Cell Behavior Video Classification Challenge, a benchmark for computer vision methods in time-lapse microscopy
By: Raffaella Fiamma Cabini , Deborah Barkauskas , Guangyu Chen and more
The classification of microscopy videos capturing complex cellular behaviors is crucial for understanding and quantifying the dynamics of biological processes over time. However, it remains a frontier in computer vision, requiring approaches that effectively model the shape and motion of objects without rigid boundaries, extract hierarchical spatiotemporal features from entire image sequences rather than static frames, and account for multiple objects within the field of view. To this end, we organized the Cell Behavior Video Classification Challenge (CBVCC), benchmarking 35 methods based on three approaches: classification of tracking-derived features, end-to-end deep learning architectures to directly learn spatiotemporal features from the entire video sequence without explicit cell tracking, or ensembling tracking-derived with image-derived features. We discuss the results achieved by the participants and compare the potential and limitations of each approach, serving as a basis to foster the development of computer vision methods for studying cellular dynamics.
Similar Papers
Segment Anything for Cell Tracking
CV and Pattern Recognition
Finds cells dividing in pictures without training.
Supervised contrastive learning for cell stage classification of animal embryos
Quantitative Methods
Lets computers watch baby cow embryos grow.
TransientTrack: Advanced Multi-Object Tracking and Classification of Cancer Cells with Transient Fluorescent Signals
CV and Pattern Recognition
Tracks cells, showing when they divide or die.