BrainTumNet: multi-task deep learning framework for brain tumor segmentation and classification using adaptive masked transformers
The proposed BrainTumNet model achieves high-precision diagnosis of brain tumor segmentation and classification through a multi-task learning strategy. Experimental results demonstrate the model's strong potential for clinical application, providing objective and reliable auxiliary information for preoperative assessment and treatment decision-making in brain tumor cases.
Authors
- Zicheng Xiong (ORCID: https://orcid.org/0009-0006-3014-5667)
- Xu-Jun Shu
- Jun Qiu (ORCID: https://orcid.org/0000-0003-2933-0727)
- Shengbo Chen (ORCID: https://orcid.org/0000-0002-9026-8128)
- Chengqing Liu (ORCID: https://orcid.org/0000-0001-9916-4627)
- Shang Li (ORCID: https://orcid.org/0000-0001-9964-8330)
- Jing Ye (ORCID: https://orcid.org/0000-0002-7832-5003)
- Hong Rao
- Quan Liang (ORCID: https://orcid.org/0000-0002-3016-225X)
- Cheng Lv (ORCID: https://orcid.org/0009-0004-8728-3628)
- Jing Niu (ORCID: https://orcid.org/0009-0009-2048-662X)
Institutions
- Nanchang University (CN)
- Nanjing General Hospital of Nanjing Military Command (CN)
- Henan University of Engineering (CN)
- Jinling Institute of Technology (CN)
- Nanjing Medical University (CN)
- Nanjing University (CN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2025-05-20
- DOI
- https://doi.org/10.3389/fonc.2025.1585891
- Citations
- 6
- Primary Topic
- Brain Tumor Detection and Classification
- Type
- article
- Field-Weighted Citation Impact
- 5.05