Scholarlink

<p>Accurate glioma segmentation is critical for clinical diagnosis and treatment planning, yet remains challenging due to infiltrative tumor growth, heterogeneous imaging protocols, and scarcity of expert annotations. We present MAGPIE, a self-supervised learning framework that combines masked autoencoding, contrastive learning, and sparse mixture of experts to enable accurate glioma segmentation with minimal labeled data. By pretraining on 43,505 unlabeled multi-modal brain MRI scans, MAGPIE learns generalizable representations through a channel-agnostic architecture that handles varying modality configurations without protocol-specific preprocessing. The sparse MoE mechanism with top-2 routing allows specialized expert networks to emerge for different glioma subregions, while deformable attention mechanisms capture infiltrative margins and multi-scale features. Fine-tuning on only 20 labeled cases achieves 60.87% Dice score on BraTS21, a 2.59% absolute improvement over training from scratch, with 70.32% on out-of-distribution data demonstrating robust cross-domain generalization. These results reduce annotation requirements by 95% compared to typical supervised methods, directly addressing the data scarcity bottleneck in rare tumor subtypes and enabling deployment across heterogeneous clinical imaging systems.</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

Masked autoencoding, generalizable pretraining, and integrated experts for enhanced glioma segmentation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月17日

查看全文
  • Mingchen Xie,
  • Qun Xiao,
  • Haitao Wu,
  • Yahui Zhang,
  • Hao Han,
  • Xun Xie,
  • Wenyue Zhang,
  • Jianhua Cheng,
  • Jian Xu

摘要

Accurate glioma segmentation is critical for clinical diagnosis and treatment planning, yet remains challenging due to infiltrative tumor growth, heterogeneous imaging protocols, and scarcity of expert annotations. We present MAGPIE, a self-supervised learning framework that combines masked autoencoding, contrastive learning, and sparse mixture of experts to enable accurate glioma segmentation with minimal labeled data. By pretraining on 43,505 unlabeled multi-modal brain MRI scans, MAGPIE learns generalizable representations through a channel-agnostic architecture that handles varying modality configurations without protocol-specific preprocessing. The sparse MoE mechanism with top-2 routing allows specialized expert networks to emerge for different glioma subregions, while deformable attention mechanisms capture infiltrative margins and multi-scale features. Fine-tuning on only 20 labeled cases achieves 60.87% Dice score on BraTS21, a 2.59% absolute improvement over training from scratch, with 70.32% on out-of-distribution data demonstrating robust cross-domain generalization. These results reduce annotation requirements by 95% compared to typical supervised methods, directly addressing the data scarcity bottleneck in rare tumor subtypes and enabling deployment across heterogeneous clinical imaging systems.