Gaining Explainability from a CNN for Stereotype Detection Based on Mice Stopping Behavior
This work addresses the need for explainable AI in animal behavior analysis to better understand neurodevelopmental disorders, but it is incremental as it applies an existing CNN method to new mouse tracking data.
The researchers tackled the problem of identifying age and sex traits in mice by analyzing their stopping behavior using a shallow CNN on 2D histograms of stop positions, achieving over 90% accuracy for females and 62.5% for males.
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.