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.
438
datasets available to search
ShareScore release 0.9.0
Dataset results
438 results for “3D imaging”
3D Tomography Images of wheat grains for several development stages
<p>Images of wheat grains acquired by 3D tomography at various stages of the early development of the grain. This data set serves as companion for the article "Use of X-ray micro computed tomography imaging to analyze the morphology of wheat grain through its development" submitted to the "Plant Methods" journal.</p> <p><strong>Grain samples</strong></p> <p>A total of 41grains obtained at height different stages was imaged. The files correspond to the collections of grains at each stage:</p> <ul> <li>060 degree-days: 5 grains</li> <li>080 degree-days: 5 grains</li> <li>100 degree-days: 5 grains</li> <li>120 degree-days: 5 grains</li> <li>180 degree-days: 6 grains</li> <li>210 degree-days: 5 grains</li> <li>270 degree-days: 5 grains</li> <li>310 degree-days: 5 grains</li> </ul> <p>A more detailed description is provided in the file "<a href="https://zenodo.org/api/files/923a7508-b325-4264-8553-6a62092bb84d/wheatGrainTomoDataset.pdf">wheatGrainTomoDataset.pdf</a>".</p> <p><strong>Image format</strong></p> <p>All images are in TIFF format.</p> <p>Two kinds of images are provided: the volumes of the whole grains after conversion tu 256 gray levels, and the results of the segmentation of the grains as described in the manuscript. </p>
VoroCrack3d: An annotated data set of 3d CT concrete images with synthetic crack structures
<p>VoroCrack3d is an annotated data set of 3d CT images of concrete with synthetic crack structures. Its main purpose is the training and testing of machine learning models for 3d crack segmentation. The data set comprises 1344 images together with their corresponding ground truths. The concrete backgrounds are cropped out sections of size 400x400x400 voxels of CT images of concrete. To this end, several different concrete samples were scanned (normal concrete (NC), high-performance concrete (HPC), ultra-high-performance concrete (UHPC), air pore concrete; without and with reinforcements (straight steel fibers, crimped steel fibers, hooked-end steel fibers, polypropylene fibers, fibers made of glass fiber-reinforced polymer). The original concrete images have a resolution between 2.8 and 106 micrometers.</p> <p>The crack structures are modeled via minimum-weight surfaces in Voronoi diagrams according to the paper</p> <p>[1] C. Jung, C. Redenbach, Crack Modeling via Minimum-Weight Surfaces in 3d Voronoi Diagrams, Journal of Mathematics in Industry, 13, 10 (2023). https://doi.org/10.1186/s13362-023-00138-1.</p> <p>The surfaces are discretized, dilated and superimposed on the concrete backgrounds.</p> <p>The data set offers a high variety regarding concrete types, noise levels and crack widths, shapes, regularity and branching. This makes it suitable for studying the generalizability and robustness of 3d crack segmentation methods.</p> <p>______________________________________________________________________________________________</p> <p>The folder 'data' contains seven subfolders, each containing the data generated from a specific concrete type (NC, HPC, air pore concrete, polypropylene fiber-reinforced concrete, steel fiber-reinforced concrete (straight, crimped and hooked-end steel fibers)).</p> <p>Each subfolder again contains four subfolders according to the point process model that was used for generating the 3d Voronoi diagrams. The point processes and Voronoi diagrams are restricted to windows of size 400x150x400. </p> <p>- 'hc': Hard core point process with 60% volume density and intensity 0.000025 obtained from force-biased sphere packing.<br>- 'matclust': Matérn cluster process with parent intensity 0.0002/50, offspring intensity 50 and cluster radius 20.<br>- 'ppp': Poisson point process with intensity 0.0002.<br>- 'ppp-scaled': Poisson point process with intensity 0.0002 (but inside 200x150x200 window). The resulting Voronoi diagram is stretched in x- and z- direction by a factor of 2.</p> <p>Each of these contains five subfolders: one for the 3d input images, two for the corresponding labels (ground truths; one with and one without pores/fibers), one for the input and label previews (slice z=200 for each of the images) and a misc folder containing the concrete background without crack and, if applicable, the pore/fiber segmentation image.</p> <p>The data itself then contains 48 images:<br>1a-1d: crack with up to seven branches; fixed crack width (~1 voxel).<br>2a-2d: crack with up to four branches; fixed crack width (~1 voxel).<br>3a-3d: crack with up to one branch; fixed crack width (~1 voxel).<br>4a-4d: crack with no branches; fixed crack width (~1 voxel).<br>5a-5d: crack with no branches; fixed crack width (~3 voxels).<br>6a-6d: crack with no branches; fixed crack width (~5 voxels).<br>7a-7d: crack with no branches; fixed crack width (~7 voxels).<br>8a-8d: crack with up to seven branches; multiscale crack (bernoulli parameter 0.01);<br>9a-9d: crack with up to seven branches; multiscale crack (bernoulli parameter 0.02);<br>10a-10d: crack with up to seven branches; multiscale crack (bernoulli parameter 0.05);<br>11a-11d: crack with up to seven branches; multiscale crack (bernoulli parameter 0.1);<br>12a-12d: crack with up to seven branches; multiscale crack (bernoulli parameter 0.2);</p> <p>The names 'a'-'d' indicate level of added noise added to the image:<br>a: None.<br>b: Uniformly on [-sigma,sigma] <br>c: Uniformly on [-2*sigma,2*sigma] <br>d: Uniformly on [-4*sigma,4*sigma] <br>Negative values are mapped to 0. <br>For inputs of type int, noise values are rounded to the nearest integer.<br>(sigma = standard deviation of voxel greyvalues in image)</p> <p>Note that the grey values in the ground truths correspond to the local crack width. They can be thresholded to obtain binary masks.</p> <p>For more details, we refer to [1].</p>
LigPCDS: Labeled Dataset of X-ray Protein Ligand Images in 3D Point Cloud and Validated Deep Learning Models
<p>The difference electron density from X-ray protein crystallography was used to create the first dataset of labeled ligand images in 3D point clouds, named <strong>LigPCDS</strong>. The dataset contain 244,226 entries of free organic ligands containing 3D representations labeled with two major labeling approaches: SP-based and AtomSymbol-based.</p> <p> </p> <p>The data from free organic molecules (non-covalent ligands) was retrieved from the Research Collaboratory for Structural Bioinformatics Protein Data Bank (RCSB PDB) in december 2019 with resolutions ranging from 1.5 to 2.2 Å. The ligand images (blobs) were interpolated from their calculated difference electron density map in a 3D grid-like bounding box, around their atomic positions, and stored in point clouds. These ligand grid representations were further processed to retrive the final ligands representation in 3D point clouds using a mask of the shape of the ligand. A grid spacing of 0.5 Å gave the best results. The density value of the grid points was used as feature. The labeling approach used the structure of the ligands to propose vocabularies of chemical classes based on the chemical atoms themselves and their cyclic substructures. These structure annotations were applied pointwise to the ligand 3D representations using an atomic sphere model. Four proposed vocabularies were validated by successfully training good performance deep learning models for the semantic segmentation of a stratified dataset from LigPCDS, using 78902 entries.</p> <p>The four validated deep learning models are: (i) the LigandRegion, composed by generic atoms of any type; (ii) the AtomCycle, composed by generic atoms outside cycles and generic cycles; (iii) the AtomC347CA56, composed by generic atoms outside cycles, not aromatic cycles of size 3 to 7 and aromatic cycles of size 5 and 6; and (iv) the AtomSymbolGroups, composed by the atoms symbols with groupings. The mean accuracy of these models in their cross-validation was between 49.7% <span lang="EN-GB">[-19.4,20.</span><span lang="EN-GB">2]</span> and 77.4% <span lang="EN-GB">[-11.7,12.1]</span> in terms of Intersection over Union (mIoU) metric and between 62.4% <span lang="EN-GB">[-18.8,19.</span><span lang="EN-GB">7]</span> and 87.0% <span lang="EN-GB">[-8.4,8.8]</span> in F1-score (mF1), confidence interval between squared brackets. The models i, ii and iii and the used labeled representations in 3D point cloud are contained in the SP-based record; and model iv and its used labeled representations are contained in the AtomSymbol-based record.</p> <p>The dataset and validated models may be used to tackle problems regarding known and unknown ligand building to drug discovery and fragment screening pipelines. </p> <p>The code used to create and validated the LigPCDS is available at the following repository: https://github.com/danielatrivella/np3_ligand</p> <p>This repository also contains the NP³ Blob Label application for ligand building using the validated deep learning models from LigPCDS.</p>
Images of 3D digitisation of articles of traditional attire
<p>These files are images digitisations of traditional, handcrafted dresses, shoes, handbags, and fabrics. These items are manufactured during the 21st century following traditional manufacturing methods and utilising designs and motifs from Greek antiquities. The 3D models were photogrammetrically captured. These images correspond to the 3D models in <a href="http://doi.org/10.5281/zenodo.8098709">https://doi.org/10.5281/zenodo.8098709</a></p>
3D mesh model and raw images of a drifting iceberg in Dickson Fjord (NE Greenland) on 21 August 2018 at 17:09 UTC
<p>This dataset consists of low-altitude aerial imagery that was acquired by a DJI Phantom 3 Standard unoccupied aerial vehicle (UAV) in Dickson Fjord in northeast Greenland on 21 August 2018. The UAV survey commenced at 17:09 UTC. These images were processed in Agisoft PhotoScan Pro (v1.4; Linux Ubuntu). During the image alignment step in PhotoScan, the ‘High’ accuracy setting and key point and tie point limits of 60000 and 0 were used. Generic and reference preselection were disabled. Gradual selection was used to remove tie points that exceeded thresholds for the projection accuracy, reconstruction uncertainty, and reprojection error and the lens parameters were computed. Reference data from images DJI_417-419 were used to scale the sparse point cloud. The dense point cloud was then computed using the ‘High’ setting, followed by the textured mesh. The mesh model was exported in .obj and .pdf formats. </p> <p>A complete file list is provided in the README file that accompanies this dataset.</p> <p>This dataset is discussed in:</p> <p>Carlson et al. Quantifying iceberg deterioration using UAV imagery and Structure from Motion photogrammetry software. Submitted to <em>Remote Sensing.</em></p>
3D mesh model and raw images of a drifting iceberg in Dickson Fjord (NE Greenland) on 20 August 2018 at 12:41 UTC
<p>This dataset consists of low-altitude aerial imagery that was acquired by a DJI Phantom 3 Standard unoccupied aerial vehicle (UAV) in Dickson Fjord in northeast Greenland on 20 August 2018. The UAV survey commenced at 12:41 UTC. These images were processed in Agisoft PhotoScan Pro (v1.4; Linux Ubuntu). During the image alignment step in PhotoScan, the ‘High’ accuracy setting and key point and tie point limits of 60000 and 0 were used. Generic and reference preselection were disabled. Gradual selection was used to remove tie points that exceeded thresholds for the projection accuracy, reconstruction uncertainty, and reprojection error and the lens parameters were computed. Reference data from images DJI_493-497 were used to scale the sparse point cloud. The dense point cloud was then computed using the ‘High’ setting, followed by the textured mesh. The mesh model was exported in .obj and .pdf formats. </p> <p>A complete file list is provided in the README file that accompanies this dataset.</p> <p>This dataset is discussed in:</p> <p>Carlson et al. Quantifying iceberg deterioration using UAV imagery and Structure from Motion photogrammetry software. Submitted to <em>Remote Sensing.</em></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>
[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>
Supplemental Data from the article "The SmARTR pipeline: a modular workflow for the cinematic rendering of 3D scientific imaging data"
<h1><strong>Please, refer to <a href="https://github.com/MeVisLab/SmARTR-Networks">this GitHub repository</a> for additional info, updates, issue reports, and discussion<br></strong></h1> <p><strong>A collection of configuration files (SmARTR networks) published in "<a href="https://doi.org/10.1016/j.isci.2024.111475">The SmARTR Pipeline: a modular workflow for the cinematic rendering of 3D scientific imaging data</a>", enabling the creation of cinematic (photorealistic) renderings of 3D data in the FREE software <a href="https://www.mevislab.de/download">MeVisLab</a><br></strong></p> <ul> <li>Each folder in the archive contains one or more SmARTR network files, the scan and mask files required for the practical examples detailed in the <a href="https://www.cell.com/cms/10.1016/j.isci.2024.111475/attachment/8d79036b-acb6-4cda-a5ff-f56317691ebc/mmc1.pdf">Supplemental Data</a> of the article, and an additional folder with LUT presets.</li> </ul>
hiPSC 3D immunofluorescence images, test data set 2x2, 10Z
<p>Example dataset of human induced pluripotent stem cells, imaged at 40x magnification with a Yokogawa CV7000. This is a small subset of a larger experiment intended as a test dataset for Fractal: https://github.com/fractal-analytics-platform/fractal</p> <p>3 Channels were imaged:</p> <p>- C01: DAPI, nuclear stain</p> <p>- C02: nanog, antibody staining with Bio-Techne AG, AF1997-SP, Lot KKJ0617121 for the stemness marker nanog</p> <p>- C03: Lamin B1, antibody staining with Abcam, ab16048, Lot GR3244890-2 for the nuclear envelope marker Lamin B1</p> <p> </p> <p>This dataset contains 10 Z levels for 4 field of views for those 3 channels, as well as (manually adjusted) metadata files from the Yokogawa CV7000.</p> <p> </p> <p>The data was acquired in the Pelkmans lab in August 2020. The images have been converted from TIFF into PNG (lossless). </p>
Data supporting 3D Super-resolution Optical Fluctuation Imaging with Temporal Focusing with two-photon excitation
<p>Data to support the publication combining temporal focusing two photon excitation with super-resolution optical fluctuation imaging.</p> <div>This research was funded by National Centre of Science, grant number: 2022/47/B/ST7/03465. For the purpose of Open Access, the author has applied a</div> <div>CC-BY public copyright licence to any author Accepted Manuscript (AAM) version arising from this submission</div>
Correlative microscopy of mice cerebellar Purkinje cells from 20x confocal tissue imaging to super-resolution 93x 3D STED of dendritic spines
<p>This Dataset concerns the paper entitled "<em>From tissues to segmentation: a modular framework for multi-scale neuron isolation</em>" by Cauzzo et al. <strong>Nature Comm (2024).</strong></p> <p>S.Cauzzo<sup>$</sup>, E. Bruno, D. Boulet, P. Nazac, M. Basile, A. L. Callara, F. Tozzi, A. Ahluwalia, C. Magliaro, L. Danglot<sup>$</sup><sup>*</sup>, N. Vanello<sup>$</sup><sup>*</sup> *shared senior authorship: Lydia.danglot@inserm.fr ; nicola.vanello@unipi.it</p> <p><sup>$</sup> corresponding authors : cauzzo.simone@gmail.com ; Lydia.danglot@inserm.fr ; nicola.vanello@unipi.it</p> <p> </p>
3D IQ Test Task (3D-IQTT) - A Dataset for Quantitative Evaluation of 3D Reconstruction from 2D Images
<p>3D reconstruction is mostly evaluated qualitatively. With this dataset, we are introducing a new difficult quantitative task, the 3D IQ test task (3D-IQTT).</p> <p>It is designed to be similar to mental rotation questions found in some IQ tests. Each element in the dataset consists of 4 images: reference object and answers 1-3. One of the answers is the reference object but randomly rotated. For every question, dataset users have to use their model to pick the rotated model out of the 3 possible answers.</p> <p>The dataset encourages semi-supervised or unsupervised 3D reconstruction because it contains a large corpus of unlabeled data and only a small set of labeled data where the correct answer is known.</p> <p>All the images are of blocky 3D shapes floating in space in front of a black background.</p> <p>Demo scripts for loading/processing the dataset can be found at <a href="https://github.com/fgolemo/3D-IQTT">https://github.com/fgolemo/3D-IQTT</a></p> <p>The dataset consists of:</p> <ul> <li> <pre>3diqtt-v2-train.h5 (XZ-compressed)</pre> <strong>(Training Dataset)</strong> <ul> <li> <pre>/labeled</pre> <ul> <li> <pre>/questions</pre> format: [10,000 x 4 x 128 x 128 x 3], corresponding to (10k items) x (reference + 3 answers) x (img width) x (img height) x (RGB), np.float32 in range [0,1]</li> <li> <pre>/answers</pre> format: [10,000], corresponding to (10k answers), np.uint8, one of the following three items: [0,1,2]</li> </ul> </li> <li> <pre>/unlabeled</pre> <ul> <li> <pre>/questions</pre> format: [100,000 x 4 x 128 x 128 x 3], corresponding to (100k items) x (reference + 3 answers) x (img width) x (img height) x (RGB), np.float32 in range [0,1]</li> </ul> </li> </ul> </li> <li> <pre>3diqtt-v2-test.h5</pre> <strong>(Test Dataset)</strong> <ul> <li> <pre>/questions</pre> format: [10,000 x 4 x 128 x 128 x 3], corresponding to (10k items) x (reference + 3 answers) x (img width) x (img height) x (RGB), np.float32 in range [0,1].<br> <strong>Important! This is what you have to evaluate yourself on. We have the correct answers but they are not public.</strong></li> </ul> </li> <li> <pre>3diqtt-v2-val.h5</pre> <strong>(Validation Dataset)</strong> <ul> <li> <pre>/questions</pre> format: [10,000 x 4 x 128 x 128 x 3], corresponding to (10k items) x (reference + 3 answers) x (img width) x (img height) x (RGB), np.float32 in range [0,1]</li> <li> <pre>/answers</pre> format [10,000], corresponding to (10k answers), np.uint8, one of the following three items: [0,1,2]</li> </ul> </li> </ul> <p> </p> <p><strong>Important:</strong> Before use, the main training dataset (3diqtt-v2-train.h5.xz) needs to be decompressed. This can take up to 24h depending on your hardware. We apologize for any inconvenience caused by this. The uncompressed file has a size of ~74GB. The reason for this compression was a restriction on the size of individual files. The command for decompression is "<strong>unxz</strong><strong> 3diqtt-v2-train.h5.xz</strong>" on Unix machines.</p> <p><strong>If you use this dataset, please cite it.</strong></p>
OME-Zarr hiPSC 3D immunofluorescence images, tiny test set
<p><em>This dataset is intended to be used for automated testing of OME-Zarr processing.</em></p> <p> </p> <p>Example dataset of human induced pluripotent stem cells, imaged at 40x magnification with a Yokogawa CV7000. This is a tiny subset of a larger experiment intended as a test dataset for the <a href="https://fractal-analytics-platform.github.io/">Fractal platform</a> and others experimenting with OME-Zarrs.</p> <p>1 Channel is included:</p> <ul> <li>C01: DAPI, nuclear stain</li> </ul> <p>It is generated from this raw data: <a href="../records/8287221">https://zenodo.org/records/8287221</a></p> <p>This dataset contains 2 Z levels for 2 field of views for this 1 channel, as well as (manually adjusted) metadata files from the Yokogawa CV7000. The data was acquired in the Pelkmans lab in August 2020.</p> <p>The images have been processed using Fractal, the workflow is attached as a json file. It ran with fractal-server==2.3.6, fractal-client==2.0.1, fractal-web==1.4.0 and fractal-tasks-core==1.2.1.</p> <p>Two versions of the OME-Zarr are added here: A 3D version with both Z planes. And a 2D version (MIP of the Z-planes) which also contains label images from cellpose segmentation, measurements and output ROI tables.</p>
Left Atrium 3D Models Extracted from Static CT Images (AF and SR Models)
<p>A cohort of 45 x 2 patient-specific 3D-models from static computed tomography (CT) images provided by the University Medical Center Hamburg-Eppendorf in Germany. The study complies with EU Regulation 2016/679 and has recieved ethical approval from the regional committee. </p> <p>The cohort has been used in two research papers:</p> <ol> <li>Kjeldsberg et al. (2024), Estimation of inlet flow rate in simulations of left atrial flows: A proposed optimized and reference-based algorithm with application to sinus rhythm and atrial fibrillation, <em>J Biomech</em> [Accepted]</li> <li>Kjeldsberg et al. (2024), Beyond CHA2DS2–VASc: hemodynamic and morphologic discriminants for thrombus formation and stroke in atrial fibrillation patients,<em> Ann. Biomed. Eng</em>. [Submitted]</li> </ol> <p><strong>models_af.zip </strong>contains 45 3D surface models (.vtp) extracted during onset of atrial diastole where <strong>A</strong>trial <strong>F</strong>ibrillation movement was applied using a motion algorithm [*]</p> <p><strong>models_sr.zip </strong>contains 45 3D surface models (.vtp) extracted during onset of atrial diastole where <strong>S</strong>inus <strong>R</strong>hytmn movement was applied using a motion algorithm [*]</p> <p> </p> <p>[*] For details on the motion algorithm, see <a href="Harrison, J., 2024. Medical Imaging, Shapes and Statistics for Stroke Prediction in Atrial Fibrillation (Doctoral dissertation, Inria & Université Cote d'Azur, CNRS, I3S, Sophia Antipolis, France).">Harrison – Medical Imaging, Shapes and Statistics for Stroke Prediction in Atrial Fibrillation </a></p>
Set of images published in publication "Cleaning strategies for 3D-printed porous scaffolds used for bone regeneration fabricated via ceramic vat photopolymerization"
<p>Figures of publication "Cleaning strategies for 3D-printed porous scaffolds used for bone regeneration fabricated via ceramic vat photopolymerization".</p> <p><a title="Persistent link using digital object identifier" href="https://doi.org/10.1016/j.ceramint.2024.10.160" target="_blank" rel="noreferrer noopener"><span><span>https://doi.org/10.1016/j.ceramint.2024.10.160</span></span></a></p>
LungVis1.0: Active learning AI-powered 3D imaging ecosystem for spatial profiling of lung geometry and pulmonary nanoparticle delivery
<p>The imaging dataset was obtained by light sheet fluorescence microscopy on tissue cleared murine lungs. It includes whole lung autofluorence image, particle fluorescence image, and artifical intelligence nnU-Net generated lung airway segments. The dataset provides 78 healthy murine lung strucutre and airway geometry for C57BL/6 mice and offers comprehensive delivery features including qualitative and quantitative analysis on the temporal and spatial inter- and intra-acinar deposition patterns and NP regional dosimetry for four commonly-used routes of pulmonary delivery,namely intranasal liquid aspiration, intratracheal liquid instillation, ventilator-assisted and nose-only aerosol inhalation.</p> <p>Raw LSFM imaging data collection was carried out between 2017-2021, the AI code and generated airway segmention were performed in 2021-2022, the whole datasets were then compiled in 2023. </p> <p>Please ensure to cite our paper for any reuse or reanalysis. Yang, L., Liu, Q., Kumar, P. <em>et al.</em> LungVis 1.0: an automatic AI-powered 3D imaging ecosystem unveils spatial profiling of nanoparticle delivery and acinar migration of lung macrophages. <em>Nat Commun</em> <strong>15</strong>, 10138 (2024). https://doi.org/10.1038/s41467-024-54267-1</p> <p>For any inquiries, please feel free to contact us at lin.yang@helmholtz-munich.de </p>
Unmanned Aerial Vehicle Image Dataset of the Built Environment for 3D reconstruction (UAVID3D)
<p>Unmanned Aerial Vehicles (UAV) provide increased access to unique types of urban imagery traditionally not available. Advanced machine learning and computer vision techniques when applied to UAV RGB image data can be used for automated extraction of building asset information and if applied to UAV thermal imagery data can detect potential thermal anomalies. However, these UAV datasets are not easily available to researchers, thereby creating a barrier to accelerating research in this area. </p> <p>To assist researchers with added data to develop machine learning algorithms, we present UAVID3D (Unmanned Aerial Vehicle (UAV) Image Dataset of the Built Environment for 3D reconstruction). The raw images for our dataset were recorded with a Zenmuse XT2 visual (RGB) and a FLIR Tau 2 (thermal, https://flir.netx.net/file/asset/15598/original/) camera on a DJI Mavic 2 pro drone (https://www.dji.com/matrice-200-series). The thermal camera is factory calibrated. All data is organized and structured to comply with FAIR principles, i.e. being findable, accessible, interoperable, and reusable. It is publicly available and can be downloaded from the Zenodo data repository. </p> <p>RGB images were recorded during UAV fly-overs of two different commercial buildings in Northern California. In addition, thermographic images were recorded during 2 subsequent UAV fly-overs of the same two buildings. UAV flights were recorded at flight heights between 60–80 m above ground with a flight speed of 1 m s and contain GPS information. All images were recorded during drone flights on May 10, 2021 between 8:45 am and 10:30 am and on May 19, 2021 between 2:15 pm and 4:30 pm. Outdoor air temperatures on these two days during the flights were between 78 and 83 degree fahrenheit and between 58 and 65 degree fahrenheit respectively. </p> <p>For the RGB flights, UAV path was planned and captured using an orbital flight plan in PIX4D capture at normal flight speed and overlap angle of 10 degree. Thermal images were captured by manual flights approximately 5 m away from each building facade. Due to the high overlap of images, similarities from feature points identified in each image can be extracted to conduct photogrammetry. Photogrammetry allows estimation of the three-dimensional coordinates of points on an object in a generated 3D space involving measurements made on images taken with a high overlap rate. Photogrammetry can be used to create a 3D point cloud model of the recorded region. UAVID3D dataset is a series of compressed archive files totaling 21GB. Useful pipelines to process these images can be found at these two repositories <a href="https://github.com/LBNL-ETA/a3dbr">https://github.com/LBNL-ETA/a3dbr</a>, and <a href="https://github.com/LBNL-ETA/AutoBFE">https://github.com/LBNL-ETA/AutoBFE</a></p> <p>This work was supported by the Assistant Secretary for Energy Efficiency and Renewable Energy, Building Technologies Program, of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231. </p> <p> </p> <p> </p>
Images and 3D digitisations of articles of traditional attire
<p>These files are 3D digitisations and images of those of traditional, handcrafted dresses, shoes, handbags, and fabrics. These items are manufactured during the 21st century following traditional manufacturing methods and utilising designs and motifs from Greek antiquities. The 3D models were photogrammetrically captured.</p>
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.