V-132 | STORM – Simple Tracker for Object Recognition Memory: Automated behavioral analysis using neural networks

Tools Development and Open Source Neuroscience
Author: Santiago D’hers | Email: sdhers@fbmc.fcen.uba.ar

Santiago D’hers^1°, Mariana Feld^1°

^1° Instituto de Fisiología, Biología Molecular y Neurociencias (IFIBYNE), UBA-CONICET.

Manual scoring of animal behavior in research, particularly in studies involving object recognition memory, is not only time-consuming but also susceptible to operator bias. To address these challenges, we have developed STORM (Simple Tracker for Object Recognition Memory), a novel automated behavioral analysis method using Python-based neural networks. STORM is designed to learn from the labeling criteria of one or more experimenters, capturing the different aspects of expert opinion and reducing subjective bias in subsequent scoring procedures.
This tool provides a robust methodology for assessing recognition memory in rodents by accurately quantifying exploration times for familiar and novel objects. By optimizing the analysis process, STORM significantly enhances the reliability and efficiency of behavioral research.
Using STORM in a protocol involving two 15′ training sessions (45′ apart) with different pairs of objects, we were able to describe different exploration dynamics between old and new familiar objects in the presence of a new one. These results challenge the way episodic memory is traditionally studied in mice, revealing a temporal window in which the recall of one object can be affected by the presentation of another.
Furthermore, it should be readily applicable to other experimental designs that rely on quantifying exploration in mice (such as Social Preference and Object Pattern Separation, among others).