BioEngine: Supercharging AI-powered BioImage analysis

SciLifeLab is thrilled to announce the launch of BioEngine, developed at the AICell Lab (https://aicell.io/) at SciLifeLab & KTH Royal Institute of Technology, in collaboration with the BioImage Archive Team at EMBL-EBI as part of the AI4Life consortium (https://ai4life.eurobioimaging.eu/).

Initially designed to support the BioImage Model Zoo (https://bioimage.io) for effortless model testing, BioEngine empowers both experts and newcomers in the field of bioimage analysis. This cloud-based infrastructure brings AI to the next level by offering a user-friendly, plug-and-play cloud solution that not only simplifies model testing but also pioneers next-generation bioimage analysis capabilities.

“BioEngine, developed at SciLifeLab, aims to democratize advanced AI for bioimage analysis. We’re at the starting line of a transformative journey and couldn’t be more excited for what’s to come,” says SciLifeLab DDLS Fellow Wei Ouyang.

For the Bioimaging Community

• Cloud-Based Testing: BioEngine lets you test-run AI models from the BioImage Model Zoo without any local installation. Try it out at https://bioimage.io
• Software Compatibility: Seamlessly connect BioEngine to popular bioimaging software platforms like Fiji, Icy, and napari, avoiding the hassle of manual dependency installations.

For Developers

• Optimized Resources: Built to efficiently serve multiple AI models to a large user base, all while judiciously using limited GPU resources.
• Simple API: Developers can effortlessly integrate BioEngine into their projects, from Python scripts to web-based applications. You can send image data arrays to the server and receive processed results, all via simple API calls.
• Broad Integration Options: Several example integrations with existing software platforms are already available, showing the ease and versatility of connecting with BioEngine.

For more information and to get involved, please refer to our API documentation.

What’s Next?

Stay tuned for upcoming deployment toolkits that will allow versatile on-premise installations, ranging from Kubernetes clusters to individual workstations or laptops. The AICell Lab is excited to collaborate closely with the SciLifeLab Data Center to deploy an instance of BioEngine specifically for the SciLifeLab community. The aim is for various labs and facilities to significantly benefit from this work. Furthermore, future updates will be focusing on integration with key AI and GPU computing clusters in Sweden, including BerzeLiUs and Alvis.

Acknowledgments

• EU: Funded by the EU’s Horizon Europe program, grant no. 101057970.
• Nvidia: Supported our development, notably with Triton Inference Server and computing credit.
• Bioimaging Community: Thanks to testers and AI4Life Stockholm Hackathon 2023 participants for vital feedback.
• SciLifeLab & KAW: The AICell Lab (http://aicell.io/), led by Wei Ouyang, is funded by the SciLifeLab & Wallenberg National Program for Data-Driven Life Science (DDLS) fellows program, with funding from the Knut and Alice Wallenberg Foundation.

Also see the news article here: announcing BioEngine