Highlights
- •Federated learning was applied to analyse data while preserving privacy.
- •LVSI, tumour size, and depth of invasion were the most important risk factors of pN+.
- •41% of the women with early-stage cervical cancer were at low risk (2.4%) of pN+.
Abstract
Objective
Lymph node metastases (pN+) in presumed early-stage cervical cancer negatively impact
prognosis. Using federated learning, we aimed to develop a tool to identify a group
of women at low risk of pN+, to guide the shared decision-making process concerning
the extent of lymph node dissection.
Methods
Women with cervical cancer between 2005 and 2020 were identified retrospectively from
population-based registries: the Danish Gynaecological Cancer Database, Swedish Quality
Registry for Gynaecologic Cancer and Netherlands Cancer Registry. Inclusion criteria
were: squamous cell carcinoma, adenocarcinoma or adenosquamous carcinoma; The International
Federation of Gynecology and Obstetrics 2009 IA2, IB1 and IIA1; treatment with radical
hysterectomy and pelvic lymph node assessment. We applied privacy-preserving federated
logistic regression to identify risk factors of pN+. Significant factors were used
to stratify the risk of pN+.
Results
We included 3606 women (pN+ 11%). The most important risk factors of pN+ were lymphovascular
space invasion (LVSI) (odds ratio [OR] 5.16, 95% confidence interval [CI], 4.59–5.79),
tumour size 21–40 mm (OR 2.14, 95% CI, 1.89–2.43) and depth of invasion>10 mm (OR
1.81, 95% CI, 1.59–2.08). A group of 1469 women (41%)—with tumours without LVSI, tumour
size ≤20 mm, and depth of invasion ≤10 mm—had a very low risk of pN+ (2.4%, 95% CI,
1.7–3.3%).
Conclusion
Early-stage cervical cancer without LVSI, a tumour size ≤20 mm and depth of invasion
≤10 mm, confers a low risk of pN+. Based on an international privacy-preserving analysis,
we developed a useful tool to guide the shared decision-making process regarding lymph
node dissection.
Graphical Abstract
Graphical Abstract
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to European Journal of CancerAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- The role of lymph nodes in cervical cancer: incidence and identification of lymph node metastases-a literature review.Int J Clin Oncol. 2021; 26: 1600-1610https://doi.org/10.1007/s10147-021-01980-2
- The European Society of Gynaecological Oncology/European Society for Radiotherapy and Oncology/European Society of Pathology guidelines for the management of patients with cervical cancer.Virchows Arch. 2018; 472: 919-936https://doi.org/10.1007/s00428-018-2362-9
National Comprehensive Cancer Network. Cervical cancer (NCCN guideline version 1.2023). 2023; Available from 〈https://www.nccn.org/professionals/physician_gls/pdf/cervical.pdf〉.
- Lower-limb lymphedema after sentinel lymph node biopsy in cervical cancer patients.Cancers. 2021; 132360https://doi.org/10.3390/cancers13102360
- SENTIREC - the sentinel node mapping in women with cervical cancer study - patient-reported early lymphedema and its impact on quality of life.Gynecol Oncol. 2022; 164: 463-472https://doi.org/10.1016/j.ygyno.2021.12.024
- Bilateral ultrastaging of sentinel lymph node in cervical cancer: lowering the false-negative rate and improving the detection of micrometastasis.Gynecol Oncol. 2012; 127: 462-466https://doi.org/10.1016/j.ygyno.2012.08.035
- Does the new FIGO 2018 staging system allow better prognostic differentiation in early stage cervical cancer? A Dutch nationwide cohort study.Cancers. 2022; 143140https://doi.org/10.3390/cancers14133140
- Privacy preserving federated big data analysis.Guide to Big Data Applications. Springer, 2018: 49-82
- A survey on federated learning systems: vision, hype and reality for data privacy and protection.IEEE Trans Knowl Data Eng. 2021; 35: 3347-3366https://doi.org/10.1109/tkde.2021.3124599
- Distributed learning on 20,000+ lung cancer patients - the personal health train.Radiother Oncol. 2020; 144: 189-200https://doi.org/10.1016/j.radonc.2019.11.019
- Prognostic factors analysis for oral cavity cancer survival in the Netherlands and Taiwan using a privacy-preserving federated infrastructure.Sci Rep. 2020; 1020526https://doi.org/10.1038/s41598-020-77476-2
- Danish gynecological cancer database.Clin Epidemiol. 2016; 8: 485-490https://doi.org/10.2147/clep.S99479
- Data quality in the Swedish Quality Register of Gynecologic Cancer - a Swedish gynecologic cancer group (SweGCG) study.Acta Oncol. 2018; 57: 346-353https://doi.org/10.1080/0284186x.2017.1366048
- Cancer incidence in the Netherlands in 1989 and 1990: first results of the nationwide Netherlands Cancer Registry. Coordinating committee for regional cancer registries.Eur J Cancer. 1995; 31a: 1822-1829https://doi.org/10.1016/0959-8049(95)00355-m
- An improved infrastructure for privacy-preserving analysis of patient data.Stud Health Technol Inform. 2022; 295: 144-147https://doi.org/10.3233/shti220682
- A federated generalized linear model for privacy-preserving analysis.Algorithms. 2022; 15243
- Approximate is better than "exact" for interval estimation of binomial proportions.Am Stat. 1998; 52: 119-126https://doi.org/10.2307/2685469
- Current status of sentinel lymph node mapping in the management of cervical cancer.Expert Rev Anticancer Ther. 2013; 13: 861-870https://doi.org/10.1586/14737140.2013.811147
- Sentinel lymph node biopsy and morbidity outcomes in early cervical cancer: results of a multicentre randomised trial (SENTICOL-2).Eur J Cancer. 2021; 148: 307-315https://doi.org/10.1016/j.ejca.2021.02.009
- From FIGO-2009 to FIGO-2018 in women with early-stage cervical cancer; does the revised staging reflect risk groups.Gynecol Oncol. 2021; 163: 281-288https://doi.org/10.1016/j.ygyno.2021.08.026
- Can conization specimens predict sentinel lymph node status in early-stage cervical cancer? A SENTICOL group study.Cancers. 2021; 135423https://doi.org/10.3390/cancers13215423
- Cervical biopsy and excision procedure specimens lack sufficient predictive value for lymph-vascular space invasion seen at hysterectomy for cervical cancer.Am J Obstet Gynecol. 2008; 199151.e1-4https://doi.org/10.1016/j.ajog.2008.02.017
- Accuracy of conization procedure for predicting pathological parameters of radical hysterectomy in stage Ia2-Ib1 (≤2 cm) cervical cancer.Sci Rep. 2016; 625992https://doi.org/10.1038/srep25992
- Variability in the identification of lymphovascular space invasion for early stage cervical cancer.Surg Oncol. 2021; 38101566https://doi.org/10.1016/j.suronc.2021.101566
- Substantial lymph-vascular space invasion (LVSI) is a significant risk factor for recurrence in endometrial cancer--a pooled analysis of PORTEC 1 and 2 trials.Eur J Cancer. 2015; 51: 1742-1750https://doi.org/10.1016/j.ejca.2015.05.015
- Reproducibility of lymphovascular space invasion (LVSI) assessment in endometrial cancer.Histopathology. 2019; 75: 128-136https://doi.org/10.1111/his.13871
- Multi-parametric magnetic resonance imaging-based radiomics analysis of cervical cancer for preoperative prediction of lymphovascular space invasion.Front Oncol. 2021; 11663370https://doi.org/10.3389/fonc.2021.663370
- MR-based radiomics nomogram of cervical cancer in prediction of the lymph-vascular space invasion preoperatively.J Magn Reson Imaging. 2019; 49: 1420-1426https://doi.org/10.1002/jmri.26531
- Pathologic and clinical tumor size discordance in early-stage cervical cancer: does it matter.Gynecol Oncol. 2020; 159: 354-358https://doi.org/10.1016/j.ygyno.2020.08.004
- Early invasive cervical cancer: Tumor delineation by magnetic resonance imaging, computed tomography, and clinical examination, verified by pathologic results, in the ACRIN 6651/GOG 183 Intergroup Study.J Clin Oncol. 2006; 24: 5687-5694https://doi.org/10.1200/jco.2006.07.4799
- The correlation of preoperative CT, MR imaging, and clinical staging (FIGO) with histopathology findings in primary cervical carcinoma.Eur Radiol. 2003; 13: 2338-2345https://doi.org/10.1007/s00330-003-1928-2
- Measurement of tumor size in early cervical cancer: an ever-evolving paradigm.Int J Gynecol Cancer. 2020; 30: 1215-1223https://doi.org/10.1136/ijgc-2020-001436
- Pattern-based classification of invasive endocervical adenocarcinoma, depth of invasion measurement and distinction from adenocarcinoma in situ: interobserver variation among gynecologic pathologists.Mod Pathol. 2016; 29: 879-892https://doi.org/10.1038/modpathol.2016.86
- Negative MRI findings with invasive cervical biopsy may indicate stage ia cervical carcinoma.Gynecol Oncol. 2000; 79: 451-456https://doi.org/10.1006/gyno.2000.5967
- Stage IB1 cervical cancer: role of preoperative MR imaging in selection of patients for fertility-sparing radical trachelectomy.Radiology. 2013; 269: 149-158https://doi.org/10.1148/radiol.13121746
- Protective role of conization before radical hysterectomy in early-stage cervical cancer: a propensity-score matching study.Ann Surg Oncol. 2021; 28: 3585-3594https://doi.org/10.1245/s10434-021-09695-4
- SUCCOR cone study: conization before radical hysterectomy.Int J Gynecol Cancer. 2022; 32: 117-124https://doi.org/10.1136/ijgc-2021-002544
Article info
Publication history
Published online: February 25, 2023
Accepted:
February 22,
2023
Received in revised form:
February 22,
2023
Received:
December 22,
2022
Footnotes
☆Dutch, dANish and sweDish gynaEcoLogIcal ONcologogy (DANDELION) research group.
Identification
Copyright
© 2023 Elsevier Ltd. All rights reserved.
