We want to organize a learnathon to teach plugin development within #FIJI #scijava #imglib2 #BigDataViewer and other Big* parts of the Java ecosystem.
Please spread the word, and if you know someone who can be interested, forward them the link below forum.image.sc/t/learnathon...
Excited to share our new paper on the future of autonomous scientific laboratory work (together with
@henrypinkard.bsky.social
). Perhaps the path to intelligent scientific instruments starts with rethinking what data we save ?
www.nature.com/articles/s41...
rdcu.be/eW7SU
Most scientific instruments throw away exactly the data AI would need to learn how to operate them.
In @natmethods.nature.com this month, @nilsnorlin.bsky.social and I describe in how capturing this data could let us train AI to run experiments like expert scientists.
doi.org/10.1038/s415...
screenshots of some of the sample implementations
Screenshot of smartmicroscopy.github.io/implementations.html, showing an overview of collected implementation examples
Want to get started with smart microscopy? 🧠🔬
Check out our online repository with implementations from labs and industry -- lots of practical tips and links to sample code! smartmicroscopy.github.io/implementati...
More details in the ✨updated preprint!✨
www.biorxiv.org/content/10.1...
A new Perspective discusses the challenges of sharing annotated image datasets and offers advice for improving bioimage annotation and reuse, particularly for AI applications.
www.nature.com/articles/s41...
🎉 Our paper “MIFA: Metadata, Incentives, Formats and Accessibility guidelines to improve the reuse of AI datasets for bioimage analysis” is out in @natmethods.nature.com!
Community-driven standards to make bioimage data AI-ready & reusable.
👉 www.nature.com/articles/s41... #AI #Bioimaging #FAIRdata
Figure legend: Categories and capabilities of smart microscopy systems integrating real-time image analysis and feedback control. Top: Smart microscopy workflows can be classified based on the driving logic behind decision-making: Event-driven (reacting to rare biological events), Outcome-driven (using feedback-control to steer biological systems toward a desired state), Quality-driven (optimizing signal quality or imaging metrics), and Information-driven (guided by models that predict which measurements/perturbations will yield the most informative data). Middle: Central feedback loop between the microscope and an image analysis system, which continuously exchanges images and commands to guide acquisition dynamically. Bottom: Key control actions enabled by smart microscopy: adjusting imaging modality (e.g. switching from brightfield to fluorescence, adjusting sampling rate), repositioning the field of view (e.g. tracking, drift correction), optimizing acquisition settings (e.g. adaptive optics), and performing photomanipulation (e.g. FRAP, ablation, optogenetics).
🔬🧠 Our paper on smart microscopy & the issue of interoperability! www.biorxiv.org/content/10.1... LONG THREAD WARNING: Smart microscopy uses real-time image analysis to automatically guide the acquisition or perturbation of the sample (closed feedback-control loop). Many applications exist:
Also, in another project we are looking for a postdoc interested in spatial omics method development and applications in cell and tissue biology. Ideally suited for someone with prior hands-on experience with MERFISH and/or ISS.
For more information or to apply, please reach out via email
Norlin Lab is expanding!
Postdoctoral scholarship available:
Computational microscopy with applications in lensless imaging.
Preferably, you have already developed applications using ML/AI in microscopy, though this is not strictly required.
