Jean-Yves Tinevez
banner
jytinevez.bsky.social
Jean-Yves Tinevez
@jytinevez.bsky.social

Research engineer and core facility manager at the Institut Pasteur
https://research.pasteur.fr/en/team/image-analysis-hub/
Everything #TrackMate #Mastodon-sc (the tool to track lineages in microscopy videos, not the social networks etc).
Views are my own .. more

Biology 51%
Engineering 10%

Eurostar: it’s a train but you’ll be as miserable as in an airport

Reposted by Jean-Yves Tinévez

Second speaker is @jytinevez.bsky.social from @institutpasteur.bsky.social introducing TrackMate 8 #CBIAS2025

But they are getting fixed. One to go:

Reposted by Jean-Yves Tinévez

BIOIMAGE ANALYSTS ASSEMBLE!!!

#CBIAS2025

Classical aftermath

Reposted by Jean-Yves Tinévez

🎥 Discover the Institut Pasteur Education Center!

We’re excited to unveil the new presentation video of our Education Center, a space dedicated to training the next generation of scientists, health professionals, and researchers from around the world

➡️ www.pasteur.fr/en/education...

@pasteur.fr
Discover the Education Center of the Institut Pasteur
YouTube video by Institut Pasteur EDUCATION
youtu.be

Optimistic Dominik

My bad, it's actually #CBIAS2025

#CBIAS 2025 let’s go!!
Recently out: “Uniform dynamics of cohesin-mediated loop extrusion in living human cells”. In this study led by brilliant former PhD student Thomas Sabaté we use live cell microscopy and polymer simulations to characterize how DNA loops and TADs form in human cells by cohesin-driven extrusion. (1/4)

Reposted by Jean-Yves Tinévez

Finally, the first public release of #BigVolumeBrowser, so after teasers, you can try it yourself. For details, please check the announcement post (1/2)
forum.image.sc/t/bigvolumeb...
BigVolumeBrowser: a new 3D multi volume/mesh/point clould (SMLM) data viewer
Hello everyone, I’d like to share with you another 3D viewer for FIJI, BigVolumeBrowser (full documentation link). It‘s a first initial public release, so there is still space for improvements. Le...
forum.image.sc

Reposted by Jean-Yves Tinévez

Give it a try following the tutorial made by @jytinevez.bsky.social imagej.net/plugins/trac...
TrackMate Trackastra
Trackastra integration in TrackMate.
imagej.net

Reposted by Jean-Yves Tinévez

Trackastra is part of the brand-new TrackMate v8.

It is the first deep-learning-based ("AI") drop-in replacement for TrackMate's regular LAP-Track algorithm.

Tracks out of the box for many types of datasets (bacteria, fluorescent nuclei, phase contrast cell culture etc), zero parameters to tune 🤖

With an image with a proper background >.<

We hope you will enjoy this new version which took us a lot of time and sweat. I am confident that the new integration will accelerate bringing SOTA segmentation and linking algorithms into a convenient platform.

Enjoy!

I will be in the #CBIAS conference next week, in the Crick London. I will be happy to discuss the new version in person. Come and say hi!

And I improved a bit the display of column headers in TrackScheme. No big deal.

And other things.

There was also an annoying bug with 3D detection giving off coordinates, that was discussed reported and discussed here several times:

Other Improvements & Bug Fixes:

The most important bugfix we introduce is the memory leak that was evading us for a long time. To fix it I completely redesigned the detector factory API, introducing big breaking changes

We have made an example use of YOLO to track bacteria against a complex background, to be released soonish.

YOLO integration

With Marie Anselmet. Here we integrated the object detection routine of YOLO, so objects are detected as boxes and add in TrackMate as circular spots. YOLO does not ship pretrained model for microscopy, so you will have to provide or train one yourself.

Trackastra integration

With Martin Weigert & Benjamin Galluser: Integrated Trackastra as a tracker into TrackMate. This required some changes in Trackastra CLI and a rework of the tracker API of TrackMate.

Spotiflow integration

With @albertdm.bsky.social - Spotiflow can now be run directly from TrackMate!

- Cellpose-SAM integration

There is a dedicated detector for Cellpose SAM. It takes into account the must lower number of parameters. I have included one: the possibility to pass to the model one channel or all channels. This might impact the segmentation accuracy based on your input.

- new Cellpose 3 integration

Cellpose 3 is wonderful, easier to install and supports GPUs everywhere.

Reworked the Cellpose integration, and add Omnipose and Cellpose-SAM

The Cellpose integration has been rewritten in full. You will now find the following detectors:

- Omnipose

Also it will be easier to extend the Helper with additional metrics.

You can now add Spot & track filter parameter sweep in the optimization, to investigate the impact of filtering an tracking accuracy. And the rewrite also yield improved performance and robustness.

Updated TrackMate Helper & Batcher

In the Helper, you can now optimize tracking parameters with two tracking metrics sets:

- Single Particle Tracking (SPT) challenge metrics for optimizing tracking of moving objects
- And the Cell Tracking Challenge (CTC) metrics Evaluation Methodology

Early GEFF File Format Support

With @lxenard.bsky.social Ko Sugawara, Tobias Pietzsch

GEFF is a new, universal file format for exchanging tracking data between tools. While Java support is still in beta, it’s already used in TrackMate (e.g., for the TrackMate-inTRACKtive integration).