Deep-learning in the bioimaging wild: Handling ambiguous data with deepflash2
This addresses the challenge of objective and reliable segmentation in bioimaging for researchers, though it is incremental as it builds on existing deep learning methods with specific improvements.
The paper tackles the problem of segmenting ambiguous bioimages by introducing deepflash2, a tool that uses multi-expert annotations and quality assurance to achieve best-in-class predictive performance for semantic and instance segmentation with efficient computational resource usage.
We present deepflash2, a deep learning solution that facilitates the objective and reliable segmentation of ambiguous bioimages through multi-expert annotations and integrated quality assurance. Thereby, deepflash2 addresses typical challenges that arise during training, evaluation, and application of deep learning models in bioimaging. The tool is embedded in an easy-to-use graphical user interface and offers best-in-class predictive performance for semantic and instance segmentation under economical usage of computational resources.