Accurate lesion segmentation is critical in stroke rehabilitation research for the quantification of lesion burden and accurate image processing. Current automated lesion segmentation methods for T1-weighted (T1w) MRIs, commonly used in rehabilitation research, lack accuracy and reliability. Manual segmentation remains the gold standard, but it is time-consuming, subjective, and requires significant neuroanatomical expertise. However, many methods developed with ATLAS v1.2 report low accuracy, are not publicly accessible or are improperly validated, limiting their utility to the field. Here we present ATLAS v2.0 (N=1271), a larger dataset of T1w stroke MRIs and manually segmented lesion masks that includes training (public. n=655), test (masks hidden, n=300), and generalizability (completely hidden, n=316) data. Algorithm development using this larger sample should lead to more robust solutions, and the hidden test and generalizability datasets allow for unbiased performance evaluation via segmentation challenges. We anticipate that ATLAS v2.0 will lead to improved algorithms, facilitating large-scale stroke rehabilitation research.

Official Paper: https://www.nature.com/articles/s41597-022-01401-7

To access this data collection, please click on the Restricted Data button above. You will need to download and complete the data use agreement and then email it to icpsr-addep@umich.edu. The instructions are in the form. The Anatomical Tracings of Lesions After Stroke (ATLAS) Dataset - Release 2.0 is an open-source data collection consisting a total of 955 T1-weighted MRIs (Magnetic Resonance Imaging) with manually segmented diverse lesions and metadata. ATLAS v2.0 has been split into a public release of 655 T1w MRIs and lesion masks and a hidden test dataset of 300 T1w MRIs. For the hidden dataset, only the T1s MRIs are available. The accompanying manually segmented lesion masks will be made available only for testing algorithm performance in lesion segmentation challenges and competitions. The goal of ATLAS is to provide the research community with a standardized training and testing dataset for lesion segmentation algorithms on T1-weighted MRIs. From 33 cohorts worldwide, 955 MRI images were collected from research groups in the ENIGMA Stroke Recovery Working Group consortium. Images consisted of T1-weighted anatomical MRIs of individuals after stroke. For each MRI, brain lesions were identified and masks were manually drawn on each individual brain in native space using ITK-SNAP (version 3.8.0). After tracing, researchers reviewed and edited lesion masks as necessary using a standardized quality control protocol. In a subset of the data, lesion masks were received from the originating site and edited and checked for quality by the team. All team members received lesion-tracing training and followed a standard operating protocol for tracing lesions to ensure inter-rater reliability on all manually traced masks. All lesion masks were checked twice for quality by trained team members. During the quality control process, researchers ensured that the boundaries of the lesion segmentation were accurate and that all identifiable lesions in the brain were traced. All subject files have undergone a lesion tracing and preprocessing pipeline and are named and stored in accordance with the Brain Imaging Data Structure (BIDS) This dataset is provided in both native subject space and normalized to a standard template (the MNI-152 template).

ATLAS-REASONING

This dataset derives from the code here: atlasunified/atlas-reasoning and is synthetically generated by GPT-3.5-turbo.

  Categories

The main 42 (See the repo to check the JSONL) categories below were human derived while the subcategories were synthetically generated by GPT-4.

  1  Deductive Reasoning

-1.1 Syllogistic Arguments -1.2 Assumptions -1.3 Abductive Reasoning -1.4 Modus Ponens -1.5 Modus Tollens -1.6 Problem Solving -1.7 Goal Oriented… See the full description on the dataset page: https://huggingface.co/datasets/AtlasUnified/Atlas-Reasoning.

Boosted top tagging is an essential binary classification task for experiments at the Large Hadron Collider (LHC) to measure the properties of the top quark. The ATLAS Top Tagging Open Data Set is a publicly available data set for the development of Machine Learning (ML) based boosted top tagging algorithms. The data are split into two orthogonal sets, named train and test and stored in the HDF5 file format, containing 42 million and 2.5 million jets respectively. Both sets are composed of equal parts signal (jets initiated by a boosted top quark) and background (jets initiated by light quarks or gluons). For each jet, the data set contains:

• The four vectors of constituent particles
• 15 high level summary quantities evaluated on the jet
• The four vector of the whole jet
• A training weight
• A signal (1) vs background (0) label.

There is one rule in using this data set: the contribution to a loss function from any jet should always be weighted by the training weight. Apart from this a model should separate the signal jets from background by whatever means necessary.

Updated on July 26th 2024. This dataset has been superseeded by a new dataset which also includes systematic uncertainties. Please use the new dataset instead of this one.

Food environment factors--such as store/restaurant proximity, food prices, food and nutrition assistance programs, and community characteristics--interact to influence food choices and diet quality. Research is beginning to document the complexity of these interactions, but more is needed to identify causal relationships and effective policy interventions. The objectives of the Atlas are to assemble statistics on food environment indicators to stimulate research on the determinants of food choices and diet quality, and to provide a spatial overview of a community's ability to access healthy food and its success in doing so.

Atlas is a dataset for e-commerce clothing product categorization. The Atlas dataset consists of a high-quality product taxonomy dataset focusing on clothing products which contain 186,150 images under clothing category with 3 levels and 52 leaf nodes in the taxonomy.

An Open Context "types" dataset item. Open Context publishes structured data as granular, URL identified Web resources. This record is part of the "Chogha Mish Fauna" data publication.

Seatizen Atlas image dataset

This repository contains the resources and tools for accessing and utilizing the annotated images within the Seatizen Atlas dataset, as described in the paper Seatizen Atlas: a collaborative dataset of underwater and aerial marine imagery.

Download the Dataset

This annotated dataset is part of a bigger dataset composed of labeled and unlabeled images. To access information about the whole dataset, please visit the Zenodo repository and follow the download instructions provided.

Scientific Publication

If you use this dataset in your research, please consider citing the associated paper:

@article{Contini2025, author = {Matteo Contini and Victor Illien and Mohan Julien and Mervyn Ravitchandirane and Victor Russias and Arthur Lazennec and Thomas Chevrier and Cam Ly Rintz and Léanne Carpentier and Pierre Gogendeau and César Leblanc and Serge Bernard and Alexandre Boyer and Justine Talpaert Daudon and Sylvain Poulain and Julien Barde and Alexis Joly and Sylvain Bonhommeau}, doi = {10.1038/s41597-024-04267-z}, issn = {2052-4463}, issue = {1}, journal = {Scientific Data}, pages = {67}, title = {Seatizen Atlas: a collaborative dataset of underwater and aerial marine imagery}, volume = {12}, url = {https://doi.org/10.1038/s41597-024-04267-z}, year = {2025},}

For detailed information about the dataset and experimental results, please refer to the previous paper.

Overview

The Seatizen Atlas dataset includes 14,492 multilabel and 1,200 instance segmentation annotated images. These images are useful for training and evaluating AI models for marine biodiversity research. The annotations follow standards from the Global Coral Reef Monitoring Network (GCRMN).

Annotation Details

Annotation Types:

Multilabel Convention: Identifies all observed classes in an image.

Instance Segmentation: Highlights contours of each instance for each class.

List of Classes

Algae

Algal Assemblage

Algae Halimeda

Algae Coralline

Algae Turf

Coral

Acropora Branching

Acropora Digitate

Acropora Submassive

Acropora Tabular

Bleached Coral

Dead Coral

Gorgonian

Living Coral

Non-acropora Millepora

Non-acropora Branching

Non-acropora Encrusting

Non-acropora Foliose

Non-acropora Massive

Non-acropora Coral Free

Non-acropora Submassive

Seagrass

Syringodium Isoetifolium

Thalassodendron Ciliatum

Habitat

Rock

Rubble

Sand

Other Organisms

Thorny Starfish

Sea Anemone

Ascidians

Giant Clam

Fish

Other Starfish

Sea Cucumber

Sea Urchin

Sponges

Turtle

Custom Classes

Blurred

Homo Sapiens

Human Object

Trample

Useless

Waste

These classes reflect the biodiversity and variety of habitats captured in the Seatizen Atlas dataset, providing valuable resources for training AI models in marine biodiversity research.

Usage Notes

The annotated images are available for non-commercial use. Users are requested to cite the related publication in any resulting works. A GitHub repository has been set up to facilitate data reuse and sharing: GitHub Repository.

Code Availability

All related codes for data processing, downloading, and AI model training can be found in the following GitHub repositories:

Plancha Workflow

Zenodo Tools

DinoVdeau Model

Acknowledgements

This dataset and associated research have been supported by several organizations, including the Seychelles Islands Foundation, Réserve Naturelle Marine de la Réunion, and Monaco Explorations, among others.

For any questions or collaboration inquiries, please contact seatizen.ifremer@gmail.com.

Abstract

The Opportunity Atlas has collected contextual data by county and tract. Rather than providing contextual socioeconomic data of where people currently live, the data represents average socioeconomic indicators (e.g., earnings) of where people grew up.

Documentation

A core element of Population Health Science is that health outcomes can only be fully understood when they are studied within their context. Therefore, we have a copy of The Opportunity Atlas, a dataset that provides socioeconomic data by county and tract.

Several studies have shown that especially childhood neighborhoods drive adult outcomes and that residential areas lived in through adulthood have much smaller effects. The focus of the Opportunity Atlas is therefore on contextual data of where people grew up:

%3E Traditional measures of poverty and neighborhood conditions provide snapshots of income and other variables for residents in an area at a given point in time. But to study how economic opportunity varies across neighborhoods, we really need to follow people over many years and see how one’s outcomes depend upon family circumstances and where on grew up. The Opportunity Atlas is the first dataset that provides such longitudinal information at a detailed neighborhood level. Using the Atlas, you can see not just where the rich and poor currently live – which was possible in previously available data from the Census Bureau – but whether children in a given area tend to grow up to become rich of poor. This focus on mobility out of poverty across generations allows us to trace the roots of outcomes such as poverty and incarceration back to where kids grew up, potentially permitting much more effective interventions.

As such, The Opportunity Atlas data provides a rich source of data for researchers who wish to overlay health data with contextual data.

Methodology

Three sources of Census Bureau are linked to compute the data

1. The 2000 and 2010 Decennial Census short form
2. Federal income tax returns for 1989, 1994, 1995, 1998-2015
3. The 2000 Decennial Census long form and the 2005-2015 American Community Surveys (ACS).

%3C!-- --%3E

20.5 million Americans born between 1987-1983 are sampled from these data and mapped back to the Census tracts they lived in through age 23. After that step, a range of outcomes are then estimated for each of the 70,000 tracts. In order to comply with federal data disclosure standards and protect the privacy of individuals no estimates in tracts with 20 or fewer children are published and noise (small random numbers) is added to all the estimates.

For more information on the data collection and methodology, please visit:

Website

Documentation

Data availability

Some variables are available for counties only. The table below gives you an overview. Open the table in a new tab for a larger view.

https://redivis.com/fileUploads/ee6544ef-e1b1-473d-a75d-36618c91f4a5%3E" alt="data availability.png">

World Ocean Atlas 2023 (WOA23) is a set of objectively analyzed (one degree grid and quarter degree grid) climatological fields of in situ temperature, salinity, dissolved oxygen, Apparent Oxygen Utilization (AOU), percent oxygen saturation, phosphate, silicate, and nitrate at standard depth levels for annual, seasonal, and monthly compositing periods for the World Ocean. Quarter degree fields are for temperature and salinity only. It also includes associated statistical fields of observed oceanographic profile data interpolated to standard depth levels on quarter degree, one degree, and five degree grids. Temperature and salinity fields are available for seven decades (1955-1964, 1965-1974, 1975-1984, 1985-1994, 1995-2004, 2005-2014, and 2015-2022), for three thirty year "climate normal" periods (1971-2000, 1981-2010, and 1991-2020), and for an average of the seven individual decades (1955-2022). Oxygen fields (as well as AOU and percent oxygen saturation) are available using all quality controlled bottle, CTD, and profiling float data from 1965-2022 as well as a thirty year "climate normal" using bottle and CTD data for 1971-2000. Nutrient fields are available using all quality controlled bottle data from the entire sampling period between 1965-2022. This accession is a product generated by the National Centers for Environmental Information's (NCEI) Ocean Climate Laboratory Team. The analyses are derived from the NCEI World Ocean Database 2023.

This data set (ATL02) contains science-unit-converted time-ordered telemetry data, calibrated for instrument effects, downlinked from the Advanced Topographic Laser Altimeter System (ATLAS) instrument on board the Ice, Cloud and land Elevation Satellite-2 (ICESat-2) observatory. The data are used by the ATLAS/ICESat-2 Science Investigator-led Processing System (SIPS) for system-level, quality control analysis and as source data for ATLAS/ICESat-2 Level-2 products and Precision Orbit Determination (POD) and Precision Pointing Determination (PPD) computations.

This dataset is an output of the ATLAS database (a dATabase of visuaL Atmospheric Stimuli) project. Here are raw data from an online survey testing the ATLAS video stimuli through felt arousal, valence, and sense of agency (ran in the spring term of 2023). We analyzed 365 participants, split into five blocks of stimuli. See document no. 3 for explanations about the stimuli’ nature and document no. 4 for a recap of the survey structure. Dataset 10.5281/zenodo.8170370 (open access) embeds all the ATLAS videos used as stimuli in the survey.

Five files compone the dataset:no. 1 dataset summary (.pdf)no. 1 database with raw data from the survey (.xlsx)no. 1 stimuli explanation (.pdf)no. 1 recap of the survey structure (.pdf)no. 1 introductive video for the survey (.mp4)

This deposit offers a comprehensive collection of geospatial and metadata files that constitute the Seatizen Atlas dataset, facilitating the management and analysis of spatial information. To navigate through the data, you can use an interface available at seatizenmonitoring.ifremer.re, which provides a condensed CSV file tailored to your choice of metadata and the selected area.To retrieve the associated images, you will need to use a script that extracts the relevant frames. A brief tutorial is available here: Tutorial.All the scripts for processing sessions, creating the geopackage, and generating files can be found here: SeatizenDOI github repository.The repository includes:

seatizen_atlas_db.gpkg: geopackage file that stores extensive geospatial data, allowing for efficient management and analysis of spatial information.
session_doi.csv: a CSV file listing all sessions published on Zenodo. This file contains the following columns:

session_name: identifies the session.
session_doi: indicates the URL of the session.
place: indicates the location of the session.
date: indicates the date of the session.
raw_data: indicates whether the session contains raw data or not.
processed_data: indicates whether the session contains processed data.
metadata_images.csv: a CSV file describing all metadata for each image published in open access. This file contains the following columns:

OriginalFileName: indicates the original name of the photo.
FileName: indicates the name of the photo adapted to the naming convention adopted by the Seatizen team (i.e., YYYYMMDD_COUNTRYCODE-optionalplace_device_session-number_originalimagename).
relative_file_path: indicates the path of the image in the deposit.
frames_doi: indicates the DOI of the version where the image is located.
GPSLatitude: indicates the latitude of the image (if available).
GPSLongitude: indicates the longitude of the image (if available).
GPSAltitude: indicates the depth of the frame (if available).
GPSRoll: indicates the roll of the image (if available).
GPSPitch: indicates the pitch of the image (if available).
GPSTrack: indicates the track of the image (if available).
GPSDatetime: indicates when frames was take (if available).
GPSFix: indicates GNSS quality levels (if available).
metadata_multilabel_predictions.csv: a CSV file describing all predictions from last multilabel model with georeferenced data.

FileName: indicates the name of the photo adapted to the naming convention adopted by the Seatizen team (i.e., YYYYMMDD_COUNTRYCODE-optionalplace_device_session-number_originalimagename).
frames_doi: indicates the DOI of the version where the image is located.
GPSLatitude: indicates the latitude of the image (if available).
GPSLongitude: indicates the longitude of the image (if available).
GPSAltitude: indicates the depth of the frame (if available).
GPSRoll: indicates the roll of the image (if available).
GPSPitch: indicates the pitch of the image (if available).
GPSTrack: indicates the track of the image (if available).
GPSFix: indicates GNSS quality levels (if available).
prediction_doi: refers to a specific AI model prediction on the current image (if available).
A column for each class predicted by the AI model.
metadata_multilabel_annotation.csv: a CSV file listing the subset of all the images that are annotated, along with their annotations. This file contains the following columns:

FileName: indicates the name of the photo.
frame_doi: indicates the DOI of the version where the image is located.
relative_file_path: indicates the path of the image in the deposit.
annotation_date: indicates the date when the image was annotated.
A column for each class with values:

1: if the class is present.
0: if the class is absent.
-1: if the class was not annotated.
seatizen_atlas.qgz: a qgis project which formats and highlights the geopackage file to facilitate data visualization.
darwincore_multilabel_annotations.zip: a Darwin Core Archive (DwC-A) file listing the subset of all the images that are annotated, along with their annotations.

The ascending arousal network (AAN) is a subcortical neural network that is critical to consciousness. AAN neurons connect the brainstem to the thalamus, hypothalamus, basal forebrain and cortex, activating cortically-based awareness networks. The reticular core of the AAN was first described by Moruzzi and Magoun in 1949, who coined the classical term "ascending reticular activating system" (Electroencephalogr Clin Neurophysiol 1949;1:455-73). Here, we use the term AAN because many brainstem nuclei that contribute to arousal are located outside of the pontine and midbrain reticular core (e.g., locus coeruleus, parabrachial complex, etc.), and because we believe that the word "network" appropriately connotes the physiological mechanisms by which multiple modular circuits interrelate to enable the emergent property of arousal, and hence consciousness. To date, the majority of studies investigating AAN connectivity have utilized animal models. As a result, current knowledge about the stru...

This collection is a legacy product that is no longer supported. It may not meet current government standards. The North American Atlas data are standardized geospatial data sets at 1:10,000,000 scale. A variety of basic data layers (e.g. roads, railroads, populated places, political boundaries, hydrography, bathymetry, sea ice and glaciers) have been integrated so that their relative positions are correct. This collection of data sets forms a base with which other North American thematic data may be integrated. The North American Atlas data are intended for geographic display and analysis at the national and continental level. Any data outside of Canada, Mexico, and the United States of America included in the North American Atlas data sets is strictly to complete the context of the data.

The dataset includes NIfTI files of MRI T2 ex-vivo data; reconstructed Nissl stained images of the same brain, registered to the shape of the MRI; brain region segmentation (with separate color lookup table); and gray, mid-cortical and white matter boundary segmentation. In addition, a 3D Slicer scene file is provided that can be used for testing the dataset within the freely downloadable 3D Slicer software (https://www.slicer.org/). The scene file can be dragged directly into 3D Slicer and the atlas can be used immediately. Files can be downloaded individually or as one zip file.
The atlas can be viewed online via the Zooming Atlas Viewer (ZAV) by clicking here.

The Brain Atlas explores the protein expression in the mammalian brain by visualization and integration of data from three mammalian species (human, pig and mouse). Transcriptomics data combined with affinity-based protein in situ localization down to single cell detail is here available in a brain-centric sub atlas of the Human Protein Atlas. The data focuses on human genes and one-to-one orthologues in pig and mouse. Each gene is provided with a summary page, showing available expression data (mRNA) for summarized regions of the brain as well as protein location for selected targets. High resolution staining images as well as expression data for the individual sub regions are all available for exploring the brain, the most complex organ.

Currently, approximately 150 different brain tumour types are defined by the WHO. Recent endeavors to exploit machine learning and deep learning methods for supporting more precise diagnostics based on the histological tumour appearance have been hampered by the relative paucity of accessible digital histopathological datasets. While freely available datasets are relatively common in many medical specialties such as radiology and genomic medicine, there is still an unmet need regarding histopathological data.

Thus, we digitized a significant portion of a large dedicated brain tumour bank based at the Division of Neuropathology and Neurochemistry of the Medical University of Vienna, covering brain tumour cases from 1995-2019. This unique dataset can potentially be used for digital image analysis, training machine learning algorithms, external validation and teaching.

The Human Pathology Atlas is based on a systems-based analysis of the transcriptome of 17 main cancer types using data from 8,000 patients. In addition, we show a new concept to present patient survival data, called Interactive Survival Scatter plots, and in the atlas, we present more than 400,000 plots. A national supercomputer center were used to analyze more than 2.5 petabytes of underlying publicly available data from the Cancer Genome Atlas (TCGA) to generate more than 900,000 survival plots describing the consequence of RNA and protein levels on clinical survival. The Pathology Atlas also contains 5 million pathology-based images generated by the Human Protein Atlas consortium. The research reports several important findings related to cancer biology and treatment. Firstly, many genes are differentially expressed in cancers, and a large proportion of these genes have an impact on overall patient survival. The research also showed that gene expression patterns of individual tumors varied considerably, and could exceed the variation observed between different cancer types. Shorter patient survival was generally associated with up-regulation of genes involved in mitosis and cell growth, and down-regulation of genes involved in cellular differentiation. The data allowed for generation of personalized genome-scale metabolic models for cancer patients to identify key genes involved in tumor growth.

The Health Atlas for the City of Los Angeles 2021 presents a data-driven snapshot of health conditions and outcomes in the City of Los Angeles. It illustrates geographic variation in socio-economic conditions, demographic characteristics, the physical environment, and access to support systems and services, and provides a context for understanding how these factors contribute to the health of Angelenos.The data underscore a key issue: where Angelenos live often influences their health and well-being. Los Angeles is a city with great health disparities and the patterns of inequality are reflected in many of the indicators highlighted in the Health Atlas. The spatial characteristics of physical and social determinants of health have roots in structural racism and historic and ongoing discrimination. Historic policies such as redlining have had lasting effects in Los Angeles. The analysis is a first step in understanding the areas of the City burdened with the most adverse health-related conditions in order to improve health outcomes and environmental justice for all Angelenos.The Health Atlas contains 115 maps covering regional context, demographic and social characteristics, economic conditions, education, health conditions, land use, transportation, food systems, crime, housing, and environmental health. In addition to displaying US Census Bureau, City, County, and other data, the Health Atlas contains several indices to facilitate comparisons across the city on subjects including environmental hazards (Map 113: Pollution Burden Index), transportation quality (Map 84: Transportation Index), and economic conditions (Map 19: Hardship Index). The Health Atlas culminates in a Community Health and Equity Index (Maps 114 and 115) which combines many of the above variables into a single index to compare health conditions across the City of Los Angeles. The Community Health and Equity Index can be used to understand the areas of the city with the highest vulnerabilities and cumulative burdens as compared to other portions of the City.The Health Atlas for the City of Los Angeles was originally developed in 2013 as an early step in the process to develop a Health, Wellness, and Equity Element of the General Plan (also known as the Plan for a Healthy Los Angeles). This data set is an update of the Health Atlas, completed in 2021. The Health Element and both editions of the Health Atlas are available as PDFs on the Los Angeles City Planning website, https://planning.lacity.gov.