Deep Learning and Attention Mechanism-based Prediction of Vaginal Invasion in Early-Stage Cervical Cancer
This preliminary study demonstrates promising deep learning performance (3D ResNet-18+Grad-CAM+AIC) for vaginal invasion assessment, despite moderate n; however, a single-center retrospective design limits generalizability.
Authors
- Changyi Guo (ORCID: https://orcid.org/0009-0000-8523-2772)
- Feng Shi (ORCID: https://orcid.org/0000-0003-1522-9943)
- Xinyang Zhu (ORCID: https://orcid.org/0000-0003-0729-8922)
- Qing Xu (ORCID: https://orcid.org/0009-0003-1494-0925)
- Chao He (ORCID: https://orcid.org/0009-0001-6040-9831)
- Yuwei Xia
Institutions
- United Imaging Healthcare (China) (CN)
- Xian Mechanical & Electric Institute (China) (CN)
- Affiliated Hospital of Shaanxi University of Chinese Medicine (CN)
- Shaanxi University of Chinese Medicine (CN)
Publication Details
- Journal
- Current Medical Imaging Formerly Current Medical Imaging Reviews
- Published
- 2025-11-28
- DOI
- https://doi.org/10.2174/0115734056392471251103125700
- Primary Topic
- Endometrial and Cervical Cancer Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00