by Beatriz Serrano-Solano
We’ve launched a new section on our website dedicated to guiding you on how to engage with our project.
Are you looking to participate, collaborate, or simply learn more about AI4Life? Our new section has all the answers. Find out how you can contribute, connect, and engage with us effortlessly!
Explore the new section: https://ai4life.eurobioimaging.eu/engage/
by Daniel Franco
The Bioimage Analysis software BiaPy has officially joined the BioImage Model Zoo as a Community Partner! This means that the BiaPy software supports the BioImage.io format for deep learning models.
BiaPy is an open source Python library to easily build bioimage analysis pipelines based on deep-learning approaches. The library supports the image processing of 2D, 3D and multichannel microscopy image data. Specifically, BiaPy contains ready-to-use solutions for tasks such as semantic segmentation, instance segmentation, object detection, image denoising, single image super-resolution and image classification, as well as self-supervised learning alternatives.
At present, BiaPy Jupyter notebooks already exporting BioImage.io compatible models are accessible through the BioImage Model Zoo. A future expansion of the current offer by adding a variety of models, including transformers, is expected. The integration of BiaPy in the BioImage Model Zoo aims to enhance the library’s visibility, foster greater collaboration, and serve the community better by increasing the variety of advanced image processing approaches, which significantly empowers the field of BioImage Analysis.
by Beatriz Serrano-Solano
We’re happy to share our latest resource: the AI4Life factsheet! This document provides a comprehensive overview all the important outputs and accomplishments of the project at a glance.
We’ll continuously update this Factsheet to ensure it remains a current resource. Whether you’re preparing a presentation, seeking project insights, or diving into the project’s accomplishments, this Factsheet is what you are looking for.
Feel free to explore and use the AI4Life Factsheet in your outreach activities!
by Beatriz Serrano-Solano
AI4Life recently participated in a series of Machine Learning mini-hackathons hosted by NFDI4DataScience at ZB MED in Cologne (Germany). Our team engaged in two different sessions, aiming to define the Machine Learning lifecycle and to discuss the metadata required for each step.
Machine Learning Lifecycle (21-22 November 2023)
Throughout the two-day event, our objectives revolved around defining the lifecycle steps, creating a graphical representation and fostering compliance with FAIR principles. To extend the discussion to the broader community, the outcomes have been presented at the RDA FAIR4ML Interest Group.
Metadata for Machine Learning (23-24 November 2023)
This session focused on mapping metadata, datasets and applications across various platforms like the DOME registry, Bioimage.io, OpenML, and schema.org, significantly contributing to standardizing ML metadata.
AI4Life’s participation in these mini-hackathons underlines the project’s commitment to enhancing the BioImage Model Zoo models specification to make them interoperable with resources outside the imaging community.
These events carried out during the Machine Learning hackathon at ZB MED sponsored by NFDI4DataScience. NFDI4DataScience is a consortium funded by the German Research Foundation (DFG), project number 460234259.
