TOPOLOGICAL LEARNING FOR BRAIN NETWORKS

• 成果类型: Article
• 署名作者: Songdechakraiwut, Tanannun; Chung, Moo K.
• 署名单位: University of Wisconsin System; University of Wisconsin Madison
• 刊物名称: ANNALS OF APPLIED STATISTICS
• ISSN/ISSBN: 1932-6157
• DOI: 10.1214/22-AOAS1633
• 发表日期: 2023
• 页码: 403-433
• 关键词: persistent homology analysis; graph-theoretical analysis; human cerebral-cortex; functional connectivity; working-memory; frechet means; head motion; mri; REGISTRATION; CLASSIFICATION

摘要

This paper proposes a novel topological learning framework that integrates networks of different sizes and topology through persistent homology. Such challenging task is made possible through the introduction of a computationally efficient topological loss. The use of the proposed loss bypasses the intrinsic computational bottleneck associated with matching networks. We validate the method in extensive statistical simulations to assess its effectiveness when discriminating networks with different topology. The method is further demonstrated in a twin brain imaging study where we determine if brain networks are genetically heritable. The challenge here is due to the difficulty of overlaying the topologically different functional brain networks obtained from resting-state functional MRI onto the template structural brain network obtained through diffusion MRI.