LapTrack

LapTrack solves the linear assignment problem (LAP) to perform particle tracking for constructing cellular lineages from live imaging data.

Key Features:

• LAP framework implementation: Implements the linear assignment problem (LAP) framework for efficient particle tracking.
• Customizable Cost Functions: Allows arbitrary connection costs and custom metric functions, enabling metrics beyond distance and improving tracking scores over distance-only methods.
• Parallel Parameter Tuning: Supports parallel parameter tuning using ground-truth annotations to optimize tracking parameters across multiple datasets.
• Ground Truth Connection Preservation: Preserves ground-truth connections to maintain annotated links during tracking.
• Python integration: Integrates with Python-based particle detection, segmentation, and visualization tools.

Scientific Applications:

• Cellular lineage reconstruction: Reconstructs cellular lineages from live-cell imaging data in cellular biology.
• Tracking benchmark and optimization: Improves tracking accuracy and enables benchmarking on real and artificial datasets using custom metric functions and ground-truth annotations.

Methodology:

Implements the linear assignment problem (LAP) framework with customizable connection cost functions, supports parallel parameter tuning with ground-truth annotations, preserves ground-truth connections, and integrates with Python-based particle detection, segmentation, and visualization tools.