Alex Kalinin
@alxndrkalinin.bsky.social
AI/ML for cell image analysis @biohub.org | prev Broad Institute, CUHK-SZ & UMich
Pinned
Alex Kalinin
@alxndrkalinin.bsky.social
· Jul 10
🔬🤖 Introducing Spotlight: virtual staining (VS) improved by focusing on cells
VS models often learn to predict both cells and noisy background, because training treats all pixels equally. We address this by explicitly training models to prioritize foreground.
1/5
VS models often learn to predict both cells and noisy background, because training treats all pixels equally. We address this by explicitly training models to prioritize foreground.
1/5
Reposted by Alex Kalinin
A game changer in our hands... www.nature.com/articles/s41...
Universal consensus 3D segmentation of cells from 2D segmented stacks - Nature Methods
u-Segment3D is a universal framework that translates and enhances 2D instance segmentations to a 3D consensus instance segmentation without training data. It performs well across diverse datasets, inc...
www.nature.com
November 11, 2025 at 6:48 PM
A game changer in our hands... www.nature.com/articles/s41...
Reposted by Alex Kalinin
Janelia is hosting a course on DL for bioimage analysis www.janelia.org/you-janelia/...
Deep Learning for Microscopy Image Analysis
Topics The following will be covered extensively during lectures, exercises, and project work: Image denoising and restoration (fully supervised and self-supervised) Image translation (e.g.,
www.janelia.org
November 6, 2025 at 5:02 PM
Janelia is hosting a course on DL for bioimage analysis www.janelia.org/you-janelia/...
Today is the last chance to register for #CytoData2025. Don’t miss a fantastic program covering the full spectrum of image-based profiling!
cytodata25.eu-openscreen.eu
cytodata25.eu-openscreen.eu
October 31, 2025 at 5:25 PM
Today is the last chance to register for #CytoData2025. Don’t miss a fantastic program covering the full spectrum of image-based profiling!
cytodata25.eu-openscreen.eu
cytodata25.eu-openscreen.eu
💡Just presented our new paper at the @iccv.bsky.social BioImage Computing workshop: cubic: CUDA-accelerated 3D Bioimage Computing. We introduce a simple way to add GPU acceleration to scikit-image–based bioimage processing pipelines by swapping import statements. 🧵
1/6 #iccv2025
1/6 #iccv2025
October 23, 2025 at 6:01 PM
💡Just presented our new paper at the @iccv.bsky.social BioImage Computing workshop: cubic: CUDA-accelerated 3D Bioimage Computing. We introduce a simple way to add GPU acceleration to scikit-image–based bioimage processing pipelines by swapping import statements. 🧵
1/6 #iccv2025
1/6 #iccv2025
Reposted by Alex Kalinin
Segment large images without tiling artifacts: sharing our work that should have been presented at ICCV in 2 weeks - the brilliant first author Elena can’t go because of visa issues.
The paper: arxiv.org/abs/2503.19545 1/🧵
The paper: arxiv.org/abs/2503.19545 1/🧵
October 9, 2025 at 12:56 PM
Segment large images without tiling artifacts: sharing our work that should have been presented at ICCV in 2 weeks - the brilliant first author Elena can’t go because of visa issues.
The paper: arxiv.org/abs/2503.19545 1/🧵
The paper: arxiv.org/abs/2503.19545 1/🧵
Reposted by Alex Kalinin
Morph Map is now published in Nature Methods. Excited to see what the community discovers with this resource mapping ~15,000 human genes!
rdcu.be/ezGre
rdcu.be/ezGre
August 7, 2025 at 1:36 PM
Morph Map is now published in Nature Methods. Excited to see what the community discovers with this resource mapping ~15,000 human genes!
rdcu.be/ezGre
rdcu.be/ezGre
Reposted by Alex Kalinin
September 10, 2025 at 3:26 PM
🔬🤖 Introducing Spotlight: virtual staining (VS) improved by focusing on cells
VS models often learn to predict both cells and noisy background, because training treats all pixels equally. We address this by explicitly training models to prioritize foreground.
1/5
VS models often learn to predict both cells and noisy background, because training treats all pixels equally. We address this by explicitly training models to prioritize foreground.
1/5
July 10, 2025 at 6:52 PM
🔬🤖 Introducing Spotlight: virtual staining (VS) improved by focusing on cells
VS models often learn to predict both cells and noisy background, because training treats all pixels equally. We address this by explicitly training models to prioritize foreground.
1/5
VS models often learn to predict both cells and noisy background, because training treats all pixels equally. We address this by explicitly training models to prioritize foreground.
1/5
🔬API-first feature extraction for image-based profiling workflows
If you need to obtain interpretable features from your segmented microscopy images, but want to do it in a fully automated way, we know the struggle.
1/6
If you need to obtain interpretable features from your segmented microscopy images, but want to do it in a fully automated way, we know the struggle.
1/6
July 8, 2025 at 7:22 PM
🔬API-first feature extraction for image-based profiling workflows
If you need to obtain interpretable features from your segmented microscopy images, but want to do it in a fully automated way, we know the struggle.
1/6
If you need to obtain interpretable features from your segmented microscopy images, but want to do it in a fully automated way, we know the struggle.
1/6
Reposted by Alex Kalinin
If you’re interested in single cell data analysis, come give Image based profiles a try! Huge dataset being made available for exploration at this hackathon (+ symposium):
Berlin, November cytodata25.eu-openscreen.eu
Berlin, November cytodata25.eu-openscreen.eu
July 2, 2025 at 12:56 PM
If you’re interested in single cell data analysis, come give Image based profiles a try! Huge dataset being made available for exploration at this hackathon (+ symposium):
Berlin, November cytodata25.eu-openscreen.eu
Berlin, November cytodata25.eu-openscreen.eu
Reposted by Alex Kalinin
The 2nd AI4Life Challenge is live!
Calling the AI & bioimaging community to tackle a key microscopy challenge: removing noise while preserving detail.
📦 Paired noisy/clean datasets
📈 Ground-truth evaluation
🧠 DL focus
Build, test, compete 👉 ai4life.eurobioimaging.eu/challenge-2/
Calling the AI & bioimaging community to tackle a key microscopy challenge: removing noise while preserving detail.
📦 Paired noisy/clean datasets
📈 Ground-truth evaluation
🧠 DL focus
Build, test, compete 👉 ai4life.eurobioimaging.eu/challenge-2/
June 27, 2025 at 1:33 PM
The 2nd AI4Life Challenge is live!
Calling the AI & bioimaging community to tackle a key microscopy challenge: removing noise while preserving detail.
📦 Paired noisy/clean datasets
📈 Ground-truth evaluation
🧠 DL focus
Build, test, compete 👉 ai4life.eurobioimaging.eu/challenge-2/
Calling the AI & bioimaging community to tackle a key microscopy challenge: removing noise while preserving detail.
📦 Paired noisy/clean datasets
📈 Ground-truth evaluation
🧠 DL focus
Build, test, compete 👉 ai4life.eurobioimaging.eu/challenge-2/
There is still time to submit an abstract to CytoData 2025!
🌟 𝗥𝗲𝗺𝗶𝗻𝗱𝗲𝗿 🌟
The deadline for abstract submissions for oral presentations at Cytodata 2025 in Berlin is approaching!
👉 𝗦𝘂𝗯𝗺𝗶𝘁 𝘆𝗼𝘂𝗿 𝗮𝗯𝘀𝘁𝗿𝗮𝗰𝘁 𝗯𝘆 𝗝𝘂𝗻𝗲 25!
cytodata25.eu-openscreen.eu/registration/
#BerlinConference #Imageanalysis #Microscopy
The deadline for abstract submissions for oral presentations at Cytodata 2025 in Berlin is approaching!
👉 𝗦𝘂𝗯𝗺𝗶𝘁 𝘆𝗼𝘂𝗿 𝗮𝗯𝘀𝘁𝗿𝗮𝗰𝘁 𝗯𝘆 𝗝𝘂𝗻𝗲 25!
cytodata25.eu-openscreen.eu/registration/
#BerlinConference #Imageanalysis #Microscopy
June 23, 2025 at 4:36 PM
There is still time to submit an abstract to CytoData 2025!
Reposted by Alex Kalinin
The submission for 2025's BioImage Computing @iccv.bsky.social is now open. If things go like the last years, I am looking forward to all you brilliant submissions.
www.bioimagecomputing.com
www.bioimagecomputing.com
BioImage Computing
a truly interdisciplinary workshop
www.bioimagecomputing.com
June 10, 2025 at 9:40 PM
The submission for 2025's BioImage Computing @iccv.bsky.social is now open. If things go like the last years, I am looking forward to all you brilliant submissions.
www.bioimagecomputing.com
www.bioimagecomputing.com
🚨 New paper alert! We developed a versatile information retrieval framework that uses mean average precision (mAP) to robustly quantify sample activity and similarity in large-scale profiling data. Now out @natcomms.nature.com: doi.org/10.1038/s414...
More in the 🧵 below:
1/7
More in the 🧵 below:
1/7
A versatile information retrieval framework for evaluating profile strength and similarity - Nature Communications
Profiling assays measure thousands of features to uncover biological insights but lack reliable methods for quality evaluation. Here, the authors develop a versatile information retrieval framework to...
doi.org
June 10, 2025 at 7:54 PM
🚨 New paper alert! We developed a versatile information retrieval framework that uses mean average precision (mAP) to robustly quantify sample activity and similarity in large-scale profiling data. Now out @natcomms.nature.com: doi.org/10.1038/s414...
More in the 🧵 below:
1/7
More in the 🧵 below:
1/7
Reposted by Alex Kalinin
The #CVPR2025 main conference open access proceedings is up:
openaccess.thecvf.com/CVPR2025
Workshop papers will be posted shortly. Stay tuned...
openaccess.thecvf.com/CVPR2025
Workshop papers will be posted shortly. Stay tuned...
June 3, 2025 at 2:46 PM
The #CVPR2025 main conference open access proceedings is up:
openaccess.thecvf.com/CVPR2025
Workshop papers will be posted shortly. Stay tuned...
openaccess.thecvf.com/CVPR2025
Workshop papers will be posted shortly. Stay tuned...
Reposted by Alex Kalinin
Our work “AI4CellFate: Interpretable Early Cell Fate Prediction with Generative AI” is finally out in
@biorxivpreprint.bsky.social !!! 😍❤️ biorxiv.org/content/10.1... @scilifelab.se , @crick.ac.uk . More about it in the thread #AI4CellFate (1/n)⬇️
@biorxivpreprint.bsky.social !!! 😍❤️ biorxiv.org/content/10.1... @scilifelab.se , @crick.ac.uk . More about it in the thread #AI4CellFate (1/n)⬇️
May 14, 2025 at 10:26 AM
Our work “AI4CellFate: Interpretable Early Cell Fate Prediction with Generative AI” is finally out in
@biorxivpreprint.bsky.social !!! 😍❤️ biorxiv.org/content/10.1... @scilifelab.se , @crick.ac.uk . More about it in the thread #AI4CellFate (1/n)⬇️
@biorxivpreprint.bsky.social !!! 😍❤️ biorxiv.org/content/10.1... @scilifelab.se , @crick.ac.uk . More about it in the thread #AI4CellFate (1/n)⬇️
Reposted by Alex Kalinin
Lovely article from our colleague Kseniia Petrova, who has been wrongfully imprisoned for months: www.nytimes.com/2025/05/13/o...
Opinion | The Science I Would Be Doing if I Weren’t in ICE Detention
www.nytimes.com
May 13, 2025 at 12:33 PM
Lovely article from our colleague Kseniia Petrova, who has been wrongfully imprisoned for months: www.nytimes.com/2025/05/13/o...
CytoData is going to Berlin this November! Submit an abstract for oral presentation by June 25, 2025.
Join us in Berlin for CytoData 2025!
👉 Info & registration: cytodata25.eu-openscreen.eu
🔬 Hackathon: Nov 17–19
📢 Symposium: Nov 20–21
Explore advancements in image-based profiling & high-content screening and Tackle real-world challenges using EU-OPENSCREEN data.
👉 Info & registration: cytodata25.eu-openscreen.eu
🔬 Hackathon: Nov 17–19
📢 Symposium: Nov 20–21
Explore advancements in image-based profiling & high-content screening and Tackle real-world challenges using EU-OPENSCREEN data.
May 6, 2025 at 3:11 PM
CytoData is going to Berlin this November! Submit an abstract for oral presentation by June 25, 2025.
Turns out Transformers do outperform Cellpose when trained by Marius and Carsen 😄 Super exiting to see this being released and can't wait to try it out on our data!
🚀🔬🦠 Releasing 🤖Cellpose-SAM🤖, a cellular segmentation algorithm with superhuman generalization 🦸♀️. Try it now on 🤗 huggingface.co/spaces/mouse...
paper: www.biorxiv.org/content/10.1...
w/ @computingnature.bsky.social 1/n
paper: www.biorxiv.org/content/10.1...
w/ @computingnature.bsky.social 1/n
May 5, 2025 at 5:33 PM
Turns out Transformers do outperform Cellpose when trained by Marius and Carsen 😄 Super exiting to see this being released and can't wait to try it out on our data!
Reposted by Alex Kalinin
🌟 Call for Proposals: Host CytoData 2026! 🌟
We invite North American institutions to submit proposals for the 2026 symposium, whether in-person or hybrid. Nominate your institution by September 1, 2025. Join us in shaping the future of image-based profiling!
docs.google.com/forms/d/e/1F...
We invite North American institutions to submit proposals for the 2026 symposium, whether in-person or hybrid. Nominate your institution by September 1, 2025. Join us in shaping the future of image-based profiling!
docs.google.com/forms/d/e/1F...
April 9, 2025 at 10:47 AM
🌟 Call for Proposals: Host CytoData 2026! 🌟
We invite North American institutions to submit proposals for the 2026 symposium, whether in-person or hybrid. Nominate your institution by September 1, 2025. Join us in shaping the future of image-based profiling!
docs.google.com/forms/d/e/1F...
We invite North American institutions to submit proposals for the 2026 symposium, whether in-person or hybrid. Nominate your institution by September 1, 2025. Join us in shaping the future of image-based profiling!
docs.google.com/forms/d/e/1F...
Reposted by Alex Kalinin
👋 We are CytoData Society (CytoDS)! 🌟 We build and maintain an active community around image-based profiling of biological phenotypes induced by genetic, chemical, or other perturbations of biological systems. Join us to explore, share, and innovate together! #CytoData #Community
March 31, 2025 at 12:01 PM
👋 We are CytoData Society (CytoDS)! 🌟 We build and maintain an active community around image-based profiling of biological phenotypes induced by genetic, chemical, or other perturbations of biological systems. Join us to explore, share, and innovate together! #CytoData #Community
Reposted by Alex Kalinin
Great to see that many noise2void inspired denoising algorithms have been ported to @pytorch.org! Kudos to @florianjug.bsky.social and many others ...
github.com/CAREamics/ca...
github.com/CAREamics/ca...
GitHub - CAREamics/careamics: A deep-learning library for denoising images using Noise2Void and friends (CARE, PN2V, HDN etc.), with a focus on user-experience and documentation.)
A deep-learning library for denoising images using Noise2Void and friends (CARE, PN2V, HDN etc.), with a focus on user-experience and documentation.) - CAREamics/careamics
github.com
March 31, 2025 at 9:38 AM
Great to see that many noise2void inspired denoising algorithms have been ported to @pytorch.org! Kudos to @florianjug.bsky.social and many others ...
github.com/CAREamics/ca...
github.com/CAREamics/ca...
Reposted by Alex Kalinin
This summer, we are running a one-week intensive workshop on Python-based BioImage Analysis.
Are there better ways to spend 6 days in mid-July in Boston?Probably.
Would you learn as much as you will here? Probably not.
Apply here:
iac.hms.harvard.edu/bobiac/2025
Are there better ways to spend 6 days in mid-July in Boston?Probably.
Would you learn as much as you will here? Probably not.
Apply here:
iac.hms.harvard.edu/bobiac/2025
March 24, 2025 at 10:03 PM
This summer, we are running a one-week intensive workshop on Python-based BioImage Analysis.
Are there better ways to spend 6 days in mid-July in Boston?Probably.
Would you learn as much as you will here? Probably not.
Apply here:
iac.hms.harvard.edu/bobiac/2025
Are there better ways to spend 6 days in mid-July in Boston?Probably.
Would you learn as much as you will here? Probably not.
Apply here:
iac.hms.harvard.edu/bobiac/2025
Reposted by Alex Kalinin
Inexplicably, US administration has launched an unprecedented assault on science, on research institutions & on vital international organizations & initiatives.
An assault on science anywhere is an assault on science everywhere; the global community must unite
🧪
www.nature.com/articles/d41...
An assault on science anywhere is an assault on science everywhere; the global community must unite
🧪
www.nature.com/articles/d41...
Trump 2.0: an assault on science anywhere is an assault on science everywhere
US President Donald Trump is taking a wrecking ball to science and to international institutions. The global research community must take a stand against these attacks.
www.nature.com
February 25, 2025 at 7:48 PM
Inexplicably, US administration has launched an unprecedented assault on science, on research institutions & on vital international organizations & initiatives.
An assault on science anywhere is an assault on science everywhere; the global community must unite
🧪
www.nature.com/articles/d41...
An assault on science anywhere is an assault on science everywhere; the global community must unite
🧪
www.nature.com/articles/d41...
Reposted by Alex Kalinin
📢 Submissions are now open for the CellMap Segmentation Challenge.
Build the best method for segmenting cellular organelles in vEM using our 289 annotated volumes, 40 organelle classes, and 22 diverse cell and tissue types.
🔗 hhmi.news/410evJQ
Build the best method for segmenting cellular organelles in vEM using our 289 annotated volumes, 40 organelle classes, and 22 diverse cell and tissue types.
🔗 hhmi.news/410evJQ
February 5, 2025 at 4:09 PM
📢 Submissions are now open for the CellMap Segmentation Challenge.
Build the best method for segmenting cellular organelles in vEM using our 289 annotated volumes, 40 organelle classes, and 22 diverse cell and tissue types.
🔗 hhmi.news/410evJQ
Build the best method for segmenting cellular organelles in vEM using our 289 annotated volumes, 40 organelle classes, and 22 diverse cell and tissue types.
🔗 hhmi.news/410evJQ