arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.20970cs.CV
收藏

GraPHFormer:一种多模态图持久同调变换器,用于神经科学形态学分析

GraPHFormer: A Multimodal Graph Persistent Homology Transformer for the Analysis of Neuroscience Morphologies

Hamad Bin Khalifa University(哈马德·本·卡西姆大学);University of Turin(都灵大学);BESE, King Abdullah University of Science and Technology(贝赛,国王阿卜杜勒阿齐兹大学科学与技术学院);University of Wollongong(沃林根大学);Neuroscience Institute Cavalieri Ottolenghi(卡瓦利埃-奥托伦奇神经科学研究所);Université Grenoble-Alpes(格勒诺布尔阿尔卑斯大学)

Uzair Shah, Marco Agus, Mahmoud Gamal, Mahmood Alzubaidi, Corrado Cali, Pierre J. Magistretti, Abdesselam Bouzerdoum, Mowafa Househ

AI总结:

GraPHFormer通过CLIP式对比学习统一拓扑和图结构分析,利用持久图像编码和树状LSTM编码器,实现对神经形态的高精度识别与分类,优于传统方法。

摘要:

GraPHFormer通过CLIP式对比学习统一拓扑和图结构分析,利用持久图像编码和树状LSTM编码器,实现对神经形态的高精度识别与分类,优于传统方法。

英文摘要:

Neuronal morphology encodes critical information about circuit function, development, and disease, yet current methods analyze topology or graph structure in isolation. We introduce GraPHFormer, a multimodal architecture that unifies these complementary views through CLIP-style contrastive learning. Our vision branch processes a novel three-channel persistence image encoding unweighted, persistence-weighted, and radius-weighted topological densities via DINOv2-ViT-S. In parallel, a TreeLSTM encoder captures geometric and radial attributes from skeleton graphs. Both project to a shared embedding space trained with symmetric InfoNCE loss, augmented by persistence-space transformations that preserve topological semantics. Evaluated on six benchmarks (BIL-6, ACT-4, JML-4, N7, M1-Cell, M1-REG) spanning self-supervised and supervised settings, GraPHFormer achieves state-of-the-art performance on five benchmarks, significantly outperforming topology-only, graph-only, and morphometrics baselines. We demonstrate practical utility by discriminating glial morphologies across cortical regions and species, and detecting signatures of developmental and degenerative processes. Code: https://github.com/Uzshah/GraPHFormer

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑