用渐进式方法让DINOv3模型适应3D医学图像分割，提升精度。
DINO-Med3D: Bridging Dimension and Domain Gaps in Volumetric Segmentation via Progressive Adaptation
- 分两阶段：先用伪3D上下文和代理任务对齐维度与领域差异
- 在冻结主干上加轻量3D适配器，增强切片间连续性
- 增设细节恢复分支，保留边界高频信息，适合医学图像分割
尽管DINOv3在自然图像中展现出出色的语义区分能力，但其直接应用于体积分割时受限于固有的维度与领域差异。为此，我们提出DINO-Med3D，一种两阶段渐进式框架，将预训练的DINOv3编码器适配至3D医学任务。第一阶段通过引入多切片嵌入模块以融合伪3D上下文，并利用分割代理任务，将自然图像学习到的表征迁移到医学领域。随后，在冻结主干网络中加入轻量级3D适配器，强化跨切片的全局一致性。最后，为补偿嵌入过程中的空间信息损失，设计并行细节恢复流，显式保留高频率边界特征。在五个公开数据集上的大量实验表明，该方法成功实现DINOv3向医学领域的迁移，并显著优于现有最先进基线。
原文摘要 · Abstract (English)
Although DINOv3 has demonstrated remarkable semantic discrimination in natural imagery, its direct application to volumetric medical segmentation is hindered by inherent dimension and domain disparities. To resolve these issues, we propose DINO-Med3D, a two-stage progressive framework that repurpose the pre-trained DINOv3 encoder for 3D medical tasks. In the first stage, we mitigate the dimension gap by introducing a multi-slice embedding module that incorporates pseudo-3D context, while simultaneously employing a segmentation proxy task to adapt representations learned from natural scenes to the medical domain. Subsequently, we further enhance volumetric understanding by adding lightweight 3D adapters into the frozen backbone to enforce global inter-slice continuity. Finally, to compensate for the spatial information loss inherent in the embedding process, we design a parallel detail recovery stream to explicitly preserve high-frequency boundary cues. Extensive experiments on five public datasets demonstrate that our approach successfully adapts DINOv3 to the medical domain and significantly outperforms state-of-the-art baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。