A multicentre validation study of 3D V-net-based segmentation model for adrenal glands: cross-protocol generalization from abdominal CT to chest CT
The study developed a deep learning model using 3D V-Net for the segmentation of adrenal glands on CT images, achieving good performance of normal and abnormal glands in validation cohorts with different scanning protocols and from multiple institutions, demonstrating its potential as a "flagging" system aiding diagnosis.
Authors
- Yaofeng Zhang (ORCID: https://orcid.org/0000-0003-0738-2163)
- Yuanchong Chen (ORCID: https://orcid.org/0000-0002-2562-7286)
- He Wang (ORCID: https://orcid.org/0000-0001-9854-955X)
- Xiaoying Wang (ORCID: https://orcid.org/0000-0001-9822-961X)
- Kexin Wang (ORCID: https://orcid.org/0000-0001-9184-3967)
- Jiangtao Liu (ORCID: https://orcid.org/0000-0001-5134-3079)
- Xiaodong Zhang (ORCID: https://orcid.org/0000-0002-4386-8163)
Institutions
- Peking University (CN)
- BOE Technology Group (China) (CN)
- Peking University First Hospital (CN)
Publication Details
- Journal
- British Journal of Radiology
- Published
- 2025-12-02
- DOI
- https://doi.org/10.1093/bjr/tqaf294
- Primary Topic
- Adrenal and Paraganglionic Tumors
- Type
- article
- Field-Weighted Citation Impact
- 0.00