Brian Northan
Contract Research and Development Engineer, Image Processing. XC skier. Stockade-athon 15 km Running Road Race Director.
- Reposted by Brian Northan🚨Gearing up for #NGFF 0.6! 🚨 Help us give this a final push over the finish line and join us in ironing out the last flaws on the way! More information here 👇 forum.image.sc/t/ngff-weekl...
- Reposted by Brian NorthanMy talk at the #I2K 2025 conference is now available online. There are also many other great talks worth checking out. My full talk is on their YouTube and includes a hands-on walkthrough of how to use VNC-Dist: youtu.be/ZxngGrqAr_Y?...
- Excited to share the 1st part of my PhD work in @plosone.org ! 🚀 Progress in biology needs not only new ideas but also #workflow_automation Open Access: 📃paper: journals.plos.org/plosone/arti... 💻Code: github.com/C-elegans-VN... #CellBiology #Neuroscience #DeepLearning #Bioimage_Analysis
- Reposted by Brian NorthanPfffffff. Chains of transformations are hard. It took me two releases to get the live deskew slider right and looking ok (hopefully) #bigvolumebrowser
- New video: more examples showing deep learning segmentation failure modes—and how to detect them with Napari. I show how Napari’s layer system compares images, ground truth, and results, and how Appose enables comparison across incompatible DL packages. www.youtube.com/watch?v=c369...
- Reposted by Brian NorthanWe're a bit late in ringing in the giving season, but it is indeed upon us. Enjoy our special edition holiday logo ☃️ and, if you can spare a bit and appreciate napari, please donate to our development efforts! 🙏 CZI will match donations up to $75K. opencollective.com/napari/donate
- If you use linkedin connect with @sabersaharkhiz.bsky.social he is posting some interesting material.
- If you’re interested in bioimage analysis tools, my LinkedIn post(s) are worth a read. #Bioimage_Analysis #Microscopy #CellBiology #AI4Microscopy
- Reposted by Brian NorthanI was invited by @focalplane.bsky.social to write a short description about it: focalplane.biologists.com/2025/12/12/a...
- I was searching for a Python utility for Fourier Ring/Shell Correlation. All I got in a blue sky search were 4 small posts from @christletx.bsky.social ... all I got from chatgpt was installation instructions for non-existent libraries and github repos... anyone know a good tool for this?
- Reposted by Brian Northan📢 After #CBIAS2025, join our hands-on 2-day napari training by @crick.ac.uk @ucl.ac.uk @liverpooluni.bsky.social From conda to plugins to Jupyter, practicals on real data with expert guidance. For Python/ImageJ coders. Apply by 1 Sept – limited to 30! crick.ac.uk/whats-on/cbias-napari-workshop-2025
- Reposted by Brian NorthanEpisode 11 - In which @erinweisbart.bsky.social and I talk about just how much we love ilastik (@ilastik-team.bsky.social) and how it's great for so many problems! Also, that you should use a small brush.
- Episode 10 - we've jumped an order of magnitude! Thanks for all the support, @erinweisbart.bsky.social and I totally appreciate it. If you have artifact-free data, you can skip this one; for us mere mortals, Erin talks about masks, alignment, and seeing how far from a mask an object is. So useful!
- Reposted by Brian NorthanThe 1st working version of my little @napari.org plugin (napari-czitools) is almost ready. It contains sample data, allows to read CZI metadata and can read CZI images (or parts of it) by using the sliders to crop what should be read. Still quite some things to improve ...
- Reposted by Brian NorthanCell tracking is never perfect, and it's important to understand the types of errors your solution contains. Here is my stab at this: Divisualisations in @napari.org. github.com/bentaculum/d... You spin tracks out upwards from the playing video. Green edges are correct, FP in magenta, FN in cyan.
- I just published a new video demonstrating how to use Pixi and Napari-Easy-Augment-Batch-DL for repeatable and reproducible deep learning segmentation. In this example, I use Pixi to set up a Python environment then launch Napari to explore and compare Cellpose3 and Micro-SAM. youtu.be/3ObAnSTBri8
- Great to see @alexhego.bsky.social share instructions on a DL pixel‑classification problem we worked on at image.sc. If you’re working on a challenging 3D DL semantic‑segmentation problem and need more options than most tools provide, check out this repository. github.com/AlexHego/DL-...
- Reposted by Brian NorthanBtw, and in the spirit of #OpenScience, all my #Napari #bioimage analysis #tutorials are freely available — from basics to #segmentation, #tracking, and #clustering. Feel free to explore and share ✌️ 🌍 www.fabriziomusacchio.com/teaching/tea...
- Reposted by Brian Northan🚀 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
- Reposted by Brian NorthanWe 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.
- Reposted by Brian NorthanNew ‘How to’ post on FocalPlane 🔬💻 Lea Kabjesz shares a step-by-step guide to get you started annotating 2D and 3D images in Cellpose, including video tutorials. focalplane.biologists.com/2025/06/05/a... #bioimageanalysis #cellpose #imaging #HowTo
- Reposted by Brian NorthanNeed help with bioimage analysis? Contact the UK Euro-BioImaging Node to see how we can help! www.eurobioimaging-access.eu/nodes/uk-node
- 🔬𝐔𝐊 𝐄𝐮𝐫𝐨-𝐁𝐢𝐨𝐈𝐦𝐚𝐠𝐢𝐧𝐠 𝐍𝐨𝐝𝐞 𝐬𝐞𝐜𝐮𝐫𝐞𝐬 £𝟏.𝟖𝐌 from @ukri.org This will: -Democratise access to cutting-edge biological and biomedical imaging -Support 200+ researchers yearly -Boost open science Thanks to BBSRC and MRC for this major upgrade! 🚀 Congrats to the entire UK Node team 👏 Link in replies⬇️
- Reposted by Brian NorthanWant to host your own AI models without relying on external infrastructure? Enter BioEngine ai4life.eurobioimaging.eu/announcing-b... Your go-to for flexible, self-hosted bioimage analysis. Open source, scalable, and built for you!
- I've started a thread on the imagesc forum about how ambiguous labels might affect deep learning models. If you've encountered mislabeled data, strange training artifacts, or examples where the former caused the latter — I'd love to hear your insights. forum.image.sc/t/are-we-see...
- Reposted by Brian NorthanWe've been trying nnInteractive (github.com/MIC-DKFZ/nap...) to quickly create labeled data for later training an Omnipose model. I whatever black magic you did there, keep at it! It's such a life-changer!
- Reposted by Brian NorthanReminder: if you go to the GloBIAS conference we can help you contribute to napari at the hackathon! A bunch of the team will be there! (Great thanks to the GloBIAS team for accommodating us!!!) More details on the conference website.
- Deadlines extended - you can still register for the GloBIAS conference! We have extended most deadlines. Please check our webpage: tinyurl.com/mr3kx5a5! Looking forward to welcoming you to Kobe, for training, developing and discussing a broad range of BIA topics!
- Reposted by Brian NorthanEpisode 5 - sure, most cells have one nucleus, but what happens when they DON'T? @erinweisbart.bsky.social and I try to get to the bottom of what on earth you can do when your cells and nuclei just don't match up on the latest episode of "Ask Erin/Dear Beth"
- Episode 4 - in which @erinweisbart.bsky.social and I fight the commonest @cellprofiler.bsky.social battle yet - with a million ways to read in your data, what is the right way for YOUR data? Shall a new hope arise? Will we find only one way to do things? Watch and find out!
- This is a nice overview of normalization techniques which are very important for deep learning training. It is pretty common that differences in the training and testing image intensity ranges lead to unpredictable errors so learning to troubleshoot normalization issues is very useful.
- Image normalization: trivial enough to automate, impactful enough to quietly sabotage your results. Here’s a Jupyter notebook I wrote on how, why & when normalization matters, feedback 💛ly welcome. 👇 haesleinhuepf.github.io/BioImageAnal...
- Reposted by Brian NorthanJust uploaded a simple script to run cellpose for cell segmentation on two-photon calcium imaging data and extract ΔF/F traces. It runs slower without a GPU, but still works well. Check it out and give it a try! github.com/dav1dcg/neur...
- Reposted by Brian NorthanWe are proudly hosting 𝐃𝐫. 𝐓𝐚𝐥𝐥𝐞𝐲 𝐋𝐚𝐦𝐛𝐞𝐫𝐭 @talley.codes (CITE, Harvard Medical School): 𝐒𝐢𝐦𝐮𝐥𝐚𝐭𝐢𝐧𝐠 𝐫𝐞𝐚𝐥𝐢𝐬𝐭𝐢𝐜 𝐥𝐢𝐠𝐡𝐭 𝐦𝐢𝐜𝐫𝐨𝐬𝐜𝐨𝐩𝐲 𝐢𝐦𝐚𝐠𝐞𝐬 𝐮𝐬𝐢𝐧𝐠 𝐦𝐢𝐜𝐫𝐨𝐬𝐢𝐦 When: 𝐌𝐚𝐲 𝟐𝟗𝐭𝐡 @ 𝟏𝟏 𝐚𝐦 𝐄𝐃𝐓 (Boston time) Join us on Zoom! harvard.zoom.us/j/9762343464...
- Reposted by Brian Northan💻 Apply to our beginner-friendly Boston Bioimage Analysis Course! Get started with Python and learn to analyze fluorescence microscopy images — no coding experience required! Fee waivers available thanks to funding from @bioimagingna.bsky.social! 🗓️ Apply June 1st! iac.hms.harvard.edu/bobiac/2025/
- Reposted by Brian NorthanWow, just implemented the new Cellpose-SAM from @computingnature.bsky.social in NimbusImage and it's *awesome*! Give it a try! nimbusimage.com
- Reposted by Brian NorthanWant to learn more about bioimage analysis and how to think like a bioimage analyst? Check out our bootcamp- applications close next week!
- BIG NEWS - for the first time ever, we're running a Bioimage Analysis Beginnings Bootcamp. Learn #bioimageanalysis from awesome folks, and gain familiarity with some new tools as well as how to pick the right tool in the first place. Aug 4th-8th - apply here (soon!) forms.gle/d2fCXsrWHVP8...
- Reposted by Brian NorthanSo excited and proud of everyone! 🎉 With this release I worked very hard to contribute to napari and learned so much along the way. I guess they want to keep me around, as I'm a core dev now! 🥳 Grateful for the entire image analysis community. 🥰
- Reposted by Brian NorthanIn case you were wondering where the "Tools" menu is gone in @napari.org 0.6.0, please update your environment using "pip install napari-assistant==0.6.0". Then just start "naparia" instead of "napari" from the terminal, while we are working on a better solution. github.com/haesleinhuep...
- Reposted by Brian NorthanStill plenty of time before first pitch to check out today’s new episode of Deep Left Field! Tremendous conversations with #Bluejays Anthony Santander and Brendon Little plus coach Mark Budzinski! Also, a look back at a week that was that started and ended awfully well, but in the middle - yuck.
- Reposted by Brian NorthanFinally BiaPy is out in Nature Methods! 🥳🥳🥳 A major milestone in my research! I'm incredibly proud of the progress made. Huge thanks to my PhD supervisors, @iarganda.bsky.social and @arratemunoz.bsky.social , for their invaluable guidance and support throughout this journey. Check out the thread🧵👇
- 🚀 Excited to share that our work on BiaPy has been published today in Nature Methods! BiaPy makes deep learning accessible for bioimage analysis, from small datasets to terabyte-scale 3D images. 👇 (1/7) 🔗 www.nature.com/articles/s41... #DeepLearning #BioimageAnalysis #OpenSource #BiaPy
- Reposted by Brian NorthanDuring the workshop earlier this week we discussed how important it is to inspect histograms of image regions in some projects. Thus, here comes stackview.histogram() - new in stackview 0.15.0 🥳 github.com/haesleinhuep...
- If you are looking to do GPU deconvolution in Fiji checkout the new updates to CLIJ (OpenCL for ImageJ) deconvolution. @nkiaru.bsky.social has done updates to the tiled deconvolution and integrated with BigDataViewer, and I've added a new script for batch processing. forum.image.sc/t/clij-openc...
- For the last couple of years I've been developing DL segmentation utilities, workflows and notebooks with the goal of making it easier to reproduce deep learning results. This new video shows how to run augmentation, training and prediction all inside Napari www.youtube.com/watch?v=ngps...
- Reposted by Brian NorthanThe OME Community Meeting, which has always be in Europe, will be at MBL this year! It's a unique opportunity for people this side of the pond who are working with open-source microscopy data. Travel grants available for NA-based folks until Feb 12th! www.bioimagingnorthamerica.org/events/ome-2...
- Reposted by Brian NorthanThere's a new wave of discussion to improve the clarity of Fiji's original menus and plugins. If you have opinions or suggestions to make, don't hesitate to participate on the forum! forum.image.sc/t/houseclean... #microscopy #imagej #fiji
- If anyone is interested in obtuse observations about 3D SIM reconstruction I've added some more figures to my thread on 3D SIM see here forum.image.sc/t/3d-sim-rec.... In particular I took a look at results from different stages of Open3DSIM github.com/Cao-ruijie/O...
- A very nice #MachineLearning example from Fiji Weka Segmentation. Was just playing with this plugin today on another problem and it works great.
- I started using #MachineLearning to classify images in #ImageJ : trainable #Weka Segmentation which is great! 3 cycles and I got this: However, the result image has one channel. Does anyone know how to split 5 (random) colors in #Fiji to make them single channels? #microscopy #imageanalysis #AI
- Reposted by Brian NorthanToday I would like to highlight one of our favorite DL-segmentation network: StarDist by @maweigert.bsky.social and colleagues. In my lab we love and use StarDist all the time github.com/stardist/sta... link.springer.com/chapter/10.1... #BioimageTooloftheDay
- Reposted by Brian NorthanContributing to this project has been very cool! Quick tip for anyone interested in cell segmentation: I started with StarDist but it failed to detect nuclei in samples with regions of very different cell density. Switched to DeepCell Mesmer and it worked like a charm!
- Just before the holidays, here is the latest from the Oricchio lab. In collaboration with the hemato-oncology team, we established a new model to test therapies on lymphoma patient samples by preserving the tissue composition and architecture of the original tumors. www.nature.com/articles/s41...
- Reposted by Brian NorthanFor people interested with a PyImageJ install also containing cellpose in the same environment, a singularity container (the file to build it) bound to 'da_tracker' is available on github now. A link to download the built container can be found as well on the main page. github.com/jaugenst/da_... 👇
- This week I tested pixel based machine learning using a Napari plugin written by @kephale.bsky.social , and posted a video of my experiments (interestingly Herbie G. may have beat both DL and ML with an ImageJ Macro on one of the test images) youtu.be/9rnNDkvVUyY
- Reposted by Brian NorthanTomorrow morning I will give a webinar talk + Q&A for the Microscopy Society of America. Tuesday 17 Dec at 8 am PT / 11 am ET. Registration free: microscopy.org/Events/detai...
- Reposted by Brian NorthanI just made a long overdue update to microfilm guiwitz.github.io/microfilm now 0.3.0! Beyond adaptations to recent Python and Matplotlib, I added support for the great cmap library cmap-docs.readthedocs.io by @talleylambert.bsky.social for easy access to the best (and most psychedelic) colormaps!1/2
- I finally got around to making a video about my utilities to render 3D projections in Jupyter notebooks. The code is useful but a bit rough so I also suggest taking a look at @guiwitz.bsky.social microfilm and @haesleinhuepf.bsky.social stackview as more polished options. youtu.be/9yOA8R03trE
- 1) I was looking for a basic Machine Learning pixel classification example the other day, and example '02' in this @haesleinhuepf.bsky.social repo is a nice starting point, simple, can get it running in few minutes, and great to start learning about the subject. github.com/BiAPoL/on_th...
- 2) If you are interested in more advanced Machine Learning pixel classification, check out ConvPaint (github.com/guiwitz/napa...) and @kephale.bsky.social 's Interactive Napari Machine Learning tutorial (github.com/kephale/napa...).
- Update. It looks like upgrading to Cellpose 3.1.0 solves some of the issues. 3.1.0 has new options for smoothing masks and the 3D mask generation is much faster. See this post forum.image.sc/t/cellpose-3.... Thanks @computingnature.neuromatch.social.ap.brid.gy and others for the new release.
- forum.image.sc/t/cellpose-3... Interesting forum question on 3D Cellpose that isn't answered yet. I played around a bit this morning but couldn't quite figure it out. Love to hear from others who work with 3D Cellpose (or other 3D segmentation methods)
- Reposted by Brian Northan#MicroscopeMonday by Raphael for our first post on bluesky here's our new image processing available on our OpenCID database: you can now directly run #denoise #deblur #upsample with the new version of cellpose on all your images thanks to the #cellpose team for their always top-notch dev
- forum.image.sc/t/cellpose-3... Interesting forum question on 3D Cellpose that isn't answered yet. I played around a bit this morning but couldn't quite figure it out. Love to hear from others who work with 3D Cellpose (or other 3D segmentation methods)
- Reposted by Brian NorthanThere's just over a month left to apply for our upcoming @royalmicrosoc.bsky.social Introduction to Image Analysis workshop with @martinjones.bsky.social and @lankylaste.bsky.social hosted by @kerrythompson8.bsky.social at @uniofgalway.bsky.social www.rms.org.uk/rms-event-ca...
- Reposted by Brian NorthanThere are also different implementations of the Tubeness Filter. One is already in ImageJ available ( Plugins › Analyze › Tubeness). The other in the amazing CLIJ2 library from @haesleinhuepf.bsky.social which I will surely feature various times again in the future.
- Reposted by Brian Northan#BIAToolTip No.13 A Must-Know: the amazing CLIJ2 library from @haesleinhuepf.bsky.social and its IJ macro extensions make image processing and analyses of 2D/3D images on the GPU a breeze and super flexible. Huge function repository, a very neat clij2 assistant and super easy to macro record.
- Reposted by Brian NorthanAre you interested in doing 3D microscopy? I will be showing on Dec 10 how I use high-resolution microscopy combined with 3D reconstruction to investigate neurodegeneration and neuroinflammation in the brain, especially with viral infections! Register here: register.gotowebinar.com/register/636...
- Reposted by Brian NorthanMy #BioimageTooloftheDay is an easy one: Cellpose by @computingnature.neuromatch.social.ap.brid.gy and colleagues An awesome DL-segmentation network to segment cells from microscopy images www.nature.com/articles/s41... When we do not use StarDist, we use Cellpose 😀
- Reposted by Brian NorthanStarting brand new on this platform, it's not to late to try our tool 'da_tracker', designed for quantitative single cell and single phagosome tracking, using PyImageJ, and Trackmate-Cellpose (So it's free): journals.biologists.com/bio/article/... Feel free to reach out if you need help to try it !
- Reposted by Brian Northan#BIAToolTip No.3 In this thread I will introduce several of the #biovoxxel figure tools for Fiji that allow you to prepare images for scientific figures in line with GSP and preserving image quality as well as data integrity 100% github.com/biovoxxel/Bi...
