Webinar series

We have partnered with AI4Life to bring you a bimonthly seminar series, starting in February. You will get insight into the different sides of the AI4Life project and learn about the state of the art in AI for BioImage Analysis. 

All events will run from 4 to 5pm CE(S)T.

13 February 2025  

New date: 27 February 2025

AI4Life: What can it do for you and your images?

Machine learning (ML) has enabled and accelerated frontier research in the life sciences, but democratised access to such methods is, unfortunately, not a given. Access to necessary hardware and software, knowledge and training, is limited, while methods are typically insufficiently documented and hard to find. Furthermore, even though modern AI-based methods typically generalize well to unseen data, no standard exists to enable sharing and fine-tuning of pre-trained models between different analysis tools. In this seminar, we will discuss how the AI4Life consortium addresses such accessibility and standardisation gaps. We will present the unified DL model metadata specification and show the trained models we have collected in the BioImage Model Zoo. Importantly, the Model Zoo is supported by a large range of community partners, e.g. ilastik, Icy or BiaPy, that can all run models which adhere to the standard. This seminar is targeting users looking for pre-trained DL models to solve their bioimage analysis problems. We will also mention important features we have introduced for model developers, such as our simple model contribution pipeline.

presenters: Anna Kreshuk, Wei Ouyang

10 April 2025 

Towards FAIR and high-quality AI-ready data for bioimage analysis

Deep learning (DL) has transformed biomedical and microscopy image analysis. However, the development, validation and benchmarking of DL algorithms rely heavily on high-quality annotated datasets that are often scarce and difficult to reuse. Furthermore, the complexity of such data presents significant challenges for accurate algorithm implementation. In the first part of this seminar, we will discuss how the BioImage Archive is working to increase the availability of annotated biological image datasets by making them FAIR (Findable, Accessible, Interoperable, and Reusable). The second part of the seminar will address the critical aspects of data quality and result validation in DL applications for biomedical imaging. The seminar will provide practical standards for sharing high-quality data while leveraging the power of deep learning in biomedical research 

presenters: Teresa Zulueta-Coarasa, Estibaliz Gómez de Mariscal

12 June 2025 

Building scalable and reproducible AI infrastructure for Bioimaging 

In this webinar, we spotlight two complementary platforms that simplify and democratise deep learning for bioimaging: BioEngine and DL4MicEverywhere.

BioEngine offers a user-friendly, cloud-based approach to serving and running BioImage Model Zoo models at your own institute. It integrates seamlessly with common tools (e.g., Fiji, Icy, napari) and automates GPU resource management, making state-of-the-art AI analyses accessible to a broad range of users. Whether you deploy BioEngine on a local workstation or a cluster, it streamlines high-throughput bioimage analysis and promotes reproducible workflows.

DL4MicEverywhere tackles the challenge of reproducible and portable deep learning by containerizing interactive Jupyter Notebooks for zero-code model training and inference. It bridges multiple computational environments—from Google Colab to personal desktops and HPC clusters—using Docker technology, ensuring that advanced pipelines can be easily replicated across platforms without sacrificing performance or usability.

By attending this session, participants will gain practical insights into deploying AI models on their own infrastructure, learn how to maintain reproducibility across varied computational setups and discover how these two platforms can work in tandem to elevate and streamline their bioimage analysis pipelines.

presenters: Wei Ouyang, Iván Hidalgo-Cenalmor

14 August 2025 

Lessons learned from 3 years of open calls and challenges 

Over the past three years, AI4Life has run an open call program to help researchers solve bioimage analysis challenges through deep learning. In this webinar, we will share our experiences and the various lessons learned that have helped us continuously refine the application, consultation, and selection processes. The open calls also gave us many insights into the community's current needs and challenges in microscopy image analysis and beyond. Additionally, we will draw comparisons to the national open calls conducted by Human Technopole in Italy, and highlight how insights from AI4Life can benefit image analysis facilities. Finally, we will discuss the various deep-learning challenges we organized and what they reveal about the capabilities of state-of-the-art algorithms for different image analysis tasks. 

presenters: Mehdi Seifi, Vera Galinova, Damian Dalle Nogare, Caterina Fuster-Barceló 

Please check also our partner webpage from AI4Life.

Registration

Please register for the webinar series here: AI4Life & GloBIAS webinars. 

The registration will be used to send you the link to the seminar sessions.  You will be registered for all upcoming webinar sessions (February to August).