The latest preprint version of DaXi, our large field of view and high-resolution single-objective light-sheet microscope is out!

CytoSelf is out!

Machine learning makes sense of the cell’s architecture!
This is the companion paper to the OpenCell paper (right) where we show that self-supervised deep learning can help crack the protein subcellular localisation code!

OpenCell is out!

OpenCell is an amazing collaboration with Manuel Leonetti (CZB), Matthias Mann (MPI-biochem), and other colleagues at the CZ Biohub and UCSF. Can't explain it better than the tweets below, just check it out!

We are hiring, again!

This is a very special opportunity to work across two labs that work on complementary state-of-the-art technologies with Zebrafish as a model organism. We are seeking to identify a candidate with whom we will be writing an application for CZ Biohub's Collaborative Postdoctoral Fellowship Program.

Follow the link above for all details regarding scope, duration, remuneration, eligibility, etc...

Loic got interviewed by the Nature journal on how novel machine learning approaches are now helping biologists denoise microscopy images!

Latest preprint: pushing the limits of single-objective light-sheet microscopy with a novel high-resolution (1.0 NA), large field-of-view, multi-view, single objective light-sheet microscope design!

New paper: Self-supervised noise-tolerant image deconvolution!

New paper: Self-supervised noise-tolerant image deconvolution!

It all started when I needed a good object oriented layer in Java for OpenCL. I wrote ClearCL, and it seem that Robert liked it because he then built upon it and extending the whole thing so that many other could use GPU acceleration from ImageJ/Fiji. Great team work!

Loic's first iBiology talk is now available as part of the iBiology bioimage course. Very exciting!

It all started when Juan came to visit us in San Francisco. We realised that we both were frustrated by the lack of a great nD image viewer in Python. I wrote the first version of napari quickly in a week end with Juan's help, and we decided to push forward. The rest is history -- well captured by Juan's blog post!

We love to build our own hardware when we have to...

Our perspective in Nature Methods on Deep Learning applied to fluorescence microscopy is out. We go through most current and future applications ideas and explain the limits and challenges.

CARE paper out!

Fluorescence microscopy is a key driver of discoveries in the life sciences, with observable phenomena being limited by the optics of the microscope, the chemistry of the fluorophores, and the maximum photon exposure tolerated by the sample. These limits necessitate trade-offs between imaging speed, spatial resolution, light exposure, and imaging depth. In this work we show how content-aware image restoration based on deep learning extends the range of biological phenomena observable by microscopy.

We got the cover!