EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prediction Model of Lymph Node Metastasis in Cervical Cancer Based on MRI Habitat Radiomics

Mei Wang, Yu Cao iD, Weiwei Zhang, Yun Liang, Jizhao Liu iD, Junqiang Lei iD

Cancers · 31.12.2025 · 18 (1) · 152

DOI: 10.3390/cancers18010152 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancers, online erschienen am 31.12.2025. Verfasst von Mei Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: The First Clinical Medical College, Lanzhou University, Lanzhou 730000, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Gansu Province, Youth Doctoral Support Project of Gansu Provincial Department of Education, Lanzhou Science and Technology Plan Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Radiomics provides a non-invasive approach for predicting lymph node metastasis (LNM) in cervical cancer, but conventional whole-tumor analysis often overlooks intratumoral heterogeneity.

Methods

This study aimed to develop and validate an MRI-based habitat radiomics model for preoperative prediction of pelvic LNM in early-stage cervical cancer. Tumor regions were delineated on diffusion-weighted imaging, and intratumoral habitats were generated using unsupervised K-means clustering. Radiomic features were extracted from whole tumors and habitat subregions, combined with clinical variables, and selected using correlation analysis and LASSO regression. Four models—clinical, conventional radiomics, habitat radiomics, and combined—were constructed and evaluated.

Results

In internal validation, the combined model achieved the best performance (AUC = 0.895), outperforming the clinical (AUC = 0.799), conventional radiomics (AUC = 0.611), and habitat models (AUC = 0.872). Calibration and decision curve analyses demonstrated good agreement and clinical utility.

Conclusions

Integrating habitat-based radiomics with clinical factors significantly improves the preoperative prediction of LNM, providing a robust and clinically applicable tool for individualized management of cervical cancer patients.

Schlagwörter

Stichwörter der Autor:innen

cervical cancerfeature engineeringhabitat radiomicsmachine learningradiomics

Autor:innen und Institutionen

  • The First Clinical Medical College, Lanzhou University, Lanzhou 730000, China.
  • Department of Obstetrics and Gynecology, The First Hospital of Lanzhou University, Lanzhou 730000, China.
  • Gansu Provincial Clinical Research Center for Gynecological Oncology, Lanzhou 730000, China.
  • The First Clinical Medical College of Gansu University of Traditional Chinese Medicine, Lanzhou 730000, China.
  • School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China.
  • Gansu Province Clinical Research Renter for Radiology Imaging, The First Hospital of Lanzhou University, Lanzhou 730000, China.

ORCID-Profile: Yu Cao, Jizhao Liu, Junqiang Lei

Förderung

  • Natural Science Foundation of Gansu Province
  • Youth Doctoral Support Project of Gansu Provincial Department of Education
  • Lanzhou Science and Technology Plan Project

Zitieren

APA

Wang, M., Cao, Y., Zhang, W., Liang, Y., Liu, J., & Lei, J. (2025). Prediction Model of Lymph Node Metastasis in Cervical Cancer Based on MRI Habitat Radiomics. Cancers, 18(1), 152. https://doi.org/10.3390/cancers18010152

Vancouver

Wang M, Cao Y, Zhang W, Liang Y, Liu J, Lei J. Prediction Model of Lymph Node Metastasis in Cervical Cancer Based on MRI Habitat Radiomics. Cancers. 2025;18(1):152. doi:10.3390/cancers18010152

BibTeX
@article{Wang2025,
  author = {Wang, Mei and Cao, Yu and Zhang, Weiwei and Liang, Yun and Liu, Jizhao and Lei, Junqiang},
  title = {Prediction Model of Lymph Node Metastasis in Cervical Cancer Based on MRI Habitat Radiomics},
  journal = {Cancers},
  year = {2025},
  volume = {18},
  number = {1},
  pages = {152},
  doi = {10.3390/cancers18010152}
}
Kostenlos starten →