FBI Challenge: we are organizing a data machine learning competition!
In order to answer image data analysis demands, France-BioImaging is launching its first data machine learning competition! The idea? To develop powerful methods that will then end up in creating standards & benchmarks in the field of bioimaging.
The FBI challenge is hinged on a double contribution: from core facilities engineers and from data scientists. The first group will acquire a large number of images to build a dataset, that will later be used by the algorithms. These images will be produced by microscopy engineers & technicians from FBI’s platforms. As for the second contribution, this is where the challenge starts! The challenge will be later published to have a maximum of data scientists to work on the algorithms that best fulfill the analysis task.
The first project is also based on four pillars:
- Open source + FAIR (Findable, Accessible, Interoperable, Reusable)
- Supervised learning, it involves annotated datasets to maintain control over performances.
- In silico annotations, a computer labeling method to avoid manual annotation and its drawbacks.
- Image-to-image analysis tasks, an image analysis tasks which aim to predict an output image from the input one.
We need you!
The first challenge is still under preparation. It will predict the fluorescence image of cell culture from a bright field, phase contrast and/or DIC microscopy label-free image. Nevertheless, we need you to contribute to the dataset that will supply the machine learning! The more images we have, the better the prediction algorithm will be.
If you are interested, please contact Dorian Kauffmann: dorian.kauffmann@france-bioimaging.org.