Automating Visual Recognition of Leprosy in Wild Chimpanzees

2026-07-19

AI Summary

This study addresses the infeasibility of manual screening for leprosy symptoms in chimpanzees within large-scale wild camera-trap videos by introducing the first deep learning pipeline for automated wildlife leprosy detection. Leveraging the newly released PanLep300 dataset, the work systematically evaluates the performance of 2D, 2.5D, and 3D approaches. It proposes an ecology-informed data partitioning strategy and demonstrates that aggregating frame-level predictions based on static skin symptoms outperforms more complex spatiotemporal models. Furthermore, the authors design bounding-box cropping and track-level aggregation techniques to mitigate performance degradation caused by partial visibility of individuals, significantly improving detection accuracy in real-world field conditions.

Abstract

Leprosy (Mycobacterium leprae) has been confirmed in wild western chimpanzees (Pan troglodytes verus) in West Africa, presenting as clear and progressive visual symptoms. Manual review of camera-trap footage at landscape scale is infeasible, motivating the need for automated screening. We present the first deep learning pipeline for wildlife leprosy detection and contribute the PanLep300 dataset of 125,670 annotated bounding-box crops across 953 tracks from 303 camera-trap videos with ecologically-motivated splits that withhold whole individuals and camera installations. We benchmark spatial (2D), temporally aggregated (2.5D), and video-based (3D) classification approaches to investigate which approach is best suited to automated leprosy detection in wild apes. We find that simple aggregation of crop-level predictions consistently matches or outperforms both learned temporal models and end-to-end video architectures -- consistent with leprosy's static cutaneous presentation. We further find that performance is suppressed when tracklets contain frames of partially visible individuals -- as commonly occurs at the start and end of a track -- and demonstrate that this can be addressed through targeted construction and aggregation strategies.

Problem

• leprosy
• wild chimpanzees
• visual recognition
• camera-trap footage
• automated screening

Innovation

• deep learning
• wildlife disease detection
• camera-trap video analysis
• temporal aggregation
• PanLep300 dataset