The analysis of spot-like structures is a widespread task in microscopy image analysis. Existing solutions are typically specific to single applications and do not use multidimensional information, often leaving manual annotation as the only option. Here, we present SpotMAX, a generalist AI-assisted framework for automated spot detection and quantification. SpotMAX detects spots in three-dimensional (3D) data and leverages the full scope of multidimensional datasets with an easy-to-use graphical user interface and a framework for cell segmentation and tracking. Tested on a large 3D dataset, SpotMAX outperforms or is on par with state-of-the-art tools and expert human annotators. We applied SpotMAX across diverse experimental questions, ranging from meiotic crossover events in Caenorhabditis elegans to mitochondrial DNA dynamics in Saccharomyces cerevisiae and telomere length in mouse stem cells, leading to new biological insights. With its flexibility in integrating other AI models into a holistic analysis workflow, we anticipate that SpotMAX will become the standard for spot analysis in microscopy data.
FörderungenGenitourinary Malignancies Branch of the National Cancer Institute at the National Institutes of Health ELIXIR-DE (Forschungszentrum Julich) De.NBI Cloud within the German Network for Bioinformatics Infrastructure (de. NBI) Helmholtz Association Deutsche Forschungsgemeinschaft (DFG, German Research foundation) Centre for Prostate Disease Research at the Henry Jackson Foundation Jane Coffin Childs Memorial Fellowship Swedish Research Council Research Council of Finland European Research Council European Molecular Biology Laboratory European Union (ERC) Human Frontier Science Program