DARE-FUSE: domain aligned evidence guided learning for joint brain tumor MRI segmentation and classification
- Published on 02/25/2026
- Reading time: 13 min.
Liu Yuqi 1, Sun Chen 1, Niu Yuning 2, Wang Xu 1, Yue Zehua 1, Zhang Tieqiang 1, Li Jiang 1, Guan Xiudong 1,3, Zhang Dainan 1,3, Jia Wang 1,3
1 https://ror.org/013xs5b60 Department of Neurosurgery Beijing Tiantan Hospital, Capital Medical University, Beijing 100070 Beijing China
2 https://ror.org/013xs5b60 Tongren Eye Center Beijing Tongren Hospital, Capital Medical University, Beijing 100005 Beijing China
3 https://ror.org/003regz62 Beijing Neurosurgical Institute Beijing 100070 Beijing China
Abstract
Brain tumor MRI segmentation and classification are essential for preoperative boundary assessment, lesion burden quantification, postoperative response monitoring, and radiotherapy planning, yet edema overlap, sequence heterogeneity, and artifacts often blur lesion margins. Together with the high cost of pixel-level annotation, these factors limit robust, cross-institution deployment. We propose DARE-FUSE (Domain Aligned Representation...
To continue reading this article in Full-Text...
Peer-Reviewed Journals A-Z
Search | Advanced search
Get the latest news in Neurology
Receive our newsletter to stay up to date with the latest news in Neurology
