The neurons in our brain that underlie thought connect to each other using tiny branch-like structures on their surfaces known as dendritic spines. Now scientists at Columbia’s Zuckerman Institute and their colleagues have come up with powerful new software driven by artificial intelligence that can automatically map these dendritic spines in pictures of neurons, a tool the researchers are making freely available.

A paper detailing the work, “A deep learning pipeline for accurate and automated restoration, segmentation, and quantification of dendritic spines,” is published in Cell Reports Methods.

“Dendritic spines are usually the first site that are implicated in neurodegenerative diseases such as Alzheimer’s and Parkinson’s,” said Sergio Bernal-Garcia, a graduate student in the lab of Franck Polleux, Ph.D., and lead author of the paper. “So understanding more about them is vitally important.”