doi.org/10.1007/s00404-010-1541-y
Rockall AG, Meroni R, Sohaib SA et al (2007) Evaluation of endometrial carcinoma on magnetic resonance imaging. Int J Gynecol Cancer. https://doi.org/10.1111/j.1525-1438.2007.00805.x
Bollineni VR, Ytre-Hauge S, Bollineni-Balabay O, Salvesen HB, Haldorsen IS (2016) High Diagnostic Value of 18F-FDG PET/CT in Endometrial Cancer: Systematic Review and Meta-Analysis of the Literature. J Nucl Med. https://doi.org/10.2967/jnumed.115.170597
Tanaka T, Terai Y, Yamamoto K, Yamada T, Ohmichi M (2018) The diagnostic accuracy of fluorodeoxyglucose-positron emission tomography/computed tomography and sentinel node biopsy in the prediction of pelvic lymph node metastasis in patients with endometrial cancer: A retrospective observational study. Medicine (Baltimore). https://doi.org/10.1097/MD.0000000000012522
Park JY, Lee JJ, Choi HJ et al (2017) The Value of Preoperative Positron Emission Tomography/Computed Tomography in Node-Negative Endometrial Cancer on Magnetic Resonance Imaging. Ann Surg Oncol. https://doi.org/10.1245/s10434-017-5901-8
Kitajima K, Murakami K, Yamasaki E, Kaji Y, Sugimura K (2009) Accuracy of integrated FDG-PET/contrast-enhanced CT in detecting pelvic and para-aortic lymph node metastasis in patients with uterine cancer. Eur Radiol. https://doi.org/10.1007/s00330-008-1271-8
Kim SH, Kim SC, Choi BI, Han MC (1994) Uterine cervical carcinoma: evaluation of pelvic lymph node metastasis with MR imaging. Radiology. https://doi.org/10.1148/radiology.190.3.8115631
Yang WT, Lam WW, Yu MY, Cheung TH, Metreweli C (2000) Comparison of dynamic helical CT and dynamic MR imaging in the evaluation of pelvic lymph nodes in cervical carcinoma. AJR Am J Roentgenol. https://doi.org/10.2214/ajr.175.3.1750759
Choi HJ, Kim SH, Seo SS et al (2006) MRI for pretreatment lymph node staging in uterine cervical cancer. AJR Am J Roentgenol. https://doi.org/10.2214/AJR.05.0263
Yamanoi K, Matsumura N, Kido A et al (2013) A novel diagnostic criterion for lymph node metastasis in cervical cancer using multi-detector computed tomography. Gynecol Oncol. https://doi.org/10.1016/j.ygyno.2013.10.014
Ballester M, Dubernard G, Lecuru F et al (2011) Detection rate and diagnostic accuracy of sentinel-node biopsy in early stage endometrial cancer: a prospective multicentre study (SENTI-ENDO). Lancet Oncol. https://doi.org/10.1016/S1470-2045(11)70070-5
Acknowledgements
The proposed LNM prediction model system is accessible on https://kuhp-drad-gyne-pred1.shinyapps.io/LN_model_with_MRI/
The authors thank Dr. Satoshi Morita for his statistical advice.
Funding
This work was supported by Japan Society for the Promotion of Science (JSPS) KAKENHI Grant Number 20K16748.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Guarantor
The scientific guarantor of this publication is Yuki Himoto.
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 (Dr. Mizuho Nishio M.D., Ph.D.) has significant expertise in machine learning.
Prof. Satoshi Morita, Ph.D. (Kyoto University Graduate School of Medicine, Department of Biomedical Statistics and Bioinformatics), kindly provided statistical advice for this manuscript.
Informed consent
Written informed consent was waived by the Institutional Review Board.
Ethical approval
Institutional Review Board approval was obtained. This study was approved by the Kyoto University Graduate School and Faculty of Medicine, Ethics Committee (Approval number: R2747), and National Cancer Center Ethics Committee (Approval number 2020–480).
Study subjects or cohorts overlap
Among 364 patients, 183 patients have been previously reported in the paper titled: “Otani S, Himoto Y, Nishio M et al (2022) Radiomic machine learning for pretreatment assessment of prognostic risk factors for endometrial cancer and its effects on radiologists’ decisions of deep myometrial invasion. Magn Reson Imaging 85:161–167. https://doi.org/10.1016/j.mri.2021.10.024” (PMID: 34687853). The previous article dealt with radiomic machine learning classifiers for the pretreatment assessment of comprehensive risk factors. This study focused on building a clinically practical prediction model for lymph node metastasis.
Methodology
• retrospective
• diagnostic or prognostic study
• multicenter study
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Below is the link to the electronic supplementary material.
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.
About this article
Cite this article
Matsumoto, Y.K., Himoto, Y., Nishio, M. et al. Nodal infiltration in endometrial cancer: a prediction model using best subset regression. Eur Radiol 34, 3375–3384 (2024). https://doi.org/10.1007/s00330-023-10310-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-023-10310-1