Reconstruct neural circuits from existing images
Human tissue preparation, imaging, proofreading and scientific analysis remain part of the project.
SCIENCE UNDER AUTOMATION
AI in Neuroscience: capabilities and evidence
524 million synaptic clefts automatically detected and associated
What has AI demonstrated?
524 million synaptic clefts automatically detected and associated
- Test
- Reconstruction of mouse visual cortex; output scale is not a reconstruction accuracy rate.
- Comparison
- Combined experimental and computational project; no autonomous-neuroscientist baseline.
- System and version
- MICrONS · 2025
- Evidence checked
- 2026-10-21
Human tissue preparation, imaging, proofreading and scientific analysis remain part of the project.
What does the field require?
Reconstruct neural circuits from existing images
- Acquire and align microscopy data
Provisional autonomy mapping for this requirement. Human tissue preparation, imaging, proofreading and scientific analysis remain part of the project.
MICrONS - Segment cells and detect synapses
Provisional autonomy mapping for this requirement. Human tissue preparation, imaging, proofreading and scientific analysis remain part of the project.
MICrONS - Proofread and assess reconstruction errors
Provisional autonomy mapping for this requirement. Human tissue preparation, imaging, proofreading and scientific analysis remain part of the project.
MICrONS
Explain how a circuit causes behaviour
Research tasks
Explain how a circuit causes behaviour
This broader workflow has not been evaluated by the cited demonstration.
Can AI replace the whole workflow?
The results above measure specific tasks. The field assessment also requires completion of the connected workflow, including the requirements listed here. A field-wide replacement percentage has not been established.
Read the assessment method