WhACC: Whisker Automatic Contact Classifier with Expert Human-Level Performance

TL;DR

WhACC is a machine learning tool that automates the detection of touch events in rodent whisker videos, achieving human-level accuracy and significantly reducing manual curation time.

Contribution

This paper introduces WhACC, a novel Python package that combines ResNet50V2 and LightGBM to identify whisker touch events with expert-level performance, enabling efficient large-scale data annotation.

Findings

Achieves 99.5% agreement with human experts.

Reduces manual curation time from 333 hours to 6 hours for 100 million frames.

Validated on electrophysiology data across multiple recordings.

Abstract

The rodent vibrissal system is pivotal in advancing neuroscience research, particularly for studies of cortical plasticity, learning, decision-making, sensory encoding, and sensorimotor integration. Despite the advantages, curating touch events is labor intensive and often requires >3 hours per million video frames, even after leveraging automated tools like the Janelia Whisker Tracker. We address this limitation by introducing Whisker Automatic Contact Classifier (WhACC), a python package designed to identify touch periods from high-speed videos of head-fixed behaving rodents with human-level performance. WhACC leverages ResNet50V2 for feature extraction, combined with LightGBM for Classification. Performance is assessed against three expert human curators on over one million frames. Pairwise touch classification agreement on 99.5% of video frames, equal to between-human agreement. Finally, we offer a custom retraining interface to allow model customization on a small subset of data, which was validated on four million frames across 16 single-unit electrophysiology recordings. Including this retraining step, we reduce human hours required to curate a 100 million frame dataset from ~333 hours to ~6 hours.