DINO-Med：用于多模态医学图像分析并应用于肝纤维化分期的统一基于补丁的适应框架
DINO-Med: A Unified Patch-Based Adaptation Framework for Multi-Modal Medical Image Analysis Applied to Liver Fibrosis Staging
浏览论文内容
中文总结 AI 辅助
针对自然图像基础模型难以适应多模态医学影像的问题，提出基于补丁的统一框架DINO-Med，利用DINOv3特征在肝纤维化分期中实现78.4%和75.8%的准确率，显著优于基线。
中文摘要 AI 辅助
将自然图像基础模型（如DINOv3）适应到多模态医学成像中，由于自然彩色图像与多通道医学扫描之间存在显著的领域差距，因此具有挑战性。我们提出了一个统一的、基于补丁的框架，通过无需训练的配准、自动定位和掩膜过滤的补丁提取来处理原始多模态成像。该架构最终形成一种分层策略，将补丁级见解聚合为受试者级诊断。以肝纤维化分期作为案例研究，我们评估了四种补丁级特征表示：手工制作的放射组学特征、学习的ResNet特征、预训练的基础模型SAM-Med2D特征以及冻结的DINOv3特征。为确保受控比较，所有模型均使用相同的轻量级MLP头部，并在刚性配准和可变形配准设置下进行评估。我们的训练协议仅关注轻度纤维化（S1）和肝硬化（S4）类别，使得单一分类器能够同时处理显著纤维化检测和肝硬化分期。通过在CARE 2025肝脏赛道4队列的360名受试者上进行10次随机训练（90%）/测试（10%）划分的评估，我们基于DINOv3的框架显著优于所有基线，在S1上达到最佳分类准确率78.4%，在S4上达到75.8%。
英文摘要
Adapting natural-image foundation models like DINOv3 to multi-modal medical imaging is challenging due to the significant domain gap between natural color images and multi-channel medical scans. We present a unified, patch-based framework that processes raw multimodal imaging through training-free registration, automated localization, and mask-filtered patch extraction. This architecture culminates in a hierarchical strategy that aggregates patch-level insights into subject-level diagnostics. Using liver fibrosis staging as a case study, we evaluate four patch-level feature representations: handcrafted Radiomics features, learned ResNet features, pre-trained foundation model SAM-Med2D features, and frozen DINOv3 features. To ensure a controlled comparison, all models utilize the same lightweight MLP head and are evaluated across both rigid and deformable registration settings. Our training protocol focuses on mild fibrosis (S1) and cirrhosis (S4) classes only, enabling a single classifier to address both substantial fibrosis detection and cirrhosis staging. Evaluated via 10 random train (90%)/ test (10%) splits on 360 subjects from the CARE 2025 Liver Track 4 cohort, our DINOv3-based framework significantly outperforms all baselines, achieving the best classification accuracy of 78.4% for S1 and 75.8% for S4.
发表机构
- University of Nottingham（诺丁汉大学）
机构由 AI 辅助整理，请以论文原文为准。
