Albert Dominguez Mantes

Spotiflow, our deep learning based spot detection method for microscopy, is now published in @naturemethods! Since the pre-print, we have added many cool features, notably native 3D detection! @martweig @GioeleLaManno @epflSV @EPFL_Imaging Paper: rdcu.be/epIB7 (1/N)

🧬🔬 Millions of molecules automatically detected in human tissues thanks to Spotiflow, a revolutionary AI-powered microscopy tool developed at @EPFL and @tudresden_de 👇 📍Supported by @EPFL_Imaging 🔗actu.epfl.ch/news/in-the-bl… #AI #Microscopy #SpatialBiology #OpenScience #EPFL

A nice advance for imaging-based spatially resolved transcriptomics from the Weigert and La Manno labs. Spotiflow uses deep learning for subpixel-accurate spot detection in diverse 2D and 3D images. nature.com/articles/s4159…

A massive thanks to all the incredible people who contributed to this work, it's been an amazing ride! And a shoutout to all the people who have tried already tried Spotiflow and provided feedback, it's truly great to see the community using it :) (N/N)

For more details on using Spotiflow, check our repository at github.com/weigertlab/spo…! We are very excited to see what uses cases people will find for Spotiflow! (9/N)

Spotiflow, our deep learning based spot detection method for microscopy, is now published in @naturemethods! Since the pre-print, we have added many cool features, notably native 3D detection! @martweig @GioeleLaManno @epflSV @EPFL_Imaging Paper: rdcu.be/epIB7 (1/N)

Get to know Spotiflow, an AI method that improves large-scale transcript localization by combining deep learning with a novel geometric detection approach. Learn more: 👉 scads.ai/transcript-det… Find the publication in Nature Methods: 👉 nature.com/articles/s4159…

🚨OPEN PhD position🚨 I am looking for a highly motivated PhD student to join my project group in the Department of Machine Learning and Systems Biology @MLSB_Borgwardt led by @kmborgwardt at @MPI_Biochem near Munich. Deadline November 15th. Please RT.

@ajinkya_talks We trained on a patch size of 256^2, but the images can be smaller than that. The lower limit would be 32^2, which is given by the depth of our UNet

@Albertdm99 Oh nice! And what is this size that the model was trained on? So I can make sure the images I input are larger than those.

@Albertdm99 Hey, thanks for your spotiflow repo. I had a quick question. What is the image size that the model was trained on? I’m looking to infer it on 1000x1000 images. Does it internally resize, then predict, or infer on patches then stitch back the patches?

Interested in navigating #metabolism in space and time? Meet uMAIA (the Unified Mass Imaging Analyzer) - a framework developed in collaboration with @Gio_Dangel0 & @OatesLab @epflSV led by @HSchede & @Leila_Alieh #omics #lipidtime #MALDI biorxiv.org/content/10.110… 1/N

Just accepted at ECCV 24 🎉🎉 big congrats to @bengallusser ! Milano in autumn it is then...

Happy to share our group's work together with @Albertdm99 on DL-based spot detection and cell tracking today at the great Swiss BioImage Analysts' Society meeting @SwissBIAS, so many cool projects around!

We present: 'Multispectral live-cell imaging with uncompromised spatiotemporal resolution'. biorxiv.org/content/10.110… 1/16