arXiv Computer Vision
SkNeXt enables topology-guided neuronal reconstruction from petabyte-scale microscopy data
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 1
CORAL: A Benchmark for Structure-aware and Brain-wide Neuron Reconstruction in Light Microscopy
arXiv:2608.30768v1 Announce Type: new Abstract: Automatic neuron reconstruction from light microscopy images is a central problem in computational neuroanatomy. While recent methods have achieved enc...
Hugging Face Trending Papers
Aug 31
CORAL: A Benchmark for Structure-aware and Brain-wide Neuron Reconstruction in Light Microscopy
Automatic neuron reconstruction from light microscopy images is a central problem in computational neuroanatomy. While recent methods have achieved encouraging results on local image blocks, it remain...
arXiv AI
Aug 11
NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentation
arXiv:2608. 09636v1 Announce Type: cross Abstract: Accurate 3D neuron segmentation in fluorescence microscopy is critical for neuroscience.
arXiv Computer Vision
Sep 21
Catena: A Comprehensive Software Suite for Large-Scale Connectomics
Catena is an open‑source, developer‑centric software suite designed to streamline large‑scale connectomics from electron microscopy data. It integrates modules for 3D neuron and organelle segmentation, synapse detection, microtubule tracking, and neurotransmitter inference into composable, chunk‑wise pipelines that are fully documented and extensible. The suite includes pretrained machine learning models, containerized runtimes, and shareable components to reduce compute and ground‑truth data needs while ensuring reproducible, scalable processing across workstations and clusters.
arXiv AI
5d ago
Atelier: Learning Local Self-Supervised Features for CryoEM Volumes via Hypernetworks
Atelier is a self‑supervised framework that uses a transformer‑based hypernetwork to generate implicit neural representations (INRs) for cryo‑EM maps, enabling efficient, scale‑agnostic, coordinate‑conditioned feature extraction. Trained on 5,439 maps from the Electron Microscopy Data Bank, the pretrained INR provides continuous local feature fields that can be used as auxiliary channels for a 3D nested U‑Net, improving voxel‑level property prediction across eight tasks compared to a volume‑only baseline. The approach demonstrates that amortized INRs can serve as a geometry‑aware primitive for large‑scale cryo‑EM analysis.
arXiv AI
Jun 16
Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks
arXiv:2606. 14975v1 Announce Type: cross Abstract: How the wiring and functional organization of cortex shape recurrent computation remains a central question in both neuroscience and machine learning.