Find research datasets worth reusing

opencc-by-4.0Jun 2024View details →

Single cell data from Imaging Mass Cytometry of mouse lung tumours treated with KRAS-G12C and immune checkpoint inhibitors (Dataset 3)

Open the record for dataset details and reuse information.

opencc-by-4.0Jul 2023View details →

Hyperspectral imaging dataset of potato plants exposed to water-deficit condition

An experiment: <ul> <li>Greenhouse experiment under controlled environmental conditions.</li> <li>Conducted at the Agricultural Institute of Slovenia (Ljubljana, Slovenia). </li> <li>From April to August 2021.</li> <li>A night/day temperature of 21 °C/15 °C; relative humidity of 60%, and photoperiod of 14h.</li> <li>28 cultivars of KIS Krka and 18 of KIS Savinja grown from tubers in 5-litre pots.</li> <li>5 weeks after planting, half plants of both cultivars were randomly assigned to either water-deficient or well-watered groups. </li> <li>The water-deficient group was exposed to a limited water irrigation regime, i.e., up to 50% of substrate saturation field capacity. </li> <li>The soil moisture was surveilled using tensiometers (14.04.04 Jett Fill tensiometers, Eijkelkamp, Giesbeek Netherlands).</li> <li>Throughout the duration of the experiment, the matric potential of the soil was maintained within the range -0,01 MPa to -0,025 MPa for well-watered plants, and -0,05 MPa to -0,07 MPa for water-deficient plants. </li> </ul>   Hyperspectral imaging:  <ul> <li>Every week after the deficit was introduced.</li> <li>Total of 5 imaging sessions were performed.</li> <li>The imaging sessions took place in a dark room, where cameras were positioned at a 3 m distance from the potato plants, together with calibrated halogen lamps.</li> <li>Hyperspectral images were acquired in the VNIR (visible to near infrared) and SWIR (short-wave infrared) spectral regions. </li> <li>Hyspex (Norsk Elektro Optikk, Oslo Norway) push-broom cameras VNIR-1600 (400–988 nm, 160 bands, bandwidth 3.6 nm) and SWIR-384 (950–2500 nm, 288 bands, bandwidth 5.4 nm) were used.</li> </ul>   Files: <ul> <li> File structure: </li> </ul>         📂 imagings         ├── 📁 imaging-1         │   ├── 📄 0_1_0__KK-K-04_KS-K-05_KK-S-03__imaging-1__1-22_20000_us_2x_HSNR02_ 2022-05-11T104633_corr_rad_f32.hdr         │   ├── 📄 0_1_0__KK-K-04_KS-K-05_KK-S-03__imaging-1__1-22_20000_us_2x_HSNR02_2022-05-11T104633_corr_rad_f32.img         │   └── 📄 ...         ├── 📁 imaging-2         │   └── 📄 ...         ├── 📁 imaging-3         │   └── 📄 ...         ├── 📁 imaging-4         │   └── 📄 ...         └── 📁 imaging-5             └── 📄 ...   <ul> <li> Description of a name: </li> </ul> A_B_C__L1_L2_L3__imaging-X__ID.img -> image file A_B_C__L1_L2_L3__imaging-X__ID.hdr -> header file belonging to an image file   A - index of original raw hyperspectral image B - index of an object on the image (of a particular potato plant) C - index of slice extracted from the image L - labels of plants on the image X - index of the imaging session ID - string identifier   <ul> <li> Description of labels (L): </li> </ul> V-T-N (e.g. KK-K-04)   V - variety (KK - KIS Krka or KS - KIS Savinja) T - treatment (K - control or S, drought) N - index of a particular plant   <ul> <li> Image properties: </li> </ul> Width of the image: 64 Height of the image: 64 Number of spectral bands: 448 Spectral range: 410nm - 2510nm Image values are expressed in reflectance   Additional links: Code where the dataset was used for the entire analysis could be found here: https://github.com/Manuscripts-code/Potato-plants-drought--plants-2024

Chest X-Ray Image Dataset: A Resource for Medical Diagnosis and Machine Learning

The Chest X-Ray Image Dataset is an extensive collection designed to support medical research and the development of diagnostic tools for COVID-19 detection. It consists of two distinct classes: COVID-19 affected X-ray images and normal X-ray images of the chest area, each covering the full lungs. This dataset provides a diverse range of X-ray images, capturing the unique characteristics of both healthy and COVID-19 affected lungs, making it an invaluable resource for training and testing machine learning models in medical image classification and analysis.

Cell features for "Datasets for "Predicting microsatellite instabilitiy from histology images with a three-level hierarchical graph fusion model""

This repository contains features and corresponding coordinates of cells extracted from 430 and 326 histologic images from patients with colorectal and gastric cancers from the TCGA cohort (original whole section SVS images are freely available at https://portal.gdc.cancer.gov/). All images in this library are from formalin-fixed paraffin-embedded (FFPE) diagnostic sections (“DX” on the GDC Data Portal). This blog explains this in detail: http://www.andrewjanowczyk.com/download-tcga-digital-pathology-images-ffpe/ Preprocessing. All SVS slices were pre-processed as follows. According to “Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer” these histology images were categorized into “MSS” (microsatellite stable) or “MSIMUT” (microsatellite unstable or highly mutated) and corresponded to the article dividing the training and test sets. The features of all cells were extracted by Hovernet and Transnuseg at 40x objective magnification for extraction masking and further feature extraction

Dataset of images SfM - FRM - Lighting and Artificial texture

This collection of images was employed to examine the impact of various configurations in the 3D modeling process for short-distance environments. This analysis established settings to achieve submillimeter accuracy in the RMSE values of the analyzed points.  Set of images used to evaluate the use of light aids (softboxes) and artificial textures in a short-distance environment. This set was used to evaluate the configurations and the possibility of using the SfM technique in the 3D modeling of structural tests. Test specimens used (Concrete, Metal and Wood)—artificial texture in white Chalk (on Concrete and Wood) and red marker (on metal). Texture patterns were drawn in a checkerboard fashion (T1) and a more closed checkerboard shape (T2). Images in CR3 - Conversion to TIFF or JPG required for use and processing in Agisoft Metashape.

Wheat Powdery Mildew Image Dataset

The dataset consists of wheat leaf images collected using a mobile phone, specifically focused on capturing diseased areas. These images are annotated with labels indicating the presence of diseases, suitable for training and testing a YOLO (You Only Look Once) object detection model. The labeled dataset aims to enable the model to accurately identify and classify diseased regions in similar images. <h2>Description of the data and file structure</h2> <h4>1. Images Folder:</h4> <ul> <li> Structure: The Images folder contains three subfolders: train, test, and val. Each subfolder contains image files in formats such as JPEG or PNG. </li> <ul> <li> train: Contains images used for training the YOLO model. </li> <li> test: Contains images used for testing the model's performance. </li> <li> val: Contains images used for validating the model during training, helping to tune hyperparameters and prevent overfitting. </li> </ul> </ul> <h4>2. Labels Folder:</h4> <ul> <li> Structure: The Labels folder mirrors the structure of the Images folder, with subfolders named train, test, and val. Each subfolder contains YOLO-format label files. </li> <ul> <li> train: Contains label files corresponding to the training images. </li> <li> test: Contains label files for the testing images. </li> <li> val: Contains label files for the validation images. </li> </ul> </ul> <h4>3. YOLO Label Format:</h4> <ul> <li> Contents: Each label file corresponds to an image and contains information in the YOLO format, which includes: </li> <ul> <li> Class ID: An integer representing the class label (e.g., a specific disease). </li> <li> Bounding Box Coordinates: Four numbers representing the center x, center y, width, and height of the bounding box, all normalized between 0 and 1. </li> <li> File Naming Convention: The label files are named identically to their corresponding images, except for the file extension (e.g., image1.jpg and image1.txt). </li> </ul> </ul> <h4>4. Usage and Application:</h4> <ul> <li> Model Training and Validation: The dataset can be used to train and validate YOLO object detection models. The clear separation into train, test, and validation sets supports robust model evaluation and helps prevent data leakage. </li> <li> Model Testing: The test set is used to evaluate the model's performance on unseen data, providing an unbiased measure of its generalization capability. </li> <li> Model Tuning: The validation set helps fine-tune model parameters and assess performance during the training process. </li> </ul>

Electron microscopy images and morphometric data of SARS-CoV-2 variants in ultrathin plastic sections - Dataset 05 (SARS-CoV-2 Delta B.1.617.2)

Dataset 05 comprises 153 transmission electron microscopy images of extracellular SARS-CoV-2 (isolate Delta B.1.617.2) particles in ultrathin plastic sections (45 nm) through Vero cell cultures. The images were recorded with dimensions of 4112 x 3008 pixels at a pixel size of 0.1641 nm and stored in 16-bit TIF format. It is recommended that an image viewer capable of reading 16-bit images, such as IrfanView, be used to visualize the images. The image files have been size calibrated and can be opened with the correct size calibration using ImageJ or Fiji with the Bioformats importer. A PDF document is provided with the image files, which describes the methods used for the generation of the images. Additionally, an XLSX file is included, offering morphometric particle measurements and the calculated statistical values for their distribution. The dataset was produced as dataset 05 for a comparative morphometric analysis of evolving SARS-CoV-2 variants. Further datasets used for the analysis are available in this repository (see dataset description document).

Electron microscopy images and morphometric data of SARS-CoV-2 variants in ultrathin plastic sections - Dataset 03 (SARS-CoV-2 Alpha B.1.1.7)

Dataset 03 comprises 147 transmission electron microscopy images of extracellular SARS-CoV-2 (isolate Alpha B.1.1.7) particles in ultrathin plastic sections (45 nm) through Vero cell cultures. The images were recorded with dimensions of 4112 x 3008 pixels at a pixel size of 0.1641 nm and stored in 16-bit TIF format. It is recommended that an image viewer capable of reading 16-bit images, such as IrfanView, be used to visualize the images. The image files have been size calibrated and can be opened with the correct size calibration using ImageJ or Fiji with the Bioformats importer. A PDF document is provided with the image files, which describes the methods used for the generation of the images. Additionally, an XLSX file is included, offering morphometric particle measurements and the calculated statistical values for their distribution. The dataset was produced as dataset 03 for a comparative morphometric analysis of evolving SARS-CoV-2 variants. Further datasets used for the analysis are available in this repository (see dataset description document).

Electron microscopy images and morphometric data of SARS-CoV-2 variants in ultrathin plastic sections - Dataset 01 (SARS-CoV-2 Munich929)

Dataset 01 comprises 150 transmission electron microscopy images of extracellular SARS-CoV-2 (isolate Munich929) particles in ultrathin plastic sections (45 nm) through Vero cell cultures. The images were recorded with dimensions of 4112 x 3008 pixels at a pixel size of 0.1641 nm and stored in 16-bit TIF format. It is recommended that an image viewer capable of reading 16-bit images, such as IrfanView, be used to visualize the images. The image files have been size calibrated and can be opened with the correct size calibration using ImageJ or Fiji with the Bioformats importer. A PDF document is provided with the image files, which describes the methods used for the generation of the images. Additionally, an XLSX file is included, offering morphometric particle measurements and the calculated statistical values for their distribution. The dataset was produced as dataset 01 for a comparative morphometric analysis of evolving SARS-CoV-2 variants. Further datasets used for the analysis are available in this repository (see dataset description document).

opencc-by-4.0Jul 2018View details →

Micro-seismic and image dataset acquired at Matterhorn Hörnligrat, Switzerland

This dataset contains annotated micro-seismic recordings and images acquired in the context of project X-Sense2 (financed by nano-tera.ch, ref. no. 530659) at the Matterhorn Hörnligrat fieldsite on 3500 m a.s.l.. Additionally, secondary data is provided which can used for further analysis. This dataset comprises a selection of measurements. The data folder contains two datasets and additional data (secondary data). Please refer to the following publication for further information:   Meyer, M., Weber, S., Beutel, J., Thiele, L.: Systematic Identification of External Influences in Multi-Year Micro-Seismic Recordings Using Convolutional Neural Networks, Earth Surface Dynamics, in review, 2018.   dataset The dataset/ folder contains micro-seismic data, images, and annotations. A list of every datapoint including annotations and start/end time is provided in two csv files in the annotations/ folder.   event_dataset The event_dataset/ folder contains micro-seismic data and annotations. A list of every datapoint including annotations and start/end time is provided in two csv files in the annotations/ folder. For a selected time period bounding boxes are provided in the bounding_box.csv file.   Micro-seismic data The data was recorded using a Nanometrics Centaur digital recorder and Lennartz electronic low-noise seismometer LE-3Dlite MKIII (1−100 Hz). The Nanometrics Centaur digital recorder aquires data with 24-bit resolution with a sampling rate of 1000 sps. The data is stored in .miniseed-format.   Image data Images where acquired with a remote controlled high-resolution camera (Nikon D300, 24 mm fixed focus).   Annotations The data was annotated manually by the authors.   Secondary data The secondary data comprises data from different sensors, including wind speed, rock temperature and radiation. Additionally, weekly aggregated hut occupancy of the Hörnlihut from the years 2016/2017 and event timestamps from running a STA/LTA trigger on an internal version of the micro-seismic data are provided.

opencc-by-4.0Mar 2019View details →

Supporting dataset for "Magnetotelluric images of Paleoproterozoic accretion and Mesoproterozoic to Neoproterozoic reworking processes in the northern Sao Francisco Craton, central-eastern Brazil"

This dataset presents .edi files from 38 magnetotelluric stations across the northern São Francisco Craton in central-eastern Brazil. Data collection was financially supported by CNPq Project 573713/2008-1.

opencc-by-4.0Jul 2019View details →

dataset for root canal configuration of mandibular first and second premolars using in vivo cone-beam computed tomography imaging

dataset for root canal configuration of mandibular first and second premolars using in vivo cone-beam computed tomography imaging

opencc-by-4.0Sep 2019View details →

Fibre Identification Blind Test dataset: Images of longitudinal and cross-section views of hemp, nettle, and flax fibres

Dataset produced by Denis Waudby while undertaking analysis of a sample of fibres presented to him as a blind test of a new fibre identification methodology designed to reduce subjectivity in fibre identification protocols for distinguishing bast fibres (specifically Hemp, Nettle, and Flax)

opencc-by-4.0Nov 2019View details →

Seismic dataset in "Source-Independent Passive Seismic Reverse-time Structure Imaging with Grouping Imaging Condition: Method and Application to Microseismic Events Induced by Hydraulic Fracturing"

This dataset contains the seismic data and the velocity model used in the manuscript entitled "Source-Independent Passive Seismic Reverse-time Structure Imaging with Grouping Imaging Condition: Method and Application to Microseismic Events Induced by Hydraulic Fracturing" submitted to Journal of Geophysical Research-Solid Earth.

CIDACC: Chlorella vulgaris Image Dataset for Automated Cell Counting

This CIDACC dataset was created to determine the cell population of Chlorella vulgaris microalga during cultivation. Chlorella vulgaris has diverse applications, including use as food supplement, biofuel production, and pollutant removal. High resolution images were collected using a microscope and annotated, focusing on computer vision and machine learning models creation for automatic Chlorella cell detection, counting, size and geometry estimation. The dataset is organized hierarchically into multiple folders and subfolders, containing 628 images taken from a microscope and further processed by external tools. It consists of three root folders: “original_images”, “clusters”, and “distinct”. The “original_images” folder holds the raw microscope images with initial dimensions of 2592x1944 pixels. These images are further subdivided into “clusters” and “distinct” folders, indicating whether they contain single cells or cell clusters. The “clusters” and “distinct” root folders contain annotated images with reduced dimensions (640x640 pixels). The “clusters” folder includes images showing C. vulgaris cells forming clusters, where counting individual cells is not possible. The “distinct” folder contains images of cells that can be counted with high precision.

Experimental dataset: stationary images for digital image correlation uncertainty quantification

<div>----------------------------------------------------------------------------------------------------------------------------------------------------------------------</div> <div>--------------------------------------------------------------------------------  SUMMARY  ---------------------------------------------------------------------------</div> <div>----------------------------------------------------------------------------------------------------------------------------------------------------------------------</div> <div> </div> <div>Stereo-DIC 5 MPx system was used to capture sets of stationary images for quantification of DIC uncertainties.</div> <div> </div> <div>----------------------------------------------------------------------------------------------------------------------------------------------------------------------</div> <div>--------------------------------------------------------------------------------  FOLDERS  ---------------------------------------------------------------------------</div> <div>----------------------------------------------------------------------------------------------------------------------------------------------------------------------</div> <div> </div> <div>Image sets: </div> <div> </div> <div>Set 1: 100 stationary images with cross polarisation to reduce effect of specular reflection. Test sample clamped in the clamps of a uniaxial tensile test bench.</div> <div>Set 2: Same as set 1, but test sample unclamped at the bottom, displaced by 1 mm vertically. Meant to introduce rigid body motion into teh stationary images. </div> <div>For investigation of the impact of cross-polarisation: image gradients made similar as much as possible by adjusting exposure time and apetrture. </div> <div>Set 3: With cross polarisation - 100 stationary images.</div> <div>Set 4: Without cross polarisation - 100 stationary images.</div> <div> </div> <div>Images for stereo calibration:</div> <div> </div> <div>Calib_sets_1_2: Calibration images for sets 1 and 2 mentioned above </div> <div>Calib_sets_3: Calibration images for set 3 mentioned above </div> <div>Calib_sets_4: Calibration images for set 4 mentioned above </div> <div> </div> <div>----------------------------------------------------------------------------------------------------------------------------------------------------------------------</div> <div>------------------------------------------------------------------------  SUPPORTING NINFORMATION --------------------------------------------------------------------</div> <div>---------------------------------------------------------------------------------------------------------------------------------------------------------------------- </div> <div> </div> <div>Image folder for each set contains an *.xaml file with image capture settings.</div> <div>Each calibration image folder contains a *.caldat file with intrinsic and extrinsic stereo camera parameters identified by MatchID 2024.2 DIC package.</div>

Dataset with segmentations of 75 stained cell images over P3HBV polymer films

<div> We segmented 75 images of stained cells, divided in 5 folders according the thickness of the Poly-3-hydroxyvalerate films. P3HBV polymer films of different thicknesses were prepared by casting solution technique. For this, P3HBV was dissolved in chloroform to obtain homogeneous solutions with concentration of 1.0, 1.5, 2.0, 2.5 and 3.0%. The films were dried at room temperature for 48 hours in a dust-free environment, allowing the chloroform to evaporate completely and resulting in solid films. Upper surfaces of the films were used for cell cultivation. Linear culture of mice fibroblasts NIH 3T3 was used to obtain the visual data of cell adhesion on P3HBV film samples. To assess the cytocompatibility of PHA samples, cells were seeded onto sterile polymer films samples at a density of 2 × 104𝑐𝑒𝑙𝑙𝑠/𝑐𝑚2 and cultured for 72 hours. After the incubation, the samples were washed with phosphate-buffered saline and cells were fixed with 4% paraformaldehyde solution. Cell membranes were permeabilized with 0.2% Triton-X, and the cytoplasm was stained with fluorescein isothiocyanate, FITC (green) (Sigma-Aldrich, USA), for 1 hour in the dark at room temperature. The nuclei were visualized using 4’,6-diamidino-2-phenylindole, DAPI (blue) (Sigma-Aldrich, USA). Cells were visualized using a Leica DMI8 fluorescent microscope with corresponding LAS X software. Per each sample, we include: A raw image (.tif) with 2 subfolders containing the segmented masks of their cells and nuclei respectively. </div>

GDCLD:A globally distributed dataset of coseismic landslide mapping via multi-source high-resolution remote sensing images

GDCLD : A globally distributed dataset of coseismic landslide mapping via multi-source high-resolution remote sensing images Fang, C., Fan, X., Wang, X., Nava, L., Zhong, H., Dong, X., Qi, J., and Catani, F.: A globally distributed dataset of coseismic landslide mapping via multi-source high-resolution remote sensing images, Earth Syst. Sci. Data Discuss. [preprint], https://doi.org/10.5194/essd-2024-239, in review, 2024.   Data description:   The training dataset and the validation dataset are composed of UAV, PlanetScope, Gaofen-6 and Map World images of the 5 earthquake regions of Luding, Nippes, Hokkaido, Jiuzhaigou and Mainling. There is no overlapping area in each TIFF. The training dataset and the validation dataset are randomly divided at a ratio of approximately 0.75:0.25.   train_dataset: train_data: The train dataset part of the GDCLD data set contains 11162 data matrices (TIFF), and the shape of the matrix is (1024, 1024, 3) (TIFF). train_label: The train dataset part of the GDCLD data set contains 11162 data matrices (TIFF), and the shape of the matrix is (1024, 1024, 1) (TIFF).   Validation_dataset val_data: The validation dataset part of the GDCLD data set contains 4459 data matrices (TIFF), and the shape of the matrix is (1024, 1024, 3) (TIFF). val_label: The validation dataset part of the GDCLD data set contains 4459 data matrices (TIFF), and the shape of the matrix is (1024, 1024, 1) (TIFF).   Test_dataset (Lushan, Sumatra, Mesetas and Palu dataset) This package contains the original files of remote sensing images from three sources: UAV, Map World, and PlaneScope belonging to the Lushan, Sumatra, Mesetas and Palu earthquake regiones, which are used to display the test area. Future work: The future work includes additional landslide data that the authors will continue to upload. In this 2.0 version update, we have added UAV imagery and interpreted data for loess landslides triggered by the December 2023 M6.2 earthquake in Gansu, China, with a resolution of 0.1 m. Due to authorization constraints, we can only provide PNG files without geographic coordinates. Additionally, this update includes PlanetScope imagery of landslides induced by heavy rainfall in Guangdong, China, in 2024, as well as PlanetScope imagery and landslide labels for events triggered by the Hualien earthquake in Taiwan. Please note that this landslide dataset is publicly available exclusively for scientific research purposes and must not be used for commercial purposes.

opencc-by-4.0Sep 2024View details →

Gro Cell Colony Image Dataset

Gro Cell Colony Image Dataset The Gro cell colony image dataset is a collection of images featuring bacterial colonies with distinct spatial and spatiotemporal patterns. These images are derived from the <a href="https://github.com/AI-UDP/GRO63">Gro</a> software and are categorized into four primary patterns: 1. Bullseye: A pattern characterized by concentric circles or rings. 2. Sun: A pattern resembling the radial arrangement of sunburst-like structures. 3. Autonomous Bioreactor: A pattern indicative of self-organizing structures typically found in bioreactor environments. 4. Repressilator: A pattern demonstrating the behavior of a synthetic gene regulatory network known as the repressilator. This dataset is valuable for studying and analyzing the growth and behavior of bacterial colonies in various controlled environments.