Scholarlink

<p>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 <i>DARE-FUSE</i> (<b>D</b>omain <b>A</b>ligned <b>R</b>epresentation with Evidence-guided <b>FUSE</b>), a unified framework for pixel-level segmentation and image-level classification under limited samples and labels. Dual encoders with a feature-interaction bridge learn a shared embedding, and a Domain Alignment Refiner maps it to task-aligned representations for the segmentation and classification branches. For segmentation, U-SEG decodes features and SEGU outputs pixel-wise uncertainty to regularize boundary over/under-segmentation. For classification, CPG produces predictions and multi-scale Grad-CAM++ evidence. A Generative Lesion Removal Prior reconstructs a tumor-free counterpart to yield a difference prior, and FUSE combines this prior with Grad-CAM++ under uncertainty attenuation to guide segmentation and suppress hallucinations. <i>DARE-FUSE</i> achieves stable, leading performance on BraTS segmentation benchmarks and several classification datasets; ablations and label-reduction experiments confirm complementary gains and smooth degradation as pixel annotations decrease. The resulting uncertainty maps and continuous priors support interpretable decision assistance in surgery, radiotherapy contouring, triage, and longitudinal follow-up.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

DARE-FUSE: domain aligned evidence guided learning for joint brain tumor MRI segmentation and classification

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月2日

查看全文
  • Yuqi Liu,
  • Chen Sun,
  • Yuning Niu,
  • Xu Wang,
  • Zehua Yue,
  • Tieqiang Zhang,
  • Jiang Li,
  • Xiudong Guan,
  • Dainan Zhang,
  • Wang Jia

摘要

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 with Evidence-guided FUSE), a unified framework for pixel-level segmentation and image-level classification under limited samples and labels. Dual encoders with a feature-interaction bridge learn a shared embedding, and a Domain Alignment Refiner maps it to task-aligned representations for the segmentation and classification branches. For segmentation, U-SEG decodes features and SEGU outputs pixel-wise uncertainty to regularize boundary over/under-segmentation. For classification, CPG produces predictions and multi-scale Grad-CAM++ evidence. A Generative Lesion Removal Prior reconstructs a tumor-free counterpart to yield a difference prior, and FUSE combines this prior with Grad-CAM++ under uncertainty attenuation to guide segmentation and suppress hallucinations. DARE-FUSE achieves stable, leading performance on BraTS segmentation benchmarks and several classification datasets; ablations and label-reduction experiments confirm complementary gains and smooth degradation as pixel annotations decrease. The resulting uncertainty maps and continuous priors support interpretable decision assistance in surgery, radiotherapy contouring, triage, and longitudinal follow-up.