皮层沟标注的几何到语义球面迁移学习
Geometric-to-Semantic Spherical Transfer Learning for Cortical Sulci Labeling
浏览论文内容
中文总结 AI 辅助
针对皮层沟标注数据稀缺导致过拟合的问题，提出几何到语义球面迁移学习框架，利用大规模无标注数据预训练并注入拓扑先验，平均Dice达0.77，在罕见沟上提升达14.8%。
中文摘要 AI 辅助
在皮层表面上的深度学习面临一个困境：捕捉每个半球超过60个依赖于命名学的沟的复杂拓扑需要高容量模型，然而专家标注的极度稀缺（N=62个受试者）不可避免地导致过拟合。标准的监督方法在这种数据稀缺的情况下难以泛化，尤其是在拓扑模糊性高的可变和小型沟上。为了克服这一限制，我们引入了一个几何到语义球面迁移学习框架。首先，我们利用大规模无标注数据（UK Biobank，约30,000名受试者）通过局部优化策略预训练一个球面编码器。通过仅依赖连续表面特征（曲率和深度），该预训练的相关性通过模型检测局部和罕见拓扑特征（如沟中断）的能力得到确认。然而，下游标注任务引入了提取的沟底（线）作为显式语义输入。为了弥合这一维度域差距（从纯几何到语义）而不引起灾难性遗忘，这些解剖线通过软初始化的拓扑先验注入器集成到预训练的主干网络中。我们的实验表明，该方法优于从头训练的完全监督基线，实现了平均Dice为0.77。关键的是，局部分析显示，自监督几何先验在可变和三级沟上产生了最大的性能提升（高达14.8%），证实了学习皮层形状对于识别其最罕见部分非常有益。
英文摘要
Deep learning on cortical surfaces faces a dilemma: capturing the complex topology of over 60 nomenclature-dependent sulci per hemisphere requires high-capacity models, yet the extreme scarcity of expert annotations ($N=62$ subjects) inevitably causes overfitting. Standard supervised approaches fail to generalize in this data-scarce regime, particularly for variable and small sulci where topological ambiguity is high. To overcome this limitation, we introduce a Geometric-to-Semantic Spherical Transfer Learning framework. First, we leverage massive unlabeled data (UK Biobank, $\approx$30,000 subjects) to pre-train a spherical encoder using a locally-optimized strategy. By relying solely on continuous surface features (curvature and depth), the relevance of this pre-training is confirmed by the model's ability to detect localized and rare topological traits, such as sulcal interruptions. The downstream labeling task, however, introduces extracted sulcal fundi (lines) as an explicit semantic input. To bridge this dimensional domain gap (from purely geometric to semantic) without causing catastrophic forgetting, these anatomical lines are integrated into the pre-trained backbone via a soft-initialized Topological Prior Injector. Our experiments demonstrate that this approach outperforms fully supervised baselines trained from scratch, achieving a mean Dice of 0.77. Crucially, a local analysis reveals that the self-supervised geometric priors yield the largest performance gains on variable and tertiary sulci (up to 14.8%), confirming that learning the cortex shape is highly beneficial for identifying its rarest parts.
发表机构
- Paris-Saclay University（巴黎-萨克雷大学）
- CEA（法国原子能委员会）
- NeuroSpin（NeuroSpin神经影像研究中心）
- Baobab（Baobab实验室）
- LTCI, Télécom Paris, Institut Polytechnique de Paris（巴黎综合理工学院电信学院LTCI实验室）
机构由 AI 辅助整理，请以论文原文为准。
