"deepmriprep: VBM preprocessing via deep neural networks" is published in Nature Computational Science 🧠💻 🔗 Paper: rdcu.be/e1t4N VBM preprocessing in ~10 seconds per #brain image 🚀 🔗 GitHub: github.com/wwu-mmll/deepm… Install via "pip install deepmriprep"

Try "pip install flashrl" to make it even faster (on CPU and GPU). Write 6 lines of code to trains Pong in a few seconds!

After "pip install viiew" it also supports scrolling through your array/tensor/dataframe

🧐view(your_data) in the terminal🧐 "pip install viiew" for a - colorfull - scrollable - sortable view of your array/Tensor/DataFrame! Supports numpy, pandas, torch, jax & @__tinygrad__ and is tiny: 4.1kB (0 dependencies)!

Running RL was never easier! Here is the whole script run in the GIF

🚀 flashrl version 0.2.0 released 🚀 ✅ RL with millions of steps/second 💨 ✅ Play against your RL agent ⚔️ ✅ Wanna add your env? Add one .pyx file! ...and it uses emoji rendering 😙👌

🚀 Launching flashrl: RL in seconds 🚀 ✅ Train with ~3M steps per second 💨 ✅ Contains only ~200 lines of code 🤯 ✅ Wanna add your env? Add one .pyx file! Free your 🧠 RAM from boilerplate!

🧠 Releasing mriaug: Fast data augmentations for 3D MRIs! Useful for deep learning to ✅ Increase the amount training data ✅ Make models more robust wrt scanner effects 🔥 GPU-support -> 50x faster than torchio

🧠 niftiai is here! Training neural nets on 3D images just got way easier! Using #fastai it enables you to ✅ Train MRI classifiers in 15 lines ✅ Train UNets in 12 lines ✅ Easily view & augment 3D images 1. Dive into the Colab Tutorials 👀 2. pip install niftiai & try it 💻

🎉 Today I release #brain-stl 🎉 🧠 Turn your MRI into a 3D printable model 🖨️ Easily add custom text, adjust the tissue threshold and smooth the surface 🤯 Try the demo (non-programmer friendly) linked on GitHub (next post) or "pip install brain-stl"

📥 Download the zipped NiftiView.exe from github.com/codingfisch/nifti… or pip install niftiview-app YouTube-Tutorial: youtube.com/watch?v=YyVJ6JKJ… App: github.com/codingfisch/nifti… Widget: github.com/codingfisch/nifti… Underlying Python package: github.com/codingfisch/nifti…

🧠 Introducing NiftiView: A nifty 3D image viewer app 👨 Drag&Drop (.nii, .npy, .dcm..) files and save as GIF 👩‍💻 Use it via Python or CLI 👩‍⚕️ Adjust contrast via keyboard shortcuts 👨‍🔬 Overlay maps, colorbar..and save high quality figures, ready for publication 🔗 Links in reply

Additionally, by setting "Output Modalities" to "rbm" atlas registration can be applied for Region-based Morphometry (RBM) 🧠 The tissue volumes per atlas region are saved as CSVs, making them easily accessible 🗂️

deepmriprep streamlines processing of #MRI data, making it easier than ever ✨ 'deepmriprep-gui' will open a user-friendly GUI that takes @BIDSstandard directories, CSVs with filepaths or filepatterns as input 🖱️ In no time, everything's ready to go 💨 with GPU-acceleration 🔥

🧠 Exciting news for #neuroscience! Launching deepmriprep: Voxel-based Morphometry (VBM) preprocessing via neural networks in ~10 seconds per #brain image 🚀 🔗 Preprint: arxiv.org/abs/2408.10656 🔗 GitHub: github.com/wwu-mmll/deepmrip… Install via "pip install deepmriprep"

Additionally, a new version of the package is released today, providing an improved GUI 💪 🔧 Install it via 'pip install deepbet' 🙏 Big thanks to everyone at @TraPLabMS involved in this project, especially @TheRealTimHahn1 who supervised and secured the funding behind it 🤝

🧠 Publication Alert 🧠 Check out my new article introducing deepbet: A neural net-based tool for brain extraction of T1w MR images 🤖 Achieves top-tier results in ~1 second 🚀 🔗 Paper: sciencedirect.com/science/ar… 🔗 GitHub: github.com/wwu-mmll/deepbet

Additionally, a new version of the package is released today, providing an improved GUI 💪 🔧 Install it via 'pip install deepbet' 🙏 Big thanks to everyone at @TraPLabMS involved in this project, especially @TheRealTimHahn1 who supervised and secured the funding behind it 🤝

📢 Publication Alert 📢 Check out my new article introducing GateNet: A novel neural net architecture that enables automatic cytometry gating with human-level performance using <10 training samples 🚀 🔗 Paper: sciencedirect.com/science/ar… 🔗 GitHub: github.com/wwu-mmll/gatenet

Manual gating, the conventional approach, identifies cells by visually partitioning 2D scatter plots of measurements of all cells in a sample (e.g. blood)💉 As shown in the GIF, this (time consuming and subjectiv) partitioning has to be done individually for each sample 😴