Carleton University
Deep Learning Scoring of Negative Affect from Mouse Facial Expressions
Abstract
dc:description.abstractAnimal models are often used in Neuroscience to build knowledge that is translatable to human traits and disorders. Emotions have been a topic of major study in Neuroscience since Charles Darwin; contributing to challenges in studying emotions are expensive labor costs and reproducibility issues associated with quantifying emotionality in popular animal models such as mice. We demonstrate a Deep Learning approach for automatically quantifying negative affectivity in mice from facial expressions. Lipopolysaccharide(LPS) was used to create a weakly labeled video dataset for anxiety and depressive-like behaviors in male and female mice with the following treatment groups: Saline, 0.1mg/kg LPS, 0.5mg/kg LPS, 1.0mg/kg LPS. To mitigate the impact of noise associated with weak labels, we utilize an approach inspired by Deep Sets for scoring collections of frames. Our final results indicate the approach can detect facial expression changes between control and LPS-injected animals, as well as between different LPS dosage levels.
Degree
thesis:*- Name thesis:degree_name
- Master of Science (M.Sc.)
- Level thesis:degree_level
- Master's
- Discipline thesis:degree_discipline
- Neuroscience
- Grantor dc:publisher
- Carleton University
- Year dc:date.issued
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Telfer, Andre
Subjects
dc:subject × 3Rights
dc:rights- Statement dc:rights
-
- Copyright © 2023 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
- Language dc:language.iso
- en