CyberNeuro: A Privacy-Preserving Agentic Workbench for Cohort-Scale Neuroimage and Clinical Data Analysis

2026-07-30

AI Summary

This work addresses the challenges of cumbersome, manual, and privacy-sensitive workflows in neuroimaging and clinical data analysis by proposing an automated platform based on a multi-agent architecture. The platform uniquely integrates a localized large language model (WandaMind) with a four-agent collaborative framework—comprising Planner, Validator, Dispatcher, and Reporter—to enable end-to-end, natural language–driven analytical pipelines. It incorporates human-in-the-loop quality control and a secure MCP communication bridge to ensure clinical-grade privacy compliance. Evaluated on the NeuroBench benchmark, the approach improves out-of-domain accuracy from 40% to 69%, substantially reduces token consumption per task, and is released as an open-source suite of production-ready modules.

Abstract

Despite tremendous success in neuroimaging methodology, making large-scale, high-dimensional datasets ready for AI/ML applications remains a critical operational bottleneck. Conventional workflows require extensive manual effort across metadata curation, pipeline execution, post-processing quality control, and data management, a burden that disproportionately excludes laboratories with limited manpower and computational infrastructure. To address this real-world barrier, there is an urgent need for scalable, cost-effective computational platforms that democratize advanced neuroimaging analytics and accelerate discoveries in mental health and clinical translation. Capitalizing on multi-agent LLM breakthroughs, we introduce CyberNeuro, an agentic workbench with a tailored local LLM-model ('WandaMind') for automated neuroimaging and health-data analysis. Driven by four dedicated agents (Planner, Validator, Dispatcher, and Reporter) communicating via a secure MCP bridge and a pinned execution layer, CyberNeuro enables researchers to execute complex workflows using natural language while maintaining clinical-grade data privacy. On the public NeuroBench suite, CyberNeuro increases held-out domain accuracy from 40% to 69% over the baseline model. Beyond automated metrics, the platform integrates a human-in-the-loop verification panel to ensure rigorous biomedical quality control. Across the same end-to-end 10-batch cohort workflow suite, the local WandaMind configuration completed all tasks with an estimated aggregate token count of about 10.6% using WandaMind and 61.7% using cloud providers of token usage, compared to Neuroclaw, respectively. The platform and its production-ready modules are available at https://wanda-cyberbench.com.

Problem

• neuroimaging
• data preprocessing bottleneck
• AI/ML readiness
• resource-limited labs
• clinical data analysis

Innovation

• agentic workbench
• privacy-preserving AI
• neuroimaging automation
• local LLM
• multi-agent system