Daniel Xenes

The paper introduces a method to estimate proofreading progress in connectomic datasets using global graph invariants, enabling optimal stopping points for reconstruction quality.

The paper maps physical cell-cell contacts in mouse visual cortex, revealing a dense contactome that exceeds synaptic connectivity and highlights the role of astrocytes in shaping the neural microenvironment.

SmartEM accelerates electron microscopy image acquisition by using machine learning to intelligently allocate imaging time, achieving up to 7-fold speedup in connectomic samples.

CAVE enables reproducible connectome analysis in large-scale datasets during ongoing annotation and proofreading.

NEURD automates proofreading and feature extraction from connectomics data to improve accuracy and accessibility of neural morphology analyses.

The paper presents a functional connectomics dataset of mouse visual cortex, combining calcium imaging with EM reconstruction to study neural circuits and their connectivity.

EM-Compressor uses Variational Autoencoders to compress EM images for connectomics, reducing data size to 1/128th while preserving features needed for segmentation.

This paper uses a generative AI model to improve 3D tissue imaging by interpolating and restoring images, enhancing resolution and reducing artifacts across multiple modalities and species.

This paper introduces a semi-automated pipeline for detecting mesh errors in neuronal EM data, improving the accuracy of connectomic reconstructions by highlighting potential inaccuracies near neuronal tips.

NeuVue is a framework for managing and prioritizing proofreading tasks in connectomic datasets, enabling scalable and coordinated error correction by over forty proofreaders.

The paper introduces a toolkit called intern to unify computational backends and abstract computer science challenges in neuroscience data analysis.