Gaining Explainability from a CNN for Stereotype Detection Based on Mice Stopping Behavior

TL;DR

This study employs a CNN to classify mice by age and sex based on their stopping behavior patterns, achieving high accuracy for females and providing insights into behavioral differences through model explainability.

Contribution

It introduces a CNN-based method for analyzing mouse behavior patterns to infer age and sex, with an emphasis on explainability of the model's decisions.

Findings

Female mice show more recognizable behavioral patterns with over 90% accuracy.

Males have less distinguishable patterns, with 62.5% accuracy.

Model explainability reveals sex-specific exploration regions in the cage.

Abstract

Understanding the behavior of laboratory animals is a key to find answers about diseases and neurodevelopmental disorders that also affects humans. One behavior of interest is the stopping, as it correlates with exploration, feeding and sleeping habits of individuals. To improve comprehension of animal's behavior, we focus on identifying trait revealing age/sex of mice through the series of stopping spots of each individual. We track 4 mice using LiveMouseTracker (LMT) system during 3 days. Then, we build a stack of 2D histograms of the stop positions. This stack of histograms passes through a shallow CNN architecture to classify mice in terms of age and sex. We observe that female mice show more recognizable behavioral patterns, reaching a classification accuracy of more than 90%, while males, which do not present as many distinguishable patterns, reach an accuracy of 62.5%. To gain explainability from the model, we look at the activation function of the convolutional layers and found that some regions of the cage are preferentially explored by females. Males, especially juveniles, present behavior patterns that oscillate between juvenile female and adult male.