Self-supervised learning using Geometric Assessment-driven Topological Smoothing (GATS) for neuron tracing and Active Learning Environment (NeuroTrALE)
Nina Shamsi, Alec Xu, Michael Snyder, David Chavez, Aaron Rodriguez, Benjamin Roop, Adam Michaleas, Webster Guan, Kwanghun Chung, Laura Brattain, Lars Gjesteby · FENS Forum 2024
Automated axon tracing via fully supervised learning requires annotated 3D brain imagery, which necessitates expertise and labor to produce. Reducing the amount of annotated training data needed for supervised algorithms for axon tracing would expedite critical brain research. In this work, we developed and integrated a self-supervised learning (SSL) algorithm trained on large unannotated data volumes into NeuroTrALE (pictured), a custom AI-driven pipeline for automatic annotation and visualization of 3D brain imagery. Our light sheet microscopy dataset consisted of stained Parvalbumin positiv