PrimateX: a unified multi-agentic framework for standardized MRI analysis across primate species
Year: 2026
Type: preprint
Abstract: Standardized preprocessing has transformed human neuroimaging into a reproducible, population-scale enterprise, yet equivalent computational frameworks for non-human primates (NHPs) remain absent, forcing continued reliance on fragmented, labor-intensive workflows. Here we introduce PrimateX, a multi-agentic computational framework in which LLM-guided orchestration dynamically routes structural MRI scans through species-tailored, topology-preserving workflows, extracting cortical surfaces directly from raw volumes with full provenance tracking across marmosets, macaques, chimpanzees, and humans. Validated on 1,221 NHP and 1,113 human scans, PrimateX outperformed existing NHP pipelines in segmentation and surface reconstruction while matching dedicated human tools such as FSL in their native domain. Through MRI-style data augmentation, the framework achieved robust zero-shot generalization to 8 unseen primate species across 31 cohorts from 19 global sites (n = 157). Critically, the routing architecture and closed-loop quality-control mechanisms, demonstrated through diverse downstream neuroimaging analyses and cross-species research, establish PrimateX as a widely-applicable computational paradigm. PrimateX is available at https://primatex.pku.edu.cn.
Source: Research Square
Authors: Zheng Wang, Xiaohui Yao, Yichun Huang, Kailong Cui, Yunfeng Wang, Junlong Huang, Hong Liang, Haoran Zhai, Chengtao Cai, Shiqi Yu, Yiheng Hu, Jiahao Huang, Hongyi Li, Ronghui Ju, Chenyuan Bian, Jing Liu, Yuanjing Feng, Sze Chai Kwok, William Hopkins, Chet Sherwood, Junichi Hata, Daisuke Yoshimaru, Hideyuki Okano, Ken Nakae, Stefan Everling, David Leopold, Ching-Yu Cheng, Huazhu Fu, Alejandro Frangi, Ravi Menon, Shan Cong
Institutions: Peking University, Harbin Engineering University, Hainan University, Zhejiang University of Technology, Liaoning Provincial People's Hospital, Affiliated Hospital of Qingdao University, Peking University First Hospital, Duke Kunshan University, The University of Texas MD Anderson Cancer Center, George Washington University, RIKEN Center for Brain Science, Keio University, University of Fukui, Western University, National Institutes of Health, National University of Singapore, Agency for Science, Technology and Research, University of Manchester
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7235560100
