Predicting isocitrate dehydrogenase status in glioma using hierarchical attention-based deep 3D multiple instance learning
The proposed HAB-MIL achieved IDH classification based on conventional preoperative MRI images, eliminating the need for pixel-level annotations and significantly reducing the annotation burden for doctors.
Authors
- Yu Shang (ORCID: https://orcid.org/0000-0003-1100-8780)
- Fan Wang (ORCID: https://orcid.org/0000-0001-5932-7567)
- Yanhui Sun (ORCID: https://orcid.org/0000-0001-5654-403X)
- Qing Xie (ORCID: https://orcid.org/0000-0002-2582-8803)
- Chen Niu (ORCID: https://orcid.org/0000-0001-8251-4336)
- Haifeng Wang (ORCID: https://orcid.org/0000-0001-5381-1657)
- Bin Chen (ORCID: https://orcid.org/0000-0002-8167-9101)
- Ming Zhang (ORCID: https://orcid.org/0000-0003-3827-8801)
- Rong Wei (ORCID: https://orcid.org/0000-0003-2846-4061)
- Y. F. Liang (ORCID: https://orcid.org/0009-0004-4540-8330)
Institutions
- First Affiliated Hospital of Xi'an Jiaotong University (CN)
- Affiliated Hangzhou First People's Hospital, Westlake University, School of Medicine (CN)
- Xi'an Jiaotong University (CN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2025-12-18
- DOI
- https://doi.org/10.3389/fonc.2025.1665690
- Primary Topic
- Glioma Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00