EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY-NC 4.0

Multiparametric MRI radiomics models for preoperative assessment of lymph vascular space invasion status in early-stage cervical cancer: a 2-centre retrospective study

Lei Deng, Rui Zhang, Huabing Lv, Feng Li, Lin Li, Xiaomin Qin, Jiang Yang, Tao Ai, Chencui Huang, Xingzhi Chen, Hui Xing, Feng Wu iD

British Journal of Radiology · 2026

DOI: 10.1093/bjr/tqaf248 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift British Journal of Radiology, 2026. Verfasst von Lei Deng und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Xiangyang Central Hospital, Affiliated Hospital of Hubei University of Arts and Science, Xiangyang, Hubei, 441021, P.R. Chin…. Hauptthemen laut MEDLINE: Uterine Cervical Neoplasms, Multiparametric Magnetic Resonance Imaging. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Hubei Provincial Health Science and Technology Project, Hubei Provincial Natural Science Foundation Joint Fund Project, Hubei Provincial Department of Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To preoperatively predict lymphovascular space invasion (LVSI) in early-stage cervical cancer (CC) using multiparametric MRI (mpMRI) radiomics models.

Methods

This dual-centre study included 196 early-stage CC patients (Centre A: 142, Dec 2020-Apr 2023; Centre B: 54, May-Oct 2023). Centre A was partitioned into training (n = 99) and internal validation (n = 43) cohorts; Centre B served as external validation. Radiomics features were extracted from T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and contrast-enhanced T1-weighted MRI (CE-MRI) sequences. Feature stability was assessed via intraclass correlation and Dice coefficient, with selection through linear correlation and F-tests. Seven radiomics models (single/combined sequences) were built using the top-performing algorithm among 11 machine learning methods. A combination model (CMIC) integrated the optimal mpMRI model’s rad-score with clinical factors. Performance was evaluated by ROC, calibration curves, and DCA across all cohorts.

Results

The AdaBoost-based mpMRI model (CE-MRI + DWI + T2WI) utilized 12 selected features. It achieved AUCs of 0.953 (95% CI: 0.916-0.989) in training, 0.868 (0.755-0.981) in internal validation, and 0.797 (0.677-0.916) externally. The CMIC model showed comparable performance (training: 0.957; validation: 0.864; external: 0.847), with no significant differences versus the mpMRI model (P > .05 all cohorts).

Conclusion

The AdaBoost-driven mpMRI radiomics model effectively predicts LVSI in early-stage CC. Both mpMRI and CMIC models demonstrate robust preoperative predictive capability. Advances in knowledge This mpMRI radiomics approach using AdaBoost outperforms single-sequence models for LVSI prediction, enabling personalized treatment strategies for early-stage CC.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Uterine Cervical NeoplasmsMultiparametric Magnetic Resonance ImagingHumansFemaleRetrospective StudiesMiddle AgedNeoplasm InvasivenessAdultNeoplasm StagingAgedPreoperative CareLymphatic MetastasisRadiomics

Stichwörter der Autor:innen

cervical cancerlymph vascular space invasionmachine learning algorithmmultiparametric MRIradiomics

Autor:innen und Institutionen

  • Department of Radiology, Xiangyang Central Hospital, Affiliated Hospital of Hubei University of Arts and Science, Xiangyang, Hubei, 441021, P.R. China.
  • Department of Obstetrics and Gynaecology, Xiangyang Central Hospital, Affiliated Hospital of Hubei University of Arts and Science, Xiangyang, Hubei, 441021, P.R. China.
  • Hubei Provincial Clinical Research Center for Cervical Lesions, Xiangyang, 441021, P.R. China.
  • Institute of Gynecological and Obstetric Disease, Xiangyang Central Hospital, Affiliated Hospital of Hubei University of Arts and Science, Xiangyang, Hubei, 441021, P.R. China.
  • Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, P.R. China.
  • Department of Research Collaboration, R&D Center, Hangzhou Deepwise & League of PHD Technology Co., Ltd, No. 88 Longyuan Road, Cangqian Street, Yuhang District, Hangzhou City, Zhejiang Province, 311101, P.R. China.

ORCID-Profile: Feng Wu

Förderung

  • Hubei Provincial Health Science and Technology Project
  • Hubei Provincial Natural Science Foundation Joint Fund Project
  • Hubei Provincial Department of Education
  • Key Research & Development Program of Hubei Province
  • Hubei Provincial Natural Science Foundation of China
  • Hubei University of Arts and Sciences Affiliated Hospital Xiangyang Central Hospital gynecological and obstetric disease Institute open fund

Zitieren

APA

Deng, L., Zhang, R., Lv, H., Li, F., Li, L., Qin, X., Yang, J., Ai, T., Huang, C., Chen, X., Xing, H., & Wu, F. (2026). Multiparametric MRI radiomics models for preoperative assessment of lymph vascular space invasion status in early-stage cervical cancer: a 2-centre retrospective study. British Journal of Radiology. https://doi.org/10.1093/bjr/tqaf248

Vancouver

Deng L, Zhang R, Lv H, Li F, Li L, Qin X, et al. Multiparametric MRI radiomics models for preoperative assessment of lymph vascular space invasion status in early-stage cervical cancer: a 2-centre retrospective study. British Journal of Radiology. 2026. doi:10.1093/bjr/tqaf248

BibTeX
@article{Deng2026,
  author = {Deng, Lei and Zhang, Rui and Lv, Huabing and Li, Feng and Li, Lin and Qin, Xiaomin and Yang, Jiang and Ai, Tao and Huang, Chencui and Chen, Xingzhi and Xing, Hui and Wu, Feng},
  title = {Multiparametric MRI radiomics models for preoperative assessment of lymph vascular space invasion status in early-stage cervical cancer: a 2-centre retrospective study},
  journal = {British Journal of Radiology},
  year = {2026},
  doi = {10.1093/bjr/tqaf248}
}
Kostenlos starten →