DeepGlioSeg: advanced glioma MRI data segmentation with integrated local-global representation architecture
By integrating CNN- and Transformer-based features in parallel and adaptively emphasizing underrepresented tumor regions, DeepGlioSeg effectively addresses the challenges associated with glioma heterogeneity and imbalanced region distributions. The final pipeline, augmented with TTA and VC post-processing, demonstrates robust segmentation capabilities. The source code for this work is publicly available at https://github.com/smallboy-code/Brain-tumor-segmentation.
Authors
- Yuehui Liao (ORCID: https://orcid.org/0009-0006-0785-4596)
- Guohua Zhao (ORCID: https://orcid.org/0000-0002-8813-8527)
- Yanbin Wang (ORCID: https://orcid.org/0000-0001-5716-3183)
- Ruipeng Li (ORCID: https://orcid.org/0000-0003-2802-5763)
- Yueqi Huang (ORCID: https://orcid.org/0000-0003-2917-1578)
- Xiaofei Ma (ORCID: https://orcid.org/0009-0000-3163-0310)
- Song Chen
Institutions
- Zhejiang Chinese Medical University (CN)
- Third People's Hospital of Hangzhou (CN)
- Hangzhou Seventh Peoples Hospital (CN)
- First Affiliated Hospital of Zhengzhou University (CN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2025-02-04
- DOI
- https://doi.org/10.3389/fonc.2025.1449911
- Citations
- 5
- Primary Topic
- Brain Tumor Detection and Classification
- Type
- article
- Field-Weighted Citation Impact
- 4.21