Predicting isocitrate dehydrogenase status in glioma using hierarchical attention-based deep 3D multiple instance learning
Frontiers in Oncology · 18.12.2025 · 15
DOI: 10.3389/fonc.2025.1665690 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Oncology, online erschienen am 18.12.2025. Verfasst von Qinqin Xie und 9 weiteren Autor:innen. Beteiligte Einrichtung: PET-CT Center, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Industry Innovation Chain of Shaanxi.
Abstract (Originalsprache)
Background
According to the 2021 WHO classification of tumors of the central nervous system, isocitrate dehydrogenase (IDH) status serve an independent prognostic biomarker and is closely associated with tumor diagnosis and treatment response. At present, the determination of IDH status still relies on invasive surgical procedures.
Method
A total of 345 patients with pathologically confirmed gliomas diagnosed at the First Affiliated Hospital of Xi’an Jiaotong University between October 2019 and October 2024 were retrospectively included, comprising 148 (42.9%) IDH-wild and 197 (57.1%) IDH-mutant. An additional 495 glioma patients were obtained from the public TCIA dataset. Patients were randomly split into training, validation, and test cohorts 6:2:2. A Hierarchical Attention-Based Multiple Instance Learning (HAB-MIL) framework was developed, integrating auxiliary positional encoding into feature maps to capture spatially specific information and generate refined 3D lesion representations. Model performance was evaluated using five-fold cross-validation, with receiver operating characteristic (ROC) curves, area under the curve (AUC), sensitivity, and specificity as assessment metrics.
Result
HAB-MIL achieved competitive performance, with AUCs of 0.917 and 0.892 on the glioma datasets from TCIA and the First Affiliated Hospital of Xi’an Jiaotong University. Additionally, our work achieves results that are comparable to the state-of-the-art methods in TCIA dataset and demonstrates that multiple instance learning has great potential for IDH prediction.
Conclusion
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- PET-CT Center, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
- Department of Network Information, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
- School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, China.
- Data Center, Hangzhou First People's Hospital, Hangzhou, China.
Förderung
- Key Industry Innovation Chain of Shaanxi
Zitieren
APA
Xie, Q., Sun, Y., Liang, Y., Shang, Y., Wang, H., Wang, F., Wei, R., Chen, B., Zhang, M., & Niu, C. (2025). Predicting isocitrate dehydrogenase status in glioma using hierarchical attention-based deep 3D multiple instance learning. Frontiers in Oncology, 15. https://doi.org/10.3389/fonc.2025.1665690
Vancouver
Xie Q, Sun Y, Liang Y, Shang Y, Wang H, Wang F, et al. Predicting isocitrate dehydrogenase status in glioma using hierarchical attention-based deep 3D multiple instance learning. Frontiers in Oncology. 2025;15. doi:10.3389/fonc.2025.1665690
BibTeX
@article{Xie2025,
author = {Xie, Qinqin and Sun, Yongheng and Liang, Yuxia and Shang, Yu and Wang, Haifeng and Wang, Fan and Wei, Rong and Chen, Bin and Zhang, Ming and Niu, Chen},
title = {Predicting isocitrate dehydrogenase status in glioma using hierarchical attention-based deep 3D multiple instance learning},
journal = {Frontiers in Oncology},
year = {2025},
volume = {15},
doi = {10.3389/fonc.2025.1665690}
}
EUVIMED