Daniel Xenes
A5063528195- Cell Image Analysis Techniques
- Advanced Electron Microscopy Techniques and Applications
- Machine Learning in Materials Science
- Scientific Computing and Data Management
- Functional Brain Connectivity Studies
- Advanced Fluorescence Microscopy Techniques
- Advanced Software Engineering Methodologies
- COVID-19 diagnosis using AI
- Embedded Systems Design Techniques
- Modular Robots and Swarm Intelligence
- Neuroinflammation and Neurodegeneration Mechanisms
- Machine Learning in Healthcare
- Distributed and Parallel Computing Systems
- Neural dynamics and brain function
- Artificial Intelligence in Healthcare and Education
- Neuroscience and Neuropharmacology Research
- Algorithms and Data Compression
- Advanced Data Storage Technologies
- Cloud Computing and Resource Management
- Software System Performance and Reliability
- Electron and X-Ray Spectroscopy Techniques
- Single-cell and spatial transcriptomics
- AI in cancer detection
- Image and Signal Denoising Methods
- Advanced Data Compression Techniques
Johns Hopkins University Applied Physics Laboratory
2019-2025
Johns Hopkins University
2022-2024
Allen Institute
2021
Allen Institute for Brain Science
2021
Earth Resources Technology (United States)
2020
Abstract Understanding the brain requires understanding neurons’ functional responses to circuit architecture shaping them. Here we introduce MICrONS connectomics dataset with dense calcium imaging of around 75,000 neurons in primary visual cortex (VISp) and higher areas (VISrl, VISal VISlm) an awake mouse that is viewing natural synthetic stimuli. These data are co-registered electron microscopy reconstruction containing more than 200,000 cells 0.5 billion synapses. Proofreading a subset...
We are in the era of millimetre-scale electron microscopy volumes collected at nanometre resolution1,2. Dense reconstruction cellular compartments these has been enabled by recent advances machine learning3-6. Automated segmentation methods produce exceptionally accurate reconstructions cells, but post hoc proofreading is still required to generate large connectomes that free merge and split errors. The elaborate 3D meshes neurons contain detailed morphological information multiple scales,...
Abstract Advances in electron microscopy, image segmentation and computational infrastructure have given rise to large-scale richly annotated connectomic datasets, which are increasingly shared across communities. To enable collaboration, users need be able concurrently create annotations correct errors the automated by proofreading. In large every proofreading edit relabels cell identities of millions voxels thousands like synapses. For analysis, require immediate reproducible access this...
Abstract To understand the brain we must relate neurons’ functional responses to circuit architecture that shapes them. Here, present a large connectomics dataset with dense calcium imaging of millimeter scale volume. We recorded activity from approximately 75,000 neurons in primary visual cortex (VISp) and three higher areas (VISrl, VISal VISlm) an awake mouse viewing natural movies synthetic stimuli. The data were co-registered volumetric electron microscopy (EM) reconstruction containing...
Technological advances in imaging and data acquisition are leading to the development of petabyte-scale neuroscience image datasets. These large-scale volumetric datasets pose unique challenges since analyses often span entire volume, requiring a unified platform access it. In this paper, we describe Brain Observatory Storage Service Database (BossDB), cloud-based solution for storing accessing petascale BossDB provides support ingest, storage, visualization, sharing through RESTful...
Abstract Advances in Electron Microscopy, image segmentation and computational infrastructure have given rise to large-scale richly annotated connectomic datasets which are increasingly shared across communities. To enable collaboration, users need be able concurrently create new annotations correct errors the automated by proofreading. In large datasets, every proofreading edit relabels cell identities of millions voxels thousands like synapses. For analysis, require immediate reproducible...
We are now in the era of millimeter-scale electron microscopy (EM) volumes collected at nanometer resolution (Shapson-Coe et al., 2021; Consortium 2021). Dense reconstruction cellular compartments these EM has been enabled by recent advances Machine Learning (ML) (Lee 2017; Wu Lu Macrina Automated segmentation methods produce exceptionally accurate reconstructions cells, but post-hoc proofreading is still required to generate large connectomes free merge and split errors. The elaborate 3-D...
ABSTRACT The development of novel imaging platforms has improved our ability to collect and analyze large three-dimensional (3D) biological datasets. Advances in computing have led an extract complex spatial information from these data, such as the composition, morphology, interactions multi-cellular structures, rare events, integration multi-modal features combining anatomical, molecular, transcriptomic (among other) information. Yet, accuracy quantitative results is intrinsically limited...
1. Abstract NeuVue is a software platform created for large-scale proofreading of machine segmentation and neural circuit reconstruction in high-resolution electron microscopy connectomics datasets. The provides robust web-based interface proofreaders to collaboratively view, annotate, edit connectivity data. A backend queuing service organizes proofreader tasks into purpose-driven task types increases throughput by limiting actions simple, atomic operations. collection analytical...
Abstract As clinicians are faced with a deluge of clinical data, data science can play an important role in highlighting key features driving patient outcomes, aiding the development new hypotheses. Insight derived from machine learning serve as support tool by connecting care providers reliable results big analysis that identify previously undetected patterns. In this work, we show example collaboration between and scientists during COVID-19 pandemic, identifying sub-groups patients...
Connectomics provides essential nanometer-resolution, synapse-level maps of neural circuits to understand brain activity and behavior. However, few researchers have access the high-throughput electron microscopes necessary generate enough data for whole circuit or reconstruction. To date, machine-learning methods been used after collection images by microscopy (EM) accelerate improve neuronal segmentation, synapse reconstruction other analysis. With computational improvements in processing...
As neuroimagery datasets continue to grow in size, the complexity of data analyses can require a detailed understanding and implementation systems computer science for storage, access, processing, sharing. Currently, several general standards (e.g., Zarr, HDF5, precomputed) purpose-built ecosystems BossDB, CloudVolume, DVID, Knossos) exist. Each these has advantages limitations is most appropriate different use cases. Using that don't fit into RAM this heterogeneous environment challenging,...
The immense scale and complexity of neuronal electron microscopy (EM) datasets pose significant challenges in data processing, validation, interpretation, necessitating the development efficient, automated, scalable error-detection methodologies. This paper proposes a novel approach that employs mesh processing techniques to identify potential error locations near tips. Error detection at tips is particularly important challenge since these errors usually indicate many synapses are falsely...
Abstract As neuroscience datasets continue to grow in size, the complexity of data analyses can require a detailed understanding and implementation systems computer science for storage, access, processing, sharing. Currently, several general standards (e.g., Zarr, HDF5, precompute, tensorstore) purpose-built ecosystems BossDB, CloudVolume, DVID, Knossos) exist. Each these has advantages limitations is most appropriate different use cases. Using that don’t fit into RAM this heterogeneous...
Abstract The ongoing pursuit to map detailed brain structures at high resolution using electron microscopy (EM) has led advancements in imaging that enable the generation of connectomic volumes have reached petabyte scale and are soon expected reach exascale for whole mouse collections. To tackle costs managing these large-scale datasets, we developed a data compression approach employing Variational Autoencoders (VAEs) significantly reduce storage requirements. Due their ability capture...
Neuroscientists are collecting Electron Microscopy (EM) datasets at increasingly faster rates. This modality offers an unprecedented map of brain structure the resolution individual neurons and their synaptic connections. Despite sophisticated image processing algorithms such as Flood Filling Networks, these huge often require large amounts hand-labeled data for algorithm training, followed by significant human proofreading. Many challenges common across neuroscience modalities (and in other...
Abstract As clinicians are faced with a deluge of new information, data science can play key role in highlighting features towards developing clinical hypotheses. Indeed, insights derived from machine learning serve as support tool by connecting care providers results big analysis to identify latent patterns that may not be easily detected even skilled human observers. In this work, we show an example collaboration between and scientists during the COVID-19 pandemic, identifying subgroups...