AI assistant makes neuroimaging data analysis easier with natural language
The AI Neuroscientist: An Interactive Agentic Interface for Neuroimaging Analysis
Artificial Intelligence
Summary
Analyzing brain imaging data usually needs special coding skills that many researchers don’t have. The authors created the AI Neuroscientist, a smart helper that lets users ask questions about their brain data and set analysis options using plain English. This system works with a tool for brain imaging and shows results visually, making it easier for people to explore small sets of brain data without complex programming. They tested it with a type of brain scan called fNIRS and compared it against other AI tools.
What this means in practice
- •For clinical neuroimaging teams: Interactively assess and control quality of clinical fNIRS data with natural language commands.
- •For brain-computer interface developers: Rapidly explore and model small-scale brain activity datasets without deep coding expertise.
Authors
Aakash Patel, Panos Ketonis, Shreya Saxena, Smita Krishnaswamy, David van Dijk
Abstract
Analyzing neuroimaging data requires specialized coding and statistical expertise, which limits accessibility for researchers without computational backgrounds. We present the AI Neuroscientist, a language agent for interactive data exploration. The system integrates a large language model (LLM) with a neuroimaging toolset to perform quality control, modeling, and visualization. This allows researchers to query data quality and specify analysis parameters directly in natural language, providing a transparent and interactive alternative to conventional scripted pipelines for small-scale data exploration. We demonstrate these capabilities using functional near-infrared spectroscopy (fNIRS) data, and evaluate the agent on a custom fNIRS benchmarking suite against general-purpose LLM agents with code sandboxes. Future extensions will generalize the architecture to additional modalities, including functional magnetic resonance imaging (fMRI) data, and expand the benchmarking suite to additional fNIRS tasks.