Building AI Infrastructure for Scalable Bioimage Analysis

Session

Artificial Intelligence

Authors

Assistant Professor Wei Ouyang (1)

Affiliations

1. KTH Royal Institute of Technology

Keywords

artificial intelligence, bioimage analysis, web, microscopy

Abstract text

The combination of artificial intelligence (AI) and microscopy has opened up new avenues for image analysis in biomedical research. However, the deployment of AI methods remains challenging due to complex hardware and software dependencies, scalability issues, and usability barriers etc. In this talk, we will present our efforts in building AI infrastructure that addresses these challenges. We will introduce ImJoy, a web platform that improves interactivity and scalability of AI software, and BioEngine, a cloud-based AI framework that enables human-in-the-loop annotation, model inference and training. Additionally, we will present the Bioimage Model Zoo (https://bioimage.io), which provides a centralized repository for sharing AI models for bioimage analysis and making them accessible to everyone. Together, these efforts represent a promising future for augmented microscopy and scalable web- and AI-powered bioimage analysis.

References

• Wei Ouyang, Fynn Beuttenmueller, Estibaliz Gómez-de-Mariscal, Constantin Pape, Tom Burke, Carlos Garcia-López-de-Haro, Craig Russell, Lucı́a Moya-Sans, Cristina de-la-Torre-Gutiérrez, Deborah Schmidt, others (2022). BioImage Model Zoo: A Community-Driven Resource for Accessible Deep Learning in BioImage Analysis. bioRxiv.
• Wei Ouyang, Florian Mueller, Martin Hjelmare, Emma Lundberg, Christophe Zimmer (2019). ImJoy: an open-source computational platform for the deep learning era. Nature methods.