用语义增强特征匹配解决神经元图像跨模态配准难题
Semantic-Enhanced Feature Matching with Learnable Geometric Verification for Cross-Modal Neuron Registration
- 融合局部几何与上下文语义的混合特征描述子，缩小模态差异
- 引入可学习的几何一致性模块，准确剔除不合理的匹配点
- 两阶段训练策略提升数据效率，适合标注数据少的生物成像场景
在活体双光子成像与离体荧光显微光学切片断层扫描图像间精确配准单个神经元，对神经科学中的结构-功能分析至关重要。该任务因显著的跨模态外观差异、标注数据稀缺及组织严重变形而极具挑战。本文提出一种新型深度学习框架：引入语义增强的混合特征描述子，融合局部特征的几何精度与视觉基础模型DINOV3的上下文鲁棒性，以弥合模态差距；为应对复杂形变，将传统RANSAC替换为可学习的几何一致性置信度模块（Geometric Consistency Confidence Module），该模块作为分类器可识别并剔除物理上不合理的对应关系；采用数据高效的两阶段训练策略——先在合成形变数据上预训练，再在少量真实数据上微调，缓解数据稀缺问题。本框架为高精度生物医学成像配准提供了鲁棒解决方案，支持大规模相关性研究。
原文摘要 · Abstract (English)
Accurately registering in-vivo two-photon and ex-vivo fluorescence micro-optical sectioning tomography images of individual neurons is critical for structure-function analysis in neuroscience. This task is profoundly challenging due to a significant cross-modality appearance gap, the scarcity of annotated data and severe tissue deformations. We propose a novel deep learning framework to address these issues. Our method introduces a semantic-enhanced hybrid feature descriptor, which fuses the geometric precision of local features with the contextual robustness of a vision foundation model DINOV3 to bridge the modality gap. To handle complex deformations, we replace traditional RANSAC with a learnable Geometric Consistency Confidence Module, a novel classifier trained to identify and reject physically implausible correspondences. A data-efficient two-stage training strategy, involving pre-training on synthetically deformed data and fine-tuning on limited real data, overcomes the data scarcity problem. Our framework provides a robust and accurate solution for high-precision registration in challenging biomedical imaging scenarios, enabling large-scale correlative studies.
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。