Google · Google Research
AI-generated synthetic neurons speed up brain mapping
Compiled by KHAO Editorial — aggregated from 1 outlet. See llms.txt for citation guidance.
★ Tier-1 Source
Michał Januszewski, Research Scientist, and Franz Rieger, Student Researcher, Google Research.
Key facts
- Michał Januszewski, Research Scientist, and Franz Rieger, Student Researcher, Google Research
- Using a PATHFINDER model trained with 10% simulated data from MoGen reduced the error rate on reconstructing the reserved mouse axons by 4.4%, driven primarily by a reduction in the merge error rate
- The fruit fly brain map, with 166,000 neurons, represents years of work by AI-enabled computers and human experts
- Their new paper “ MoGen: Detailed neuronal morphology generation via point cloud flow matching ”, to be presented at ICLR 2026, uses synthetic neural shapes to improve AI reconstruction models
Summary
Generating synthetic neuron geometries helps AI learn to better classify neurons by their shape, speeding up future brain map reconstructions. Using computers to create full wiring maps of complex brains is enabling a new era of neuroscience. But reconstructing the entire brains of mammals, and certainly of humans, remains far out of reach. Google Research is developing AI techniques to tackle larger brain mapping projects by speeding up the identification, classification, and visualization of neurons.