Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
979
datasets available to search
ShareScore release 0.9.0
Dataset results
979 results for “Image Dataset”
Pre-training with simulated ultrasound images for breast mass segmentation and classification - dataset
<p>Dataset assosiated with the MICCAI Workshop on Data Engineering in Medical Imaging paper: "Pre-training with Simulated Ultrasound Images for Breast Mass Segmentation and Classification"</p>
Dataset and images for "Instantaneous R calculation for COVID-19 epidemic in Brazil"
<p>This dataset was generated from raw data obtained at </p> <ul> <li>Ceará State - <a href="https://indicadores.integrasus.saude.ce.gov.br/api/casos-coronavirus/export-csv">https://indicadores.integrasus.saude.ce.gov.br/api/casos-coronavirus/export-csv</a></li> <li>São Paulo State - <a href="http://www.seade.gov.br/wp-content/uploads/2020/04/Dados-covid-19-estado.csv">http://www.seade.gov.br/wp-content/uploads/2020/04/Dados-covid-19-estado.csv</a></li> <li>Brazil - <a href="https://covid.saude.gov.br/">https://covid.saude.gov.br/</a></li> </ul> <p>Data was processed with R package EpiEstim (methodology in the associated preprint). Briefly, instantaneous R was estimated within a 5 day time window. Prior mean and standard deviation values for R were set at 3 and 1. Serial interval was estimated using a parametric distribution with uncertainty (offset gamma). We compared the results at two time points (day 7 and day 21 after the first case was registered at each region) from different brazillian states in order to make inferences about the epidemic dynamics.</p>
68 image lysozyme dataset recorded on the Jungfrau 16M detector at SwissFEL and formatted as a NeXus file
<p>Data provided by Meitian Wang at PSI and master file revised May 2020 for full NXmx compliance.</p> <p>To create a new NeXus master file, assuming DIALS is installed in the folder $DIALS, use this command:</p> <p>libtbx.python $DIALS/modules/cctbx_project/xfel/swissfel/jf16m_cxigeom2nexus.py unassembled_file=lyso009a_0087.JF07T32V01.h5 geom_file=16M_bernina_backview_optimized_adu_quads.geom wavelength=1.368479 detector_distance=97.830 mask_file=lyso009a_0087.JF07T32V01.mask.h5 nexus_details.start_time=2018-01-00T00:00:00.000 nexus_details.end_time=2018-01-00T00:00:02.720Z nexus_details.end_time_estimated=2018-01-00T00:00:02.720Z nexus_details.sample_name=Lysozyme nexus_details.total_flux=1000000000000</p> <p>Some notes about the parameters:<br> - Geometry file is in CrystFEL format but has been realigned to group the modules hierarchically into quadrants.<br> - Wavelength is a single wavelength for the whole dataset, but options exist to do 1 wavelength per image, or a whole spectrum per image.<br> - Start and end times are example timestamps for illustration. End times are estimated for 68 frames using a 25 Hz recording rate.<br> - Total flux of 1e12 photons is an estimate.</p> <p>View the data using DIALS: dials.image_viewer lyso009a_0087.JF07T32V01_master.h5</p> <p>Process the data using DIALS, treating the images as stills, assuming 64 cores available on the system:<br> dials.stills_process mp.nproc=64 lyso009a_0087.JF07T32V01_master.h5 dispersion.gain=10 known_symmetry.space_group=P43212 known_symmetry.unit_cell=77,77,37,90,90,90 refinement_protocol.d_min_start=2.5</p> <p>Download DIALS at dials.github.io.</p>
Tutorial and dataset for gigapixel-like imaging strategies for dental anthropology
<p>This tutorial and image dataset to accompany the following publication: Willman JC, Lozano M, Hernando R, Vergès JM. Gigapixel-like imaging strategies for dental anthropology: Applications for scientific communication and training in digital image analysis. Quaternary International, <a href="https://doi.org/10.1016/j.quaint.2020.05.027">https://doi.org/10.1016/j.quaint.2020.05.027</a>. Part of the Special Issue: Not Only Use.</p> <p><strong>Contains: </strong>tutorial,<strong> </strong>183 images files for reconstructing three examples of gigapixel-like images, and one “READ ME” file describing the images.</p> <p>The tutorial is meant to be used as a guideline for the creation of gigapixel-like (GPL) images of dental surfaces based on our experience. The methodology can be extrapolated to other types of materials and surfaces, but you may need to augment these guidelines according to the specificity of your own research needs. We hope that the inclusion of this supplement will stimulate other researchers to include specific guidelines and step-by-step processes for how they created their own GPL images. While this study concentrates on scanning electron microscopy (SEM) images, there are many other ways to acquire two-dimensional images (e.g., digital photography, optical light microscopy, etc.) that can be used to create GPL images. Likewise, the number of software packages and their numerous built-in parameters for creating extended focus and mosaic images vary greatly. Therefore, more tutorials/guidelines will surely improve the transparency and accessibility of the GPL methodology in the archaeological sciences, biological anthropology, and allied fields.</p>
Imaging spectroscopy and elemental mapping of Haughton impact melt rock: Datasets
<p>Description of archived data for manuscript Greenberger et al. (accepted, JGR Planets)<br> </p> <p>This archive contains the data underlying the results reported in the following paper:<br> Greenberger, R. N., Ehlmann, B. L., Osinski, G. R., Tornabene, L. L., & Green, R. O. Compositional Heterogeneity of Impact Melt Rocks at the Haughton Impact Structure, Canada: Implications for Planetary Processes and Remote Sensing. Journal of Geophysical Research: Planets, accepted.<br> 1. ImageList.txt: Contains information required to connect sample names from paper with images, which often contain multiple samples.<br> 2. FieldImages.tar.gz: Imaging spectroscopy files from images of outcrops in the field<br> 3. LabImages.tar.gz: Imaging spectroscopy files from samples imaged in the laboratory<br> 4. XRF_Data.tar.gz: Elemental mapping of cut samples via mapping x-ray fluorescence</p> <p>Imaging spectroscopy files (for all below, * is image name from ImageList.txt):<br> 1. *_SWIRcalib.img files: Laboratory images of samples processed to reflectance, including a dark current subtraction, line-by-line ratio to an image of Spectralon acquired with identical lighting, and correction for the reflectance properties of Spectralon. These files are stored with BIL interleave.<br> 2. *_SWIRcalib.hdr files: Header files for (1).<br> 3. *_SWIRcalib_atmcorr.img: Images of outcrops acquired in the field processed to reflectance, including instrument level corrections (dark current subtraction and flat field correction) and atmospheric correction (dark object subtraction and correction to in-scene Spectralon calibration target).<br> 4. *_SWIRcalib_atmcorr.hdr: Header files for (3).<br> 5. mask# and mask#.hdr: Masks and associated header files where the sample or region of interest has a value of 1 and outside of the sample or region of interest has a value of 0. Imaging spectroscopy measurements of multiple samples were sometimes acquired within the same image, and each sample has its own mask. ImageList.txt shows conversions from image and mask names to sample numbers. For files with no # after mask, only one sample or region of interest is present within the image.<br> 6. *_SWIRcalibmask#_MAP, *_SWIRcalib_atmcorrmask_MAP, and corresponding .hdr files: These are image files with 12 bands, one for each lithologic classification in the paper, and associated header files. Values of 1 indicate that the lithology is present, and values of 0 indicate that it is absent. The mask files (5) were used to ignore areas outside of the sample or outcrop. The band named "Mixed 2.2 and 2.3 micron features" is Mixed Carbonate + Si-OH, and "Illite-y" is Illite-like. These files are stored with BSQ interleave.</p> <p>X-ray fluorescence (XRF) data:<br> Each folder corresponds with measurements of a single sample. These are measurements of the same surfaces of some cut samples analyzed by imaging spectroscopy. ImageList.txt gives the corresponding image cubes. All exported elements are .tsv files and are in quantized relative counts as exported by the instrument software. Data for Mg are unreliable due to its low atomic number, as is typical for XRF.</p>
Image captioning dataset for human activities
<p>An image captioning dataset including images of humans performing various activities. The included images include the following activities: <code>walking, running, sleeping, swimming, sitting, jumping, riding, climbing, drinking and reading.</code></p>
Cu dataset – A copper ore labeled images dataset for segmentation training and testing
<p>This dataset is composed of 121 pairs of correlated images. Each pair contains one image of a copper ore sample acquired through reflected light microscopy (RGB, 24-bit), and the corresponding binary reference image (8-bit), in which the pixels are labeled as belonging to one of two classes: ore (0) or embedding resin (255).</p> <p>The sample came from a copper ore from Yauri Cusco (Peru) with a complex mineralogy, mainly composed of sulfides, oxides, silicates, and native copper. It was classified by size. The fraction +74-100 μm was cold mounted with epoxy resin and subsequently ground and polished.</p> <p>Correlative microscopy was employed for image acquisition. Thus, 121 fields were imaged on a reflected light microscope with a 20× (NA 0.40) objective lens and on a scanning electron microscope (SEM). In sequence, they were registered, resulting in images of 1017×753 pixels with a resolution of 0.53 µm/pixel. As matter of fact, some images (the images No. 2, 3, 24, 25, 46, 47, 69, 91, and 113) have slightly smaller sizes because they were cropped during the registration procedure to correct co-localization errors of the order of a few pixels. Finally, the images from SEM were thresholded to generate the reference images.</p> <p>Further description of this sample and its imaging procedure can be found in the work by Gomes and Paciornik (2012).</p> <p>This dataset was created for developing and testing deep learning models on semantic segmentation tasks. The paper of Filippo et al. (2021) presented a variant of the DeepLabv3+ model (Chen et al., 2018) that reached mean values of 90.56% and 92.12% for overall accuracy and F1 score, respectively, for 5 rounds of experiments (training and testing), each with a different, random initialization of network weights.</p> <p>For further questions and suggestions, please do not hesitate to contact us.</p> <p> </p> <p><strong>Contact email</strong>: ogomes@gmail.com</p> <p> </p> <p>If you use this dataset in your own work, please cite this DOI: 10.5281/zenodo.5020566</p> <p> </p> <p>Please also cite this paper, which provides additional details about the dataset:</p> <p>Michel Pedro Filippo, Otávio da Fonseca Martins Gomes, Gilson Alexandre Ostwald Pedro da Costa, Guilherme Lucio Abelha Mota. <em>Deep learning semantic segmentation of opaque and non-opaque minerals from epoxy resin in reflected light microscopy images</em>. <strong>Minerals Engineering</strong>, Volume 170, 2021, 107007, https://doi.org/10.1016/j.mineng.2021.107007.</p>
Diffraction images of crystals of the spectrin repeats 7 and 8 (SR7-SR8) of the plakin domain of human plectin (PDB code 5J1G): native and Hg-derivative datasets for phasing by SIRAS
<p>Diffraction images of crystals of a fragment of the plakin domain of human plectin that includes the spectrin repeats 7 to 8 (SR7-SR8).</p> <p>Images correspond to the dataset used to solve and refine the pdb entry <strong>5J1G</strong> (http://www.rcsb.org/pdb/explore/explore.do?structureId=5J1G).</p> <p> </p> <p>The structure was phase by single isomorphous replacement with anomalous scattering (SIRAS) using two datasets: one from a native crystal and another one from a crystal derivatized with the mercurial compound ethylmercurithiosalicylate (EMTS).</p> <p> </p> <p>The <strong>Native dataset</strong> was collected on a single crystal at the beamline XALOC of the ALBA Synchrotron (Barcelona, Spain) using radiation of 0.9792 Å wavelength and a PILATUS 6M detector. The dataset consists of 4 wedges of 450 images each (0.2º oscillation per image). Each wedge was collected at a different position of the same crystal. The crystals belong to the space group P2<sub>1</sub> with approximate cell dimensions <em>a</em>=45.7 Å, <em>b</em>=115.9 Å, <em>c</em>=64.8 Å, beta=97.6 º.</p> <p> </p> <p>The data from a <strong>mercurial derivative</strong> (EMTS) was collected in house using a rotating anode X-ray generator (wavelength 1.54179 Å) and a mar345 image plate detector. The dataset consists of 360 images (1º oscillation per image). The crystal was isomorphic to the native crystal.</p> <p> </p> <p>In addition to the diffraction images the following files are included:</p> <p>a) Files for indexing with the program XDS and the HKL files containing the integrated intensities.</p> <p>b) Files for scaling using the program xscale (directory XSCALE_5J1G_Native_EMTS).<br> c) The directory “phasing_shelx” contains hkl files of the intensities of the native and EMTS datasets in a format suitable for analysis with Shelx. This directory also contains the files of the phasing by SIRAS using Shelx C/D/E.</p>
A Public Ground-Truth Dataset for Handwritten Circuit Diagram Images
<p><strong>CGHD</strong></p> <p>This dataset contains images of hand-drawn electrical circuit diagrams as well as accompanying annotation and segmentation ground-truth files. It is intended to train (e.g. ANN) models for extracting electrical graphs from raster graphics.</p> <p><strong>Content</strong></p> <ul> <li><strong>3.269</strong> Annotated Raw Images<br> <ul> <li>31 Main Drafters <ul> <li>12 Circuits per Drafter</li> <li>2 Drawings per Circuit</li> <li>4 Photos per Drawing</li> </ul> </li> <li>Additional Circuit Images provided by TU Dresden (from Real-World Examinations, Drafter 0)</li> <li>Additional Circuit Images provided by RPTU Kaiserslautern-Landau (Drafter -1)</li> <li><strong>248.020 </strong>Bounding Box Annotations</li> <li><strong>40.711</strong> Rotation Annotations</li> <li><strong>1.437</strong> Mirror Annotations</li> <li><strong>85.417</strong> Text String Annotations (equals <strong>93.74%</strong> completeness)<br> <ul> <li><strong>289.850</strong> Text Characters</li> <li><strong>98</strong> Character Types (Upper/Lower Case Latin, Numbers, Special Characters)</li> </ul> </li> </ul> </li> <li><strong>320</strong> Binary Segmentation Maps<br> <ul> <li>Strokes vs. Background</li> <li>Accompanying Polygon Annotation Files</li> <li><strong>22.929</strong> Polygon Annotations</li> </ul> </li> <li><strong>59 </strong>Object Classes</li> <li><strong>Scripts</strong> for Data Loading, Statistics, Consistency Check and Training Preparation</li> </ul>
MultiCaRe: An open-source clinical case dataset for medical image classification and multimodal AI applications
<p>The dataset contains multi-modal data from over 70,000 open access and de-identified case reports, including metadata, clinical cases, image captions and more than 130,000 images. Images and clinical cases belong to different medical specialties, such as oncology, cardiology, surgery and pathology. The structure of the dataset allows to easily map images with their corresponding article metadata, clinical case, captions and image labels. Details of the data structure can be found in the file data_dictionary.csv.</p> <p>More than 90,000 patients and 280,000 medical doctors and researchers were involved in the creation of the articles included in this dataset. The citation data of each article can be found in the metadata.parquet file.</p> <p>Refer to the examples showcased in this <a href="https://github.com/mauro-nievoff/MultiCaRe_Dataset">GitHub repository</a> to understand how to optimize the use of this dataset.<br><br>The license of the dataset as a whole is CC BY-NC-SA. However, its individual contents may have less restrictive license types (CC BY, CC BY-NC, CC0). For instance, regarding image filess, 66K of them are CC BY, 32K are CC BY-NC-SA, 32K are CC BY-NC, and 20 of them are CC0.</p>
K1702 - Kura Clover (Trifolium ambiguum) USDA Accession Image Dataset
<p><strong>Images</strong></p> <p>This dataset consists of 1135 images of Kura clover (Trifolium ambiguum) USDA accessions grown at The Land Institute in Salina, Kansas over the 2017 growing season. Each image contains a single Kura clover plant framed by a 1/2" PVC sampling quadrat with internal dimensions of 16"x16" (internal area of 0.165 m2). Kura clover plots were hand weeded to remove all other vegetation except Kura clover. Some images may contain dead clover accessions that are either brown and dried up, or missing entirely. The images were acquired with a Canon EOS Rebel T6 DSLR camera under the following settings:</p> <ul> <li>ISO: 200</li> <li>Exposure: Auto</li> <li>Focal Length: Variable (33-40mm)</li> <li>Format: JPEG</li> <li>Size: 5184x3456</li> <li>Metering Mode: Multi-segment</li> </ul> <p>Images were acquired on two different dates: 2017-06-08 and 2017-07-03 and were named using the following convention "<IMG_ID>_<yyyymmdd>.jpg". All image can be found in processed/images folder. No image preprocessing was performed.</p> <p><strong>Annotations</strong></p> <p>The annotations consist of segmentation masks and bounding boxes. Each segmentation mask is saved as a png image and named using the convention "IMG_ID>_<yyyymmdd>.png". The segmentation class labels ('segmentation_class_map.json') are as follows:</p> <ul> <li>0: 'soil' background class containing all soil and non-target materials</li> <li>1: 'quadrat'</li> <li>2: 'clover'</li> </ul> <p>We drew bounding boxes for the quadrat, each quadrat corner, and the entire clover plant. The class labels ('obj_det_class_map.json') are as follows:</p> <ul> <li>1: 'clover'</li> <li>2: 'quadrat'</li> <li>3: 'quadrat_corner'</li> </ul> <p>Bounding boxes are in (xmin, ymin, xmax, ymax) format and can be found in 'bboxes.csv'.</p> <p>All images are annotated using Labelbox software. Masks were generated by point prompts using Meta's Segment Anything model (SAM). The point prompts used to generate the masks can be found in 'SAM_points.csv'</p> <p>Additionally, some kura clover plants died or are not present in the plots where they were planted. We included the file 'plant_status.csv' to indicate which images include a living plant or a dead one.</p> <p><strong>Train/Val/Test Split</strong></p> <p>All 1035 images were randomly split with an 80/20 split on 1000 of the images (n=880, n=220) with the final 35 images reserved for the test holdout set. The file 'data_split.csv' holds the split class for each image.</p> <p>This dataset is released under a Creative Commons Attribution 4.0 International license which allows redistribution and re-use of the data herein as long as all authors are appropriately credited.</p>
Type III interferons may suppress viral infections by triggering cell death -- Imaging Dataset
<p>This dataset accompanies the article "Type III interferons may suppress viral infections by triggering cell death". Earlier version is available as a preprint, <a href="https://doi.org/10.1101/2024.09.09.612051" target="_blank" rel="noopener">https://doi.org/10.1101/2024.09.09.612051</a>. The updated dataset includes quantifications for Figure 7C and Figure 7D.</p>
Product Images of Life Cycle Assessment Dataset For Peritoneal Dialysis in Madrid, Spain
<p>The database contains a collection of images showcasing the individual components of peritoneal dialysis (PD) products, along with their corresponding weights. These images serve as a visual record for life cycle assessment (LCA) purposes, focusing on the material composition and environmental impact of each product.</p> <ol> <li> <p><strong>Patient Education Materials</strong>: Photographs of educational materials provided to patients, with accompanying data on the weight of the paper and packaging.</p> </li> <li> <p><strong>Catheters and Surgical Kits</strong>: Images display the disassembled components of PD catheters and surgical kits, including tubing, connectors, and packaging. Each image is annotated with the precise weight of the individual components.</p> </li> <li> <p><strong>Dialysis Solution Bags</strong>: The database includes images of both CAPD and APD solution bags, separated into their constituent parts (e.g., plastic bag, solution, and protective wrapping), with weights noted for each component.</p> </li> <li> <p><strong>Connection Devices and Consumables</strong>: Detailed images of connection devices, clamps, and other consumable items, with individual component weights clearly labeled.</p> </li> <li> <p><strong>Packaging and Transport Materials</strong>: Photographs of transport packaging, such as cardboard boxes and plastic wraps, alongside recorded weights for each element.</p> </li> <li> <p><strong>Maintenance Items</strong>: Visuals of terminal catheter sets, cleaning agents, and related products, each accompanied by their respective weight data.</p> </li> <li> <p><strong>Disposal Components</strong>: Images of used solution bags, syringes, and other single-use items, separated into recyclable and non-recyclable components, with weights specified for each.</p> </li> </ol> <p>This image-based database provides a clear and comprehensive reference for the material breakdown and weight distribution of PD product components, essential for conducting a thorough LCA and identifying areas for environmental improvement.</p>
Dataset for Fisher et al. (2023). Motion stereo at sea: Dense 3D reconstruction from image sequences monitoring conveyor systems on board fishing vessels. IET Image Processing, 17(2), pp.349-361.
<p>This dataset contains the video clips used to produce the results presented in:</p><p>Fisher, M., French, G., Gorpincenko, A., Holah, H., Clayton, L., Skirrow, R. and Mackiewicz, M., 2023. Motion stereo at sea: Dense 3D reconstruction from image sequences monitoring conveyor systems on board fishing vessels. IET Image Processing, 17(2), pp.349-361.</p>
ARCADE: Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs Dataset
<p>ARCADE: Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs Dataset Phase 2 consist of two folders with 300 images in each of them as well as annotations. </p> <p>ARCADE: Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs Dataset Phase 1 consists of two datasets of XCA images for each of two tasks of ARCADE challenge. The first task includes in total 1200 coronary vessel tree images, which are divided into train(1000) and validation(200) groups, images for training are followed with annotations, depicting the division of a heart into 26 different regions based on the Syntax Score methodology[1]. Similarly, the second task includes a different set of 1200 images with same train-val division proportion with annotated regions containing atherosclerotic plaques. This dataset, carefully annotated by medical experts, enables scientists to actively contribute towards the advancement of an automated risk assessment system for patients with CAD. </p> <p>The dataset structure is as follows: top-level directories "syntax" and "stenosis" contain files for the two dataset objectives, namely: i) vessel branch classification according to the SYNTAX methodology; and ii) stenosis detection. Inside both directories, there are 3 subsets of the dataset, such as "train", "val", and "test". Inside each of those folders, there are 2 lower-level directories - "images", and "annotations". Inside the "images" folder there are images in ".png" format, extracted from DICOM recordings. The "annotations" folders contain single ".JSON" files, which are named in correspondence to the objective, i.e. "train.JSON", "val.JSON", and "test.JSON".</p> <p>The structure of ".JSON" contains three top-level fields: "images", "categories", and "annotations". The "images" field contains the unique "id" of the image in the dataset, its "width" and "height" in pixels, and the "file_name" sub-field, which contains specific information about the image. The "categories" field contains a unique "id" from 1 to 26, and a "name", relating it to the SYNTAX descriptions. The "annotations" field contains a unique "id" of the annotation, "image_id" value, relating it to the specific image from the "images" field, and a "category_id" relating it to the specific category from the "categories" field. The "segmentation" sub-field contains coordinates of mask edge points in "XYXY" format. Bounding box coordinates are given in the "bbox" field in the "XYWH" format, where the first 2 values represent the x and y coordinates of the left-most and top-most points in the segmentation mask. The height and width of the bounding box are determined by the difference between the right-most and bottom-most points and the first two values. Finally, the "area" field provides the total area of the bounding box, calculated as the area of a rectangle.</p> <p> </p> <p>The corresponding Dataset Article will be provided later. </p> <p>[1] Syntax score segment definitions. https://syntaxscore.org/index.php/tutorial/definitions/14-appendix-i-segment-definitions</p>
Metadata of a Large Sonar and Stereo Camera Dataset Suitable for Sonar-to-RGB Image Translation
<h1>Metadata of a Large Sonar and Stereo Camera Dataset Suitable for Sonar-to-RGB Image Translation</h1> <h2>Introduction</h2> <p>This is a set of metadata describing a large dataset of synchronized sonar and stereo camera recordings, that were captured between August 2021 and September 2023 during the project <a href="https://robotik.dfki-bremen.de/en/research/projects/deepersense/">DeeperSense</a> (https://robotik.dfki-bremen.de/en/research/projects/deepersense/), as training data for Sonar-to-RGB image translation. <a href="../records/7728089">Parts</a> <a href="../records/10220989">of</a> the sensor data have been published (https://zenodo.org/records/7728089, https://zenodo.org/records/10220989). Due to the size of the sensor data corpus, it is currently impractical to make the entire corpus accessible online. Instead, this metadatabase serves as a relatively compact representation, allowing interested researchers to inspect the data, and select relevant portions for their particular use case, which will be made available on demand. This is an effort to comply with the <a href="https://www.go-fair.org/fair-principles/">FAIR</a> principle A2 (https://www.go-fair.org/fair-principles/) that metadata shall be accessible, even when the base data is not immediately.</p> <h3>Locations and sensors</h3> <p>The sensor data was captured at four different locations, including one laboratory (Maritime Exploration Hall at DFKI RIC Bremen) and three field locations (Chalk Lake Hemmoor, Tank Wash Basin Neu-Ulm, Lake Starnberg). At all locations, a ZED camera and a Blueprint Oculus M1200d sonar were used. Additionally, a SeaVision camera was used at the Maritime Exploration Hall at DFKI RIC Bremen and at the Chalk Lake Hemmoor. The <code>examples/</code> directory holds a typical output image for each sensor at each available location.</p> <h3>Data volume per session</h3> <p>Six data collection sessions were conducted. The table below presents an overview of the amount of data captured in each session:</p> <table> <tbody> <tr> <th>Session dates</th> <th>Location</th> <th>Number of datasets</th> <th>Total duration of datasets [h]</th> <th>Total logfile size [GB]</th> <th>Number of images</th> <th>Total image size [GB]</th> </tr> <tr> <td>2021-08-09 - 2021-08-12</td> <td>Maritime Exploration Hall at DFKI RIC Bremen</td> <td>52</td> <td>10.8</td> <td>28.8</td> <td>389’047</td> <td>88.1</td> </tr> <tr> <td>2022-02-07 - 2022-02-08</td> <td>Maritime Exploration Hall at DFKI RIC Bremen</td> <td>35</td> <td>4.4</td> <td>54.1</td> <td>629’626</td> <td>62.3</td> </tr> <tr> <td>2022-04-26 - 2022-04-28</td> <td>Chalk Lake Hemmoor</td> <td>52</td> <td>8.1</td> <td>133.6</td> <td>1’114’281</td> <td>97.8</td> </tr> <tr> <td>2022-06-28 - 2022-06-29</td> <td>Tank Wash Basin Neu-Ulm</td> <td>42</td> <td>6.7</td> <td>144.2</td> <td>824’969</td> <td>26.9</td> </tr> <tr> <td>2023-04-26 - 2023-04-27</td> <td>Maritime Exploration Hall at DFKI RIC Bremen</td> <td>55</td> <td>7.4</td> <td>141.9</td> <td>739’613</td> <td>9.6</td> </tr> <tr> <td>2023-09-01 - 2023-09-02</td> <td>Lake Starnberg</td> <td>19</td> <td>2.9</td> <td>40.1</td> <td>217’385</td> <td>2.3</td> </tr> <tr> <th> </th> <th> </th> <th>255</th> <th>40.3</th> <th>542.7</th> <th>3’914’921</th> <th>287.0</th> </tr> </tbody> </table> <h2>Data and metadata structure</h2> <h3>Sensor data corpus</h3> <p>The sensor data corpus comprises two processing stages:</p> <ul> <li>raw data streams stored in ROS bagfiles (aka <strong>logfiles</strong>),</li> <li>camera and sonar images (aka <strong>datafiles</strong>) extracted from the logfiles.</li> </ul> <p>The files are stored in a file tree hierarchy which groups them by session, dataset, and modality:</p> <pre><code>${session_key}/ ${dataset_key}/ ${logfile_name} ${modality_key}/ ${datafile_name}</code></pre> <p>A typical logfile path has this form:</p> <pre><code>2023-09_starnberg_lake/ 2023-09-02-15-06_hydraulic_drill/ stereo_camera-zed-2023-09-02-15-06-07.bag</code></pre> <p>A typical datafile path has this form:</p> <pre><code>2023-09_starnberg_lake/ 2023-09-02-15-06_hydraulic_drill/ zed_right/ 1693660038_368077993.jpg</code></pre> <p>All directory and file names, and their particles, are designed to serve as identifiers in the metadatabase. Their formatting, as well as the definitions of all terms, are documented in the file <code>entities.json</code>.</p> <h3>Metadatabase</h3> <p>The metadatabase is provided in two equivalent forms:</p> <ul> <li>as a standalone <a href="https://www.sqlite.org/index.html">SQLite</a> (https://www.sqlite.org/index.html) database file <code>metadata.sqlite</code> for users familiar with SQLite,</li> <li>as a collection of CSV files in the <code>csv/</code> directory for users who prefer other tools.</li> </ul> <p>The database file has been generated from the CSV files, so each database table holds the same information as the corresponding CSV file. In addition, the metadatabase contains a series of convenience views that facilitate access to certain aggregate information.</p> <p>An entity relationship diagram of the metadatabase tables is stored in the file <code>entity_relationship_diagram.png</code>. Each entity, its attributes, and relations are documented in detail in the file <code>entities.json</code></p> <p>Some general design remarks:</p> <ul> <li>For convenience, timestamps are always given in both a human-readable form (ISO 8601 formatted datetime strings with explicit local time zone), and as seconds since the UNIX epoch.</li> <li>In practice, each logfile always contains a single stream, and each stream is stored always in a single logfile. Per database schema however, the entities <code>stream</code> and <code>logfile</code> are modeled separately, with a “many-streams-to-one-logfile” relationship. This design was chosen to be compatible with, and open for, data collections where a single logfile contains multiple streams.</li> <li>A <code>modality</code> is not an attribute of a <code>sensor</code> alone, but of a <code>datafile</code>: Because a <code>sensor</code> is an attribute of a <code>stream</code>, and a single stream may be the source of multiple modalities (e.g. RGB vs. grayscale images from the same camera, or cartesian vs. polar projection of the same sonar output). Conversely, the same modality may originate from different sensors.</li> </ul> <p>As a usage example, the data volume per session which is tabulated at the top of this document, can be extracted from the metadatabase with the following SQL query:</p> <div> <pre><code><span><span>SELECT</span></span> <span> PRINTF(</span> <span> <span>'%s - %s'</span>,</span> <span> <span>SUBSTR</span>(session_start, <span>1</span>, <span>10</span>),</span> <span> <span>SUBSTR</span>(session_end, <span>1</span>, <span>10</span>)) <span>AS</span> <span>'Session dates'</span>,</span> <span> location_name_english <span>AS</span> Location,</span> <span> number_of_datasets <span>AS</span> <span>'Number of datasets'</span>,</span> <span> total_duration_of_datasets_h <span>AS</span> <span>'Total duration of datasets [h]'</span>,</span> <span> total_logfile_size_gb <span>AS</span> <span>'Total logfile size [GB]'</span>,</span> <span> number_of_images <span>AS</span> <span>'Number of images'</span>,</span> <span> total_image_size_gb <span>AS</span> <span>'Total image size [GB]'</span></span> <span><span>FROM</span></span> <span> location</span> <span> <span>JOIN</span> <span>session</span> <span>USING</span> (location_id)</span> <span> <span>JOIN</span> (</span> <span> <span>SELECT</span></span> <span> session_id,</span> <span> <span>COUNT</span>(dataset_id) <span>AS</span> number_of_datasets,</span> <span> <span>ROUND</span>(</span> <span> <span>SUM</span>(dataset_duration) <span>/</span> <span>3600</span>,</span> <span> <span>1</span>) <span>AS</span> total_duration_of_datasets_h,</span> <span> <span>ROUND</span>(</span> <span> <span>SUM</span>(total_logfile_size) <span>/</span> <span>10e9</span>,</span> <span> <span>1</span>) <span>AS</span> total_logfile_size_gb</span> <span> <span>FROM</span></span> <span> location</span> <span> <span>JOIN</span> <span>session</span> <span>USING</span> (location_id)</span> <span> <span>JOIN</span> dataset <span>USING</span> (session_id)</span> <span> <span>JOIN</span> view__dataset_total_logfile_size <span>USING</span> (dataset_id)</span> <span> <span>GROUP</span> <span>BY</span></span> <span> session_id</span> <span> ) <span>USING</span> (session_id)</span> <span> <span>JOIN</span> (</span> <span> <span>SELECT</span></span> <span> session_id,</span> <span> <span>COUNT</span>(datafile_id) <span>AS</span> number_of_images,</span> <span> <span>ROUND</span>(<span>SUM</span>(datafile_size) <span>/</span> <span>10e9</span>, <span>1</span>) <span>AS</span> total_image_size_gb</span> <span> <span>FROM</span></span> <span> <span>session</span></span> <span> <span>JOIN</span> dataset <span>USING</span> (session_id)</span> <span> <span>JOIN</span> stream <span>USING</span> (dataset_id)</span> <span> <span>JOIN</span> <span>datafile</span> <span>USING</span> (stream_id)</span> <span> <span>GROUP</span> <span>BY</span></span> <span> session_id</span> <span> ) <span>USING</span> (session_id)</span> <span><span>ORDER</span> <span>BY</span> session_id;</span></code></pre> </div>
[MedMNIST+] 18x Standardized Datasets for 2D and 3D Biomedical Image Classification with Multiple Size Options: 28 (MNIST-Like), 64, 128, and 224
<h2><strong>Code</strong> [<a href="https://github.com/MedMNIST/MedMNIST" target="_blank" rel="noopener">GitHub</a>] | <strong>Publication</strong> [<a href="https://doi.org/10.1038/s41597-022-01721-8" target="_blank" rel="noopener">Nature Scientific Data'23</a> / <a href="https://doi.org/10.1109/ISBI48211.2021.9434062" target="_blank" rel="noopener">ISBI'21</a>] | <strong>Preprint</strong> [<a href="https://arxiv.org/abs/2110.14795" target="_blank" rel="noopener">arXiv</a>]</h2> <p> </p> <p><strong>Abstract</strong></p> <p>We introduce MedMNIST, a large-scale MNIST-like collection of standardized biomedical images, including 12 datasets for 2D and 6 datasets for 3D. All images are pre-processed into 28x28 (2D) or 28x28x28 (3D) with the corresponding classification labels, so that no background knowledge is required for users. Covering primary data modalities in biomedical images, MedMNIST is designed to perform classification on lightweight 2D and 3D images with various data scales (from 100 to 100,000) and diverse tasks (binary/multi-class, ordinal regression and multi-label). The resulting dataset, consisting of approximately 708K 2D images and 10K 3D images in total, could support numerous research and educational purposes in biomedical image analysis, computer vision and machine learning. We benchmark several baseline methods on MedMNIST, including 2D / 3D neural networks and open-source / commercial AutoML tools. The data and code are publicly available at <a href="https://medmnist.com/">https://medmnist.com/</a>.</p> <p><em><strong>Disclaimer</strong></em>: The only official distribution link for the MedMNIST dataset is <a href="https://doi.org/10.5281/zenodo.10519652">Zenodo</a>. We kindly request users to refer to this original dataset link for accurate and up-to-date data.</p> <p><strong><em>Update</em>:</strong> We are thrilled to release <a href="https://github.com/MedMNIST/MedMNIST/blob/main/on_medmnist_plus.md">MedMNIST+</a> with larger sizes: 64x64, 128x128, and 224x224 for 2D, and 64x64x64 for 3D. As a complement to the previous 28-size MedMNIST, the large-size version could serve as a standardized benchmark for medical foundation models. Install the latest API to try it out!</p> <p> </p> <p><strong>Python Usage</strong></p> <p>We recommend our official <a href="https://github.com/MedMNIST/MedMNIST">code</a> to download, parse and use the MedMNIST dataset:</p> <blockquote> <pre>% pip install medmnist<br>% python</pre> <div> <div>To use the standard 28-size (MNIST-like) version utilizing the downloaded files:</div> <br> <div>>>> from medmnist import PathMNIST</div> <div>>>> train_dataset = PathMNIST(split="train")</div> <br> <div>To enable automatic downloading by setting `download=True`:</div> <br> <div>>>> from medmnist import NoduleMNIST3D</div> <div>>>> val_dataset = NoduleMNIST3D(split="val", download=True)</div> <br> <div>Alternatively, you can access MedMNIST+ with larger image sizes by specifying the `size` parameter:</div> <br> <div>>>> from medmnist import ChestMNIST</div> <div>>>> test_dataset = ChestMNIST(split="test", download=True, size=224)</div> </div> </blockquote> <p> </p> <p><strong>Citation</strong></p> <p>If you find this project useful, please cite both v1 and v2 paper as:</p> <blockquote> <p>Jiancheng Yang, Rui Shi, Donglai Wei, Zequan Liu, Lin Zhao, Bilian Ke, Hanspeter Pfister, Bingbing Ni. Yang, Jiancheng, et al. "MedMNIST v2-A large-scale lightweight benchmark for 2D and 3D biomedical image classification." Scientific Data, 2023.</p> <p>Jiancheng Yang, Rui Shi, Bingbing Ni. "MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis". IEEE 18th International Symposium on Biomedical Imaging (ISBI), 2021.</p> </blockquote> <p>or using bibtex:</p> <blockquote> <pre>@article{medmnistv2, title={MedMNIST v2-A large-scale lightweight benchmark for 2D and 3D biomedical image classification}, author={Yang, Jiancheng and Shi, Rui and Wei, Donglai and Liu, Zequan and Zhao, Lin and Ke, Bilian and Pfister, Hanspeter and Ni, Bingbing}, journal={Scientific Data}, volume={10}, number={1}, pages={41}, year={2023}, publisher={Nature Publishing Group UK London} } @inproceedings{medmnistv1, title={MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis}, author={Yang, Jiancheng and Shi, Rui and Ni, Bingbing}, booktitle={IEEE 18th International Symposium on Biomedical Imaging (ISBI)}, pages={191--195}, year={2021} }</pre> </blockquote> <p>Please also cite the corresponding paper(s) of source data if you use any subset of MedMNIST as per the description on the <a href="https://medmnist.github.io/">project website</a>.</p> <p> </p> <p><strong>License</strong></p> <p>The MedMNIST dataset is licensed under <em>Creative Commons Attribution 4.0 International</em> (<a href="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0</a>), except DermaMNIST under <em>Creative Commons Attribution-NonCommercial 4.0 International</em> (<a href="https://creativecommons.org/licenses/by-nc/4.0/">CC BY-NC 4.0</a>).</p> <p>The code is under <a href="https://github.com/MedMNIST/MedMNIST/blob/main/LICENSE">Apache-2.0 License</a>.</p> <p> </p> <p><strong>Changelog</strong></p> <p><a href="https://doi.org/10.5281/zenodo.10519652">v3.0</a> (this repository): Released MedMNIST+ featuring larger sizes: 64x64, 128x128, and 224x224 for 2D, and 64x64x64 for 3D.</p> <p><a href="https://doi.org/10.5281/zenodo.10519195">v2.2</a>: Removed a small number of mistakenly included blank samples in OrganAMNIST, OrganCMNIST, OrganSMNIST, OrganMNIST3D, and VesselMNIST3D. </p> <p><a href="https://doi.org/10.5281/zenodo.6496656">v2.1</a>: Addressed an issue in the NoduleMNIST3D file (i.e., nodulemnist3d.npz). Further details can be found in this <a href="https://github.com/MedMNIST/MedMNIST/issues/22#issuecomment-1103438191">issue</a>.</p> <p><a href="https://doi.org/10.5281/zenodo.5208230">v2.0</a>: Launched the initial repository of MedMNIST v2, adding 6 datasets for 3D and 2 for 2D.</p> <p><a href="https://doi.org/10.5281/zenodo.4269852">v1.0</a>: Established the initial repository (in a separate repository) of MedMNIST v1, featuring 10 datasets for 2D.</p> <p> </p> <p><strong>Note</strong>: This dataset is <strong>NOT</strong> intended for clinical use.</p>
Precision viticulture dataset for detailed vineyard mapping composed of geotagged smartphone ground images, phytosanitary status, UAV orthomosaics, 3D point clouds, and RTK GNSS data - Northern Spain, July 2022
<p>This dataset offers a rich multimodal collection of data from vineyards, designed to enhance agricultural research with a focus on vineyard management and disease monitoring. It includes geotagged smartphone ground images in ".7z" format for detailed plant-level analysis, a ".csv" file detailing plants' phytosanitary status for health assessment, UAV-derived 3D Point Clouds and orthomosaics in ".las" and ".tiff" formats for aerial landscape views, and RTK GNSS data in ".shp" format for precise plant geolocations.</p> <p>This dataset can be combined with other datasets to enable a comprehensive view of the vineyards and improve its value:</p> <div> <ul> <li>Ariza-Sentís, Mar, Sergio Vélez, and João Valente. ‘Dataset on UAV RGB Videos Acquired over a Vineyard Including Bunch Labels for Object Detection and Tracking’. <em>Data in Brief</em> 46 (February 2023): 108848. <a href="https://doi.org/10.1016/j.dib.2022.108848">https://doi.org/10.1016/j.dib.2022.108848</a>.</li> <li>Vélez, Sergio, Mar Ariza-Sentís, and João Valente. ‘VineLiDAR: High-Resolution UAV-LiDAR Vineyard Dataset Acquired over Two Years in Northern Spain.’ <em>Data in Brief</em>, October 2023, 109686. <a href="https://doi.org/10.1016/j.dib.2023.109686">https://doi.org/10.1016/j.dib.2023.109686</a>.</li> <li> <div> <div>Vélez, Sergio, Mar Ariza-Sentís, and João Valente. ‘Dataset on Unmanned Aerial Vehicle Multispectral Images Acquired over a Vineyard Affected by Botrytis Cinerea in Northern Spain’. <em>Data in Brief</em> 46 (February 2023): 108876. <a href="https://doi.org/10.1016/j.dib.2022.108876">https://doi.org/10.1016/j.dib.2022.108876</a>.</div> <div> </div> </div> </li> </ul> </div>
A Construction Waste Landfill Dataset of Two Districts in Beijing, China from High Resolution Satellite Images
<p>CWLD_model project shows scripts and instructions on how to use this dataset to train a segmentation model. requirements.txt files provide the libraries you need to run your project. The README.md document details the deployment process and features of each module.</p> <p>You can also visit the GitHub page for scripts and instructions on how to use this dataset for visualizing and plotting basic statistics. The models and the code to execute them are released on <a href="https://github.com/huangleinxidimejd/CWLD_Model">https://github.com/huangleinxidimejd/CWLD_Model</a>.</p> <h2>Training details</h2> <p>The model was trained with two GPUs, an Nvidia GeForce RTX 2080Ti, and the following parameters:</p> <ul> <li>'train_batch_size': 4,</li> <li>'val_batch_size': 4,</li> <li>'train_crop_size': 512,</li> <li>'val_crop_size': 512,</li> <li>'lr': 0.001, # the learning rate used during training. It determines how quickly the model learns from the data</li> <li>'Epoch Times': 200,</li> <li>'gpu': correct,</li> <li>'weight_decay': 5E-4,</li> <li>'Momentum': 0.9,</li> <li>'print_freq': 100,</li> <li>'predict_step': 5,</li> </ul> <h2>usage</h2> <ul> <li>After downloading the dataset from Zenodo, place the train and val files from the Deep Learning Datasets file into the data folder of the CWLD semantic segmentation model.</li> <li>Open: CWLD_ Open the root directory in CWLD_model/dataset/ and start training with the WasteSeg_Train.py file. The modelss module provides five convolutional networks, Improved_DeeplabV3_plus, PSPNet, ResNet, SegNet, and UNet, which can be selected and modified accordingly.</li> <li>The utils package provides a large number of data processing tools to use.</li> <li>The trained model can be predicted from a EvalSeg.py file.</li> </ul>
OCTDL: Optical Coherence Tomography Dataset for Image-Based Deep Learning Methods
<p>Optical coherence tomography (OCT) is a non-invasive imaging technique that has extensive clinical applications in ophthalmology. OCT enables the visualization of the retinal layers, playing a vital role in the early detection and monitoring of retinal diseases. OCT uses the principle of light wave interference to create detailed images of the retinal microstructures, making it a valuable tool for diagnosing ocular conditions. Optical Coherence Tomography Dataset for Image-Based Deep Learning Methods (OCTDL) comprising over 2000 OCT images labeled according to disease group and retinal pathology.</p> <p>The dataset consists of the following categories and images:<br>- Age-Related Macular Degeneration - 1231 images;<br>- Diabetic Macular Edema - 147 images;<br>- Epiretinal Membrane- 155 images;<br>- Normal - 332 images;<br>- Retinal Artery Occlusion - 22 images;<br>- Retinal Vein Occlusion - 101 images;<br>- Vitreomacular Interface Disease - 76 images.</p> <p>This dataset is published to provide researchers and developers with access to a large set of labeled images, which contributes to the development and improvement of algorithms for the automatic processing and analysis of OCT images for early diagnosis and monitoring of eye diseases. CSV file consists of file_name, disease, subcategory, condition, patient_id, eye, sex, year, image_width, and image_height. The dataset will be updated periodically.</p> <p> </p> <p>For more information and details about the dataset see:</p> <p>https://rdcu.be/dELrE</p> <p>https://arxiv.org/abs/2312.08255</p> <pre>@article{kulyabin2024octdl, title={OCTDL: Optical Coherence Tomography Dataset for Image-Based Deep Learning Methods}, author={Kulyabin, Mikhail and Zhdanov, Aleksei and Nikiforova, Anastasia and Stepichev, Andrey <br> and Kuznetsova, Anna and Ronkin, Mikhail and Borisov, Vasilii and Bogachev, Alexander <br> and Korotkich, Sergey and Constable, Paul A and Maier, Andreas}, journal={Scientific Data}, volume={11}, number={1}, pages={365}, year={2024}, publisher={Nature Publishing Group UK London},<br> doi={https://doi.org/10.1038/s41597-024-03182-7} } </pre>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.