🧠 In #connectomics, artificial neural networks analyze biological ones, but large-scale benchmarks have been lacking. We introduce NISB - the Neuron Instance Segmentation Benchmark, generated with novel 3D diffusion models!
1/2
Proofreading connectomes still costs billions 💸. NISB will drive measurable progress in #ML segmentation with
- 9 diverse synthetic datasets
- 100x more voxel-perfect ground truth
- Accessible evaluation
Compete by 31 Dec 2024! 🏆 structuralneurobiologylab.gi…
2/2
We launched NISB to make #connectomics neuron segmentation progress measurable. 📈 First submission — straight to the top 🏆
@dstevewei: 59.6% NERL vs our baseline's 43.0%. Congrats! 👏
~40% of neuron length still unaccounted for. Rolling submissions 👉 structuralneurobiologylab.gi…
Can generative AI accelerate neuroscience? Excited to share MoGen at ICLR 2026!🧠
We use point cloud flow matching to generate high-fidelity 3D neuron fragments, capturing intricate details like dendritic spines.
By improving automated reconstruction through synthetic data augmentation, MoGen is estimated to save over 157 person-years of manual proofreading labor for a full mouse brain connectome.
🔗 mogen-release.web.app/
With @janmatthis, Viren Jain & @michalj
Franz Rieger retweeted
Replying to @E11BIO
@E11BIO is excited to unveil PRISM technology for mapping brain wiring with simple light microscopes. Today, brain mapping in humans and other mammals is bottlenecked by accurate neuron tracing. PRISM uses molecular ID codes and AI to help neurons trace themselves. We discovered a new cell barcoding approach exceeding comparable methods by more than 750x. This is the heart of PRISM. We integrated this capability with microscopy and AI image analysis to automatically trace neurons at high resolution and annotate them with molecular features.
This is a key advance towards economically viable brain mapping - 95% of costs stem from neuron tracing. It is also an important step towards democratizing neuron tracing for everyday neuroscience. Solving these problems is critical for curing brain disorders, building safer and human-like AI, and even simulating brain function.
In our first pilot study, we acquired a unique dataset in mouse hippocampus. Barcodes improved the accuracy of tracing genetically labelled neurons by 8x – with a clear path to 100x or more. They also permit tracing across spatial gaps – essential for mitigating tissue section loss in whole-brain scaling. Using molecular annotation, we uncover an intriguing feature of synaptic organization, demonstrating how PRISM can be used for systematic discovery 🧵
Franz Rieger retweeted
Excited to announce the release of the first #basalganglia connectomes together with a major update of our SyConn connectomics pipeline syconn.esc.mpcdf.mpg.de/, out today in @naturemethods nature.com/articles/s41592-0…!



