Automated gross tumour volume delineation on T2-weighted magnetic resonance imaging coupled with radiomics for predicting cervical cancer recurrence
The 3D MedNext-7L model outperforms nnUNetV2 in GTV delineation on pretreatment T2-weighted MR images. Rapid manual modifications combined with radiomics and machine learning techniques can effectively predict recurrence risk. The automatic delineation results show promise for direct application in recurrence prediction, indicating a feasible pathway towards a fully automated predictive system.
Authors
- Mengjiao Cai (ORCID: https://orcid.org/0000-0002-7655-9092)
- Jinlu Ma
- Che Wang (ORCID: https://orcid.org/0000-0001-5333-6796)
- Lecheng Jia (ORCID: https://orcid.org/0000-0001-8157-4556)
- Jie Chen (ORCID: https://orcid.org/0000-0002-8196-0454)
- Jue Pan (ORCID: https://orcid.org/0000-0001-5429-0291)
- Zijie Mo
- Jinyu Qiao
- J. Yang
- Silin Liu
- Yu Liang
- Jin Wang
Institutions
- First Affiliated Hospital of Xi'an Jiaotong University (CN)
Publication Details
- Journal
- European journal of medical research
- Published
- 2026-02-18
- DOI
- https://doi.org/10.1186/s40001-025-03777-9
- Primary Topic
- Endometrial and Cervical Cancer Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00