DeepLabCut-Based Mouse Exploratory Behavior Metrics for Aging and Periodontitis Models

A dataset likely contains 36 automatically quantified indicators of mouse exploratory behavior across three categories: sniffing frequency, exploration duration, and novelty preference. The data was generated by Cenfei Zhou using a custom DeepLabCut-based object recognition system and was last updated on April 21, 2026. It was used to assess cognitive function in natural aging and elderly periodontitis mouse models.

Use Cases

• Training machine learning models for fine-grained rodent behavior classification based on 5 tracked body landmarks.
• Comparing cognitive performance between aged and young mice using multidimensional behavioral metrics like sniffing frequency and exploration duration.
• Investigating the link between inflammation (e.g., periodontitis) and cognitive decline through quantified novelty preference indices.
• Benchmarking automated tracking systems against traditional visual inspection methods in novel object and object location recognition paradigms.

Strengths

• Quantifies 36 distinct behavioral indicators across three categories, providing multidimensional analysis.
• Uses a trained DeepLabCut algorithm to track 5 body landmarks, enabling automated and precise measurement.
• Captures fine-grained exploration by subdividing behaviors and using dynamic distance thresholds (1 cm, 1.5 cm, 2 cm).

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small (42.0 KB), indicating limited scope, likely containing summary metrics or a description rather than raw tracking data.

Provenance

Source

Cenfei Zhou via figshare

Collection Method

Data was generated using a custom hardware arena with a high-definition industrial camera and a DeepLabCut deep learning algorithm trained to track mouse body landmarks.

Freshness

Last updated 2026-04-21 05:35:21; freshness should be verified.