AI4Life

AI4Life_Logo
Menu

Author: Pasi Kankaanpää

Categories
News

Icy joins as a Community Partner!

Icy joins as a community partner!

by Carlos Garcia-López-de-Haro

The Bioimage Analysis software Icy has officially joined the BioImage Model Zoo as a Community Partner! This means that the Icy software will soon be compatible with the Deep Learning (DL) models present in the BioImage.io repository.

Icy is a powerful, open-source software designed for bioimage analysis, with features including visualization, annotation, graphical programming, and more. Now, with the compatibility with BioImage Model Zoo, Icy will further enhance its capabilities by leveraging the power of Deep Learning to analyze complex biological images better.

Meanwhile, Icy users will be encouraged to upload new models and datasets to the BioImage.io website, improving the collaboration and pushing the Bioimage Analysis field forward. The plugin to run Deep Learning models in Icy is in its final stage of development and it will be released soon. The Icy team is also providing the backend of their plugin as an independent Java library to run any Deep Learning model from various of the supported DL frameworks by the BioImage Model Zoo (Tensorflow 1, Tensorflow 2, Pytorch and Onnx) in an easy way.

Categories
News

New videos in the AI4Life YouTube channel

First videos in the AI4Life YouTube channel

 

The AI4Life YouTube channel is officially inaugurated! It features two training videos currently, with more to come in the future. The first two videos mark the beginning of a new playlist for training, showing how to upload models to the BioImage Model Zoo and the cross-compatibility of these models, which allows researchers to use them with different software tools and platforms.

We look forward to seeing more content on this channel in the future.

Categories
event report

Outcomes of the hackathon “Deep Learning in Java”

Outcomes of the Hackathon “deep Learning in Java”

Milan, 6-10 February 2023

by Florian Jug

Global BioImaging and AI4Life organized a hackathon in Milan from February 6-10, 2023. The overarching goal of this event was to improve the accessibility of Deep Learning methods in Java-based image analysis tools and libraries. The event was held at the Human Technopole and was attended by a total of 21 participants from various parts of the world. 

The participants, representing tools such as bioimage.io, deepImageJ, Fiji, Icy, ImageJ, ImJoy, and QuPath, self-organized into topic-groups on day one and then tackled various challenges to bridge the system gap between typically python-based deep learning methods and Java (i.e. ImgLib2 based) image processing. 

These topic-groups made significant progress on different fronts over the 5-day event. A more in-depth report will soon be made available as an BioHackrXiv preprint. Among the highlights was the integration of a library by Carlos Garcia and colleagues (model-runner-java) into deepImageJ (and therefore into Fiji) and several other participants using this new way of running deep learning models on images opened in ImgLib2 containers (e.g. directly from Fiji). This was even pushed to extremes by combining the execution of models live from within BigDataViewer, e.g., enabling lazy prediction on terabyte sized datasets.

Additionally, another topic-group explored alternative ways to use the model-runner-java library, by directly sharing memory between native python processes and running Java VMs. Similar solutions exist (see for example imglyb or PyImageJ), but the newly explored idea is not any longer based on sub-processes but instead on inter-process communication. The big advantage of this approach is that parallel processes can be started independently, hook into each other on demand using shared memory, work together but die alone.

All participants are now continuing to flesh out the work that was started during the event and releases of updated versions of deepImageJ and a Fiji and Icy based deep learning integration are on their way. These updates will benefit hundreds of users world-wide.

 
AcknowledgementS
Categories
upcoming events

Course Microscopy data analysis: machine learning and the BioImage Archive

Microscopy data analysis: machine learning and the BioImage Archive

Date

Venue

Description

 

22-26 May 2023

Online

This virtual course will show how public bioimaging data resources, centred around the BioImage Archive, enable and enhance machine learning based image analysis. The content will explore a variety of data types including electron and light microscopy and miscellaneous or multi-modal imaging data at the cell and tissue scale. Participants will cover contemporary biological image analysis with an emphasis on machine learning methods, as well as how to access and use images from databases. Further instruction will be offered using applications such as ZeroCostDL4Mic, ilastik, ImJoy, the BioImage Model Zoo, and CellProfiler.

Contact information

Program, registration and more can be found here.

Categories
News

Summary of recommendations from the AI4Life & BioImage Archive FAIR AI workshop

Summary of recommendations from the AI4Life & BioImage Archive FAIR AI Workshop

27 February 2023

by Teresa Zulueta-Coarasa

The summary of recommendations gathered in the AI4Life & BioImage Archive FAIR AI Workshop that took place on January 24-25, 2023, is now public in Zenodo:

https://doi.org/10.5281/zenodo.7681687

A huge thank you to all the workshop participants for providing feedback on the summary. All the discussions, comments and suggestions have provided a great starting point for the manuscript with recommendations that will follow. We are looking forward to implementing the recommended updates on the BioImage Archive!

AcknowledgementS
Categories
upcoming events

Conference: 5th NEUBIAS Conference 2023

5th NEUBIAS Conference 2023

Defragmentation Training School & Open Symposium

Date

Venue

Description

8-12 May, 2023

Porto, Portugal

The Defragmentation Training School 2 is addressed to the new generation of bioimage analysts and will take place from the 8th to the 12th of May 2023. The training school is supported by EOSC-Life, Euro-BioImaging, AI4Life and i3S.

The Open Symposium will start on Thursday the 11th of May and will focus on recent scientific developments and open tools in bioimage analysis. There will be a special session for AI4Life, covering Deep Learning-related topics.

More information about the Defragmentation Training School can be found here and the Open Symposium here.

Categories
upcoming events

Workshop: Euro-BioImaging’s Guide to FAIR bioimage data

Euro-BioImaging’s Guide to FAIR bioimage data

Date

Venue

Description

 

 

 

March 28, 2023, 2pm – 5pm CEST (see in your local time)

Online

Wondering how to make the most out of your bioimaging data?

Join us for a free, online workshop that will introduce the FAIR (Findable, Accessible, Interoperable and Reusable) principles, focusing on their implementation for bioimaging data.

Speakers will include representatives from Euro-BioImaging, BioImage Archive, the AI4Life project, and more … Our special guest, Katrín Möller, a post-doctoral researcher at Biomedical Center of the University of Iceland, will share her personal story of depositing her microglia dataset on the BioImage Archive.

Contact information

 

Find more information in Euro-BioImaging’s LinkedIn event.

Categories
News

Celebrating the International Day of Women and Girls in Science

Celebrating the International Day of Women and Girls in Science

Milan, 11 February 2023

At the recent Hackathon “Deep Learning in Fiji”, organized by AI4Life and Global Bioimaging at the Human Technopole, several talented and accomplished women engineers made their mark.

As the world celebrated the International Day of Women and Girls in Science during the Hackathon, we took the opportunity to highlight the contributions of the female participants to the hackathon. Read below their trajectories and accomplishments.

Caterina Fuster-Barceló

Caterina is a post-doctoral researcher immersed in AI4Life with Dr Arrate Muñoz Barrutia. In December 2022, she defended a PhD in Computer Science and Technology with a cum-laude mention obtained at Carlos III University of Madrid (UC3M), Spain, under the supervision of Dr Pedro Peris and Dr Carmen Cámara. She possesses a BSc in Telematics Engineering from the University of the Balearic Islands (UIB) and an MSc in Cybersecurity for the UC3M. One of her great passions is sharing the knowledge she obtained these last years with different communities. For this reason, she is participating in Skype A Scientist and has explained her thesis to people from different backgrounds at different conferences that you will find on her website.

Hackathons are a great opportunity to meet personally who you are working with. Being able to talk and work face to face is a rich experience that sometimes we forget how important it is. So glad that I have met those amazing people from all around the globe to share knowledge, skills and drinks!
Caterina Fuster-Barceló

Estibaliz is a mathematician by training and an expert in biomedical image analysis. She did her PhD at Universidad Carlos III de Madrid (Spain) with Prof. Arrate Muñoz-Barrutia and Prof. Denis Wirtz on the study of 3D cancer cell motility. Currently, she’s an EMBO postdoctoral fellow within the group of Prof. Ricardo Henriques at the Instituto Gulbenkian de Ciência in Portugal. She is heavily involved in the bioimage analysis community, more particularly in the development of deepImageJ, ZeroCostDL4Mic, DeepBacs and the BioImage Model Zoo. She also collaborates in the Cell Tracking Challenge and she’s a trainer in NEUBIAS training school for BioImage Analysts, EMBO practical courses on image processing, EMBL-EBI courses for Microscopy Data Analysis, Neurophotonics Summer School at CERVO institute & Universidad Laval, and the DL@MBL. Find out more about her career on her website and Twitter account.

In AI4Life, Estibaliz works on the connection between the resources that build models (ZeroCostDL4Mic) and consume them (deepImageJ), and the BioImage Model Zoo.

Estibaliz Gomez de Mariscal
Fiona Inglis

Fiona is currently a Research Software Engineer developing QuPath, a software for viewing, processing and quantifying microscopic images with a specific focus on large whole-slide images. She was first exposed to the imaging world while working as a slide-scanning imaging technician for the University of Edinburgh, after her first BSc in infectious diseases. 2 years on, she switched her career path to web development as she wanted to pursue programming full-time after enjoying scripting imageJ macros for researchers. Fiona completed another BSc alongside working, this time in Software Development, and then she found out about the opportunity to be part of Pete Bankhead’s growing QuPath team. This role has allowed her to combine her interests and has introduced her to a fantastic community, working together to put cutting-edge AI tools into researchers’ hands.

This was my first hackathon and therefore I planned to absorb as much knowledge as possible from those around me. Being at an in-person event after working remotely for so long was very refreshing and hugely beneficial to knowledge sharing and discussions. I spent the time understanding QuPaths current integration of deep learning, exploring the tools developed by others at the event and ways to increase the compatibility of these tools with each other.

Fiona Inglis

Lucia is a biomedical and computer science engineer, working on AI4Life with Dr Arrate Muñoz Barrutia. She did an MSc in Information Engineering for Health in order to use her skills to make deep learning accessible and easy to use in the Life Sciences field. She is now involved in the development of new tools and resources for biomedical image analysis and the improvement of some currently existing like DeepimageJ.

In the past years, she has been involved in projects related to neurodegeneration and rare blood diseases, trying to understand these conditions and find new ways to diagnose them. She is committed to inspiring new generations to pursue STEM careers and making science easy to understand for people not in the field. For that matter she has been part of some initiatives like #JuntosXElCancer, creating didactical biomedical engineering content related to cancer research; and she has also been part of CEEIBIS, the national committee for biomedical and health engineering, organizing talks and events for students that want to pursue a career in this field. Know more about Lucia on her website.

During these days, I have been Improving deepImageJ plugin, to make it easier to use and creating new ImageJ plugins for image processing, using both classical and deep learning tools.
Lucia Moya-Sans
Lucia Moya-Sans
Beatriz Serrano-Solano

Beatriz Serrano-Solano is a software engineer with a PhD in Computational Biology from the University of Málaga (Spain). After successfully defending her thesis, she embarked on a journey to Germany where she continued her academic pursuits as a postdoctoral researcher at EMBL Heidelberg. There, she participated in scientific projects for the European project EOSCpilot and later EOSC-Life. Later, and for a bit more than two years, she served as the community manager for the European Galaxy project, showcasing her expertise in project management and community building. Today, she holds the position of Scientific Project Manager at Euro-BioImaging, where she is involved in the European project AI4Life.

In AI4Life, Beatriz leads the work package for Communication, Outreach and Training, being also heavily involved in the organisation of the Open Calls and Challenges that will take place during the 3 years of the project.

Categories
event report

Outcomes of the AI4Life & BioImage Archive FAIR AI Workshop

AI4Life & BIOIMAGE ARCHIVE FAIR AI WORKSHOP

Online, 24-25 January 2023

 

AI4Life & BioImage Archive FAIR AI Workshop

by Matthew Hartley and Teresa Zulueta-Coarasa

Artificial Intelligence (AI) and deep learning (DL) are transforming the way we analyse biological images, benefitting particularly the processing of large and heterogenous image datasets. The development of these AI models relies on high-quality annotated images, which will determine the model’s performance, robustness, and scalability. Therefore, providing open access to useful, annotated datasets adhering to the FAIR principles (Findability, Accessibility, Interoperability and Reusability), is essential for the development, reproducibility, and reuse of AI models. However, sharing biological image AI datasets is challenging due to the lack of standards for representing annotation data widely adopted across the community.

The BioImage Archive (BIA), EMBL-EBI’s data resource for open life sciences image data, provides general purpose deposition services for any imaging dataset accompanying a publication, as well as reference image data. As part of the AI4Life project, we want to improve the BIA’s support for image annotations as part of AI-ready datasets and to develop annotation standards for the community. 

To this end, we held a virtual workshop on the 24 and 25 of January with 46 community experts from various backgrounds, including data generators, annotators, curators, AI researchers and software developers. The participants discussed four main topics:

  • What are the important types of annotation to record, and what extra information/metadata should accompany them?
  • What are the useful ways (formats, metadata) to share and present annotation data?
  • How should we support/allow/encourage sharing and archival of annotations?
  • What are our community recommendations to accelerate AI methods development through sharing AI image annotations, what are the missing pieces?

Each topic was first discussed in breakout rooms and afterwards each group presented their conclusions to the rest of the participants. This approach resulted in lively and insightful discussions and a series of recommendations.

The immediate output from the workshop will be a white paper, co-authored by the workshop participants, summarising community recommendations. Furthermore, The BIA team is now working on transforming the workshop outcomes into metadata standards for AI datasets, and into software and tools to facilitate the deposition and sharing of AI images and annotations.

Beyond these outputs, we expect that the workshop recommendations will help annotation generators and consumers work together more effectively, facilitating the construction of benchmark collections of datasets to test model generalisation and reuse. Thank you to all the participants for their valuable contributions!

AcknowledgementS