Arrate Munoz-Barrutia

Excited to share our new paper (CVPR 2026 🚀): "MuViT: Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy" which enables local predictions to use global context.
Great work led by @albertdm.bsky.social & another fun collab w @gioelelamanno.bsky.social! @scadsai.bsky.social

Mastodon: the Command Center for Large-Scale Lineage-Tracing Microscopy Datasets https://www.biorxiv.org/content/10.64898/2025.12.10.693416v1

Assistant/associate Professor of AI-assisted Biophysics at the Ecole polytechnique fédérale de Lausanne (EPFL) and Group Leader at the Paul Scherrer Institute (PSI) The School of Basic Sciences (Physics, Chemistry and Mathematics) at EPFL and the Paul Scherrer Institute (PSI) jointly seek to appoint a Tenure Track Assistant or tenured Associate Professor in AI-As...

#EPFL has an open faculty position - tenure track or tenured!! - in AI driven biophysics. Deadline is Nov 15th. Please spread the word!

www.epfl.ch/about/workin...

Biological Laboratory | LEGO® Ideas This is a two-floor realistic Biological Laboratory building. In this design, I try to tell stories about biologists, introduce biology concepts to general publ…

I just made an account and voted for this biology laboratory made of LEGO to "promote biological research and inspire more people into the world of biology". They need 10K votes. Reposting and/or voting below would be helpful. 🤗
beta.ideas.lego.com/product-idea...

❗The official application call for our PhD position has already started:

www.ehu.eus/es/web/ikerk...

Since most of the application is in either Spanish or Basque, I have prepared a document in English 👇

drive.google.com/file/d/1q0mH...

Looking forward to receiving applications! 🤩

📢 Open 4-year PhD Position in Deep Learning for Bioimage Analysis! | CVPD Research group The Computer Vision and Pattern Discovery (CVPD) group at the University of the Basque Country (UPV/EHU) is offering a fully funded 4-year PhD position within the recently awarded project TOSBI: Towar...

📣 We’re hiring, please RT! Fully funded 4-year PhD position in our CVPD group at @informatikaehu.bsky.social!

Research at the intersection of AI, deep learning & bioimage analysis. 🧠🔬

📅 Applications open Oct 6 (deadline: ~Oct 27)
📍 San Sebastian, Spain.
👉 cvpd.github.io/post/2025-09...

Raúl Rabadán será el nuevo director del CNIO tras la destitución de Maria Blasco Catedrático en la Universidad de Columbia y experto en genómica del cáncer, Rabadán ha sido elegido por unanimidad; el pasado enero el patronato cesó a Blasco y al gerente en un proceso que convulsion...

‼️ Raúl Rabadán será el nuevo director del CNIO tras la destitución de Maria Blasco

Nanotechnology for immuno-oncology - Nature Cancer Kim and colleagues provide an overview of the current state of the art of nanomaterials and their application in immuno-oncology, discussing preclinical development and the clinical landscape.

Our latest article is online @natcancer.nature.com describing the application of #nanotechnology in #immuno-oncology. A great effort led by Adam Grippin, our star Holman resident and soon to be Physician Scientist. @bettykimmdphd.bsky.social @mdanderson.bsky.social @eileenparkes.bsky.social

⛴️ BiaPy just reached version 3.6.1 💫 (latest release)!

github.com/BiaPyX/BiaPy...

➡️ v3.6.1 came right after (the more dense) v3.6.0 to fix some small bugs 🐞

Let me tell you a bit about what's new 👇

In the meantime, we have more than 46 pretrained models from ⛴️ BiaPy available now in the 🦒 Bioimage Model Zoo 🫶 @ai4life.bsky.social

🔗 Have a look at: bioimage.io#/models

As usual, they are accesible from BiaPy's GUI 🖥️, Colab notebooks 📔 and our API 🤓

🚀 Manual mask annotation slowing you down?
💡 SAMJ is a new ImageJ/Fiji plugin using Segment Anything (SAM) for fast, interactive segmentation — no GPU needed, one-click install, real-time results.
🔬 Perfect for large biomedical images.
arxiv.org/abs/2506.02783
#AI #Bioimaging #ImageJ #OpenSource

@ai4life.bsky.social & @eu-openscreen.bsky.social link highlighted in the isciii eu infrastructures for health event

We released version 1.6 of micro_sam:
- Improvements for automatic tracking.
- A new experimental mode for object classification.
- **New versions of the LM and EM models**
The models fix artifacts in automatic segmentation, see old vs. new prediction and better 3D segmentation results due to it.

InterpolAI is an optical flow tool to restore and replace input images for enhanced 3D imaging.

Here is a mouse lung where 6 out of 7 light-sheet images were missing or photobleached. We used InterpolAI to reconstruct.

More about InterpolaAI here: www.nature.com/articles/s41...

Spotiflow: accurate and efficient spot detection for fluorescence microscopy with deep stereographic flow regression - Nature Methods Spotiflow uses deep learning for subpixel-accurate spot detection in diverse 2D and 3D images. The improved accuracy offered by Spotiflow enables improved biological insights in both iST and live imag...

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. www.nature.com/articles/s41...

Researcher Positions Currently, the Finnish Cancer Institute has nine researcher positions funded by the Cancer Foundation Finland and the K. Albin Johansson Foundation. The Finnish Cancer Institute handles the selection ...

Delighted to share that I will start a five-year K. Albin Johansson Research Professorship next year. I am deeply honored to have been selected for this position. Many thanks to the Finnish Cancer Institute and the K. Albin Johansson Foundation 🙏
www.syopainstituutti.com/researcher-p...

Segment any MRI, CTscan, histology, transcriptomic image using CODA using Prof. Kiemen's CODAvision.

CODAvision enhances the usability of the CODA algorithm to automatically generating quantitative results and comprehensive reports.

More here: www.biorxiv.org/content/10.1...

InterpolaAI, based on deep learning-based optical flow, restores and interpolates sparse image stacks.

This first example is a stack of histological images of a human pancreatic duct.

6 out of 7 images were missing or defective, all now generated.

Download here: www.nature.com/articles/s41...

Can you go from protein sequence to a generated image of protein localization? New work from the Uhler lab says yes, and it is generalizable to unseen proteins and more than one cell type. I'm excited for work moving us toward virtual cell models.

Inauguramos el Hospital Universitario de Melilla con 265 camas, cirugía robótica, resonancia, cámara hiperbárica, hemodinámica y UCI pediátrica. La mayor dotación de personal de la sanidad melillense: 1.100 profesionales que contarán con los medios y las condiciones que merecen.

My office for the day… Quite an honor I must say…

This work is part of the results from my sabbatical stay at Prof. Denis Wirtz’s lab at Johns Hopkins during the 2022–2023 academic year. Very grateful to have been part of this exciting collaboration—congrats to the team on the Nature Methods publication!

Prou (ex-)supervisor & (always) mentor of @ai4life.bsky.social @egomezm.bsky.social Teresa Zulueta Coarasa; @danifranco93.bsky.social @cfusterbarcelo.bsky.social Carlos Garcia Lopez de Haro @uc3m @cienciauc3m

InterpolAI accurately generates synthetic images between real image pairs to help restore tissue damage and reduce stitching artifacts across different imaging modalities. Shows that deep learning can understand data to intelligently fill in the gaps.

Scientific research, working for everyone.

InterpolAI: deep learning-based optical flow interpolation and restoration of biomedical images for improved 3D tissue mapping Nature Methods - InterpolAI leverages optimal flow-based artificial intelligence to produce synthetic images between pairs of images for diverse three-dimensional image types. InterpolAI is more...

Dream Police alert: InterpolAI for enhanced 3D imaging (CODA, MRI, EM, confocal).

Read about and InterpolAI here: www.nature.com/articles/s41...

Very excited about this paper that came online today! InterpolAI can predict missing image data from light microscopy to H&E to MRI for improved volumetric imaging and image analysis.

🧠 AI4Life wouldn’t be the same without the amazing BioImage.IO community partners!
Now showcasing real-world tools from our partners: DeepIcy, @biapyx.bsky.social, SpotMAX and QuPath.

Huge thanks to our collaborators!

🔧 Time for our tech-savvy crowd!
The afternoon kicks off with a workshop for developers and image analysts: creating, uploading, containerising, and deploying models like a pro.

🧩 The dream: FAIR models and data. Only standards can solve the MxN problem, and this session is exactly about that. And we wrap up today’s workshops with a group reflection:
Why are FAIR resources essential for scientific progress?