Browse
Submit Data
Databases
API
Help

Dataset Information

31 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

CEM500K, a large-scale heterogeneous unlabeled cellular electron microscopy image dataset for deep learning.

ABSTRACT: Automated segmentation of cellular electron microscopy (EM) datasets remains a challenge. Supervised deep learning (DL) methods that rely on region-of-interest (ROI) annotations yield models that fail to generalize to unrelated datasets. Newer unsupervised DL algorithms require relevant pre-training images, however, pre-training on currently available EM datasets is computationally expensive and shows little value for unseen biological contexts, as these datasets are large and homogeneous. To address this issue, we present CEM500K, a nimble 25 GB dataset of 0.5 × 10⁶ unique 2D cellular EM images curated from nearly 600 three-dimensional (3D) and 10,000 two-dimensional (2D) images from >100 unrelated imaging projects. We show that models pre-trained on CEM500K learn features that are biologically relevant and resilient to meaningful image augmentations. Critically, we evaluate transfer learning from these pre-trained models on six publicly available and one newly derived benchmark segmentation task and report state-of-the-art results on each. We release the CEM500K dataset, pre-trained models and curation pipeline for model building and further expansion by the EM community. Data and code are available at https://www.ebi.ac.uk/pdbe/emdb/empiar/entry/10592/ and https://git.io/JLLTz.

SUBMITTER: Conrad R

PROVIDER: S-EPMC8032397 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

CEM500K - A large-scale heterogeneous unlabeled cellular electron microscopy image dataset for deep learning.

Project description: Not available

| EMPIAR-10592 | biostudies-other

CEM1.5M : a cellular EM dataset containing ~1.5 x 106 unlabeled 2D image patches curated for deep learning

Project description: Not available

| EMPIAR-11035 | biostudies-other

EM-stellar: benchmarking deep learning for electron microscopy image segmentation.

Project description:MotivationThe inherent low contrast of electron microscopy (EM) datasets presents a significant challenge for rapid segmentation of cellular ultrastructures from EM data. This challenge is particularly prominent when working with high-resolution big-datasets that are now acquired using electron tomography and serial block-face imaging techniques. Deep learning (DL) methods offer an exciting opportunity to automate the segmentation process by learning from manual annotations of a small sample of EM data. While many DL methods are being rapidly adopted to segment EM data no benchmark analysis has been conducted on these methods to date.ResultsWe present EM-stellar, a platform that is hosted on Google Colab that can be used to benchmark the performance of a range of state-of-the-art DL methods on user-provided datasets. Using EM-stellar we show that the performance of any DL method is dependent on the properties of the images being segmented. It also follows that no single DL method performs consistently across all performance evaluation metrics.Availability and implementationEM-stellar (code and data) is written in Python and is freely available under MIT license on GitHub (https://github.com/cellsmb/em-stellar).Supplementary informationSupplementary data are available at Bioinformatics online.

| S-EPMC8034537 | biostudies-literature

Fluorescence microscopy tensor imaging representations for large-scale dataset analysis.

Project description:Understanding complex biological systems requires the system-wide characterization of cellular and molecular features. Recent advances in optical imaging technologies and chemical tissue clearing have facilitated the acquisition of whole-organ imaging datasets, but automated tools for their quantitative analysis and visualization are still lacking. We have here developed a visualization technique capable of providing whole-organ tensor imaging representations of local regional descriptors based on fluorescence data acquisition. This method enables rapid, multiscale, analysis and virtualization of large-volume, high-resolution complex biological data while generating 3D tractographic representations. Using the murine heart as a model, our method allowed us to analyze and interrogate the cardiac microvasculature and the tissue resident macrophage distribution and better infer and delineate the underlying structural network in unprecedented detail.

| S-EPMC7101442 | biostudies-literature

Large-scale, heterogeneous integration of nanowire arrays for image sensor circuitry.

Project description:We report large-scale integration of nanowires for heterogeneous, multifunctional circuitry that utilizes both the sensory and electronic functionalities of single crystalline nanomaterials. Highly ordered and parallel arrays of optically active CdSe nanowires and high-mobility Ge/Si nanowires are deterministically positioned on substrates, and configured as photodiodes and transistors, respectively. The nanowire sensors and electronic devices are then interfaced to enable an all-nanowire circuitry with on-chip integration, capable of detecting and amplifying an optical signal with high sensitivity and precision. Notably, the process is highly reproducible and scalable with a yield of approximately 80% functional circuits, therefore, enabling the fabrication of large arrays (i.e., 13 x 20) of nanowire photosensor circuitry with image-sensing functionality. The ability to interface nanowire sensors with integrated electronics on large scales and with high uniformity presents an important advance toward the integration of nanomaterials for sensor applications.

| S-EPMC2516247 | biostudies-other

Large-scale electron microscopy database for human type 1 diabetes.

Project description:Autoimmune ?-cell destruction leads to type 1 diabetes, but the pathophysiological mechanisms remain unclear. To help address this void, we created an open-access online repository, unprecedented in its size, composed of large-scale electron microscopy images ('nanotomy') of human pancreas tissue obtained from the Network for Pancreatic Organ donors with Diabetes (nPOD; www.nanotomy.org). Nanotomy allows analyses of complete donor islets with up to macromolecular resolution. Anomalies we found in type 1 diabetes included (i) an increase of 'intermediate cells' containing granules resembling those of exocrine zymogen and endocrine hormone secreting cells; and (ii) elevated presence of innate immune cells. These are our first results of mining the database and support recent findings that suggest that type 1 diabetes includes abnormalities in the exocrine pancreas that may induce endocrine cellular stress as a trigger for autoimmunity.

| S-EPMC7235089 | biostudies-literature

A large-scale solar dynamics observatory image dataset for computer vision applications.

Project description:The National Aeronautics Space Agency (NASA) Solar Dynamics Observatory (SDO) mission has given us unprecedented insight into the Sun's activity. By capturing approximately 70,000 images a day, this mission has created one of the richest and biggest repositories of solar image data available to mankind. With such massive amounts of information, researchers have been able to produce great advances in detecting solar events. In this resource, we compile SDO solar data into a single repository in order to provide the computer vision community with a standardized and curated large-scale dataset of several hundred thousand solar events found on high resolution solar images. This publicly available resource, along with the generation source code, will accelerate computer vision research on NASA's solar image data by reducing the amount of time spent performing data acquisition and curation from the multiple sources we have compiled. By improving the quality of the data with thorough curation, we anticipate a wider adoption and interest from the computer vision to the solar physics community.

| S-EPMC5525637 | biostudies-literature

Image restoration in cryo-electron microscopy.

Project description:Image restoration techniques are used to obtain, given experimental measurements, the best possible approximation of the original object within the limits imposed by instrumental conditions and noise level in the data. In molecular electron microscopy (EM), we are mainly interested in linear methods that preserve the respective relationships between mass densities within the restored map. Here, we describe the methodology of image restoration in structural EM, and more specifically, we will focus on the problem of the optimum recovery of Fourier amplitudes given electron microscope data collected under various defocus settings. We discuss in detail two classes of commonly used linear methods, the first of which consists of methods based on pseudoinverse restoration, and which is further subdivided into mean-square error, chi-square error, and constrained based restorations, where the methods in the latter two subclasses explicitly incorporates non-white distribution of noise in the data. The second class of methods is based on the Wiener filtration approach. We show that the Wiener filter-based methodology can be used to obtain a solution to the problem of amplitude correction (or "sharpening") of the EM map that makes it visually comparable to maps determined by X-ray crystallography, and thus amenable to comparative interpretation. Finally, we present a semiheuristic Wiener filter-based solution to the problem of image restoration given sets of heterogeneous solutions. We conclude the chapter with a discussion of image restoration protocols implemented in commonly used single particle software packages.

| S-EPMC3166661 | biostudies-literature

CAS Landslide Dataset: A Large-Scale and Multisensor Dataset for Deep Learning-Based Landslide Detection.

Project description:In this work, we present the CAS Landslide Dataset, a large-scale and multisensor dataset for deep learning-based landslide detection, developed by the Artificial Intelligence Group at the Institute of Mountain Hazards and Environment, Chinese Academy of Sciences (CAS). The dataset aims to address the challenges encountered in landslide recognition. With the increase in landslide occurrences due to climate change and earthquakes, there is a growing need for a precise and comprehensive dataset to support fast and efficient landslide recognition. In contrast to existing datasets with dataset size, coverage, sensor type and resolution limitations, the CAS Landslide Dataset comprises 20,865 images, integrating satellite and unmanned aerial vehicle data from nine regions. To ensure reliability and applicability, we establish a robust methodology to evaluate the dataset quality. We propose the use of the Landslide Dataset as a benchmark for the construction of landslide identification models and to facilitate the development of deep learning techniques. Researchers can leverage this dataset to obtain enhanced prediction, monitoring, and analysis capabilities, thereby advancing automated landslide detection.

| S-EPMC10762236 | biostudies-literature

Large-scale deep tissue voltage imaging with targeted illumination confocal microscopy.

Project description:Voltage imaging with cellular specificity has been made possible by the tremendous advances in genetically encoded voltage indicators (GEVIs). However, the kilohertz rates required for voltage imaging lead to weak signals. Moreover, out-of-focus fluorescence and tissue scattering produce background that both undermines signal-to-noise ratio (SNR) and induces crosstalk between cells, making reliable in vivo imaging in densely labeled tissue highly challenging. We describe a microscope that combines the distinct advantages of targeted illumination and confocal gating, while also maximizing signal detection efficiency. The resulting benefits in SNR and crosstalk reduction are quantified experimentally and theoretically. Our microscope provides a versatile solution for enabling high-fidelity in vivo voltage imaging at large scales and penetration depths, which we demonstrate across a wide range of imaging conditions and different GEVI classes.

| S-EPMC10370169 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data