SPOT
Abstract
SPOT is a generalized and streamlined workflow for analysing object dynamics in movies. It is designed to suit high-content imaging applications where analytical tools should be push-and-go and require no prior knowledge of the expected behaviour of the objects to be studied. In other words, users should be able to run through all the steps in one go, then retrospectively interpret the produced results. This workflow is inspired by that for single-cell sequencing and is summarized in the figure above. Three innovations drive SPOT for temporal image analysis: a standardized Shape, Appearance and Motion phenome - a single feature set for all objects a standardized temporal analysis of compiled SAM phenomes - minimal assumption, push-and-go automated and standardized techniques to cluster related SAM features into SAM modules for interpreting discovered phenotypes SPOT is provided here as a Python package to allow full flexibility. To get started, please check out exemplar scripts in the examples/ folder. Link to GitHub: https://github.com/fyz11/SPOT
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 10 June 2026