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.
3,036
datasets available to search
ShareScore release 0.9.0
Dataset results
3,036 results for “ct”
Simulated industrial CT dataset for deep learning with dual-energy tomograms and ground truth material maps for copper and iron
<p>We use this dataset for training and evaluation of a deep learning model to discriminate multi-material systems with X-ray CT.</p> <p>The dataset consists of:</p> <ul> <li>inputs: dual-energy tomograms as binary files without a header (tensor <strong>shape for numpy: 2x128x128 @float32</strong>) <ul> <li>simulated spectra are 250kVp and 450kVp both prefiltered using 2mmCuSn</li> </ul> </li> <li>outputs: the material maps a.k.a. ground truths for the training (same shape as inputs) <ul> <li>sampled with a delaunay algorithm and randomly filled with iron and copper fractions</li> </ul> </li> </ul> <p>The <strong>dataset is normalized to [0, 1]</strong>, so you have to multiply by the mass densities of copper and iron to obtain effective fractions in g/cm^3.</p>
Supplementary material S1. Donacia (Protodonacia) bienkowskii Bukejs and Alekseev subgen. et sp. nov., holotype, Nr. 3300.142 [RSKM], X-ray micro-CT volume rendering of the habitus without legs and antennae.
<p>Supplementary material S1 in paper: Bukejs A., Alekseev V.I. & McKellard R.C. First described reed beetle (Chrysomelidae: Donaciinae) from amber inclusion: member of the littoral community in the Eocene Baltic amber forest. Historical Biology.</p> <p> </p>
X-ray CT of subsea pipe
<p>This record contains 2D X-ray tomography data of a subsea pipe with layers consisting of steel, concrete, polyurethane (PU) foam, and polyethylane (PE) rubber. The data was acquired at FORCE Technologies test facilities. Files included:</p> <p>- Sinogram with absorption data as .dat file.</p> <p>- Meta data needed for reconstruction in .txt file.</p> <p>- Data acquisition geometry illustration in .png file. </p> <p> </p> <p>Contact: jakj@dtu.dk</p>
CT Simulations of MITA Low Contrast Detectability Phantom for Model Observer Assessments
<p>Dataset of CT Simulations of MITA Low Contrast Detectability Phantom for Model Observer Assessments. </p>
Lung nodule CT false positive reduction
<p>This data set is part of the public development data for the <a href="http://auc23.grand-challenge.org/">2023 Automated Universal Classification Challenge</a> (AUC23). The data set concerns the classification of lung nodules on screening thoracic computed tomography (CT) scans and was derived from the <a href="https://luna16.grand-challenge.org/Data/">2016 Lung Nodule Analysis (LUNA) challenge</a>. The data set was previously introduced and described by <a href="https://www.sciencedirect.com/science/article/pii/S1361841517301020?via%3Dihub">Setio et al. (2017)</a> and no images or patient information were added. Only the "false positive reduction" track was considered, where a provided set of nodule candidates should be classified. Data was restructured in compliance with the <a href="https://auc23.grand-challenge.org/">AUC23</a> challenge format. The data set was collected from the largest publicly available reference database for lung nodules: <a href="https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=1966254">The Lung Image Database Consortium image collection</a>.</p> <p>Images are 3D tensors:</p> <ul> <li>0: 3D axial screening CT scan (cropped to candidate nodule's region of interest)</li> </ul> <p>Classification labels:</p> <ul> <li>0: Is a nodule</li> <li>1: Is not a nodule</li> </ul> <p>Folder structure:</p> <p>imagesTr (root folder with all patients and studies)<br> ├── LUNA16_0000_0000.mha (axial CT imaging for nodule 0000)<br> ├── LUNA16_0000_0002.mha (axial CT imaging for nodule 0002)<br> ├── ...<br> </p> <p>Please cite the following article if you are using the <a href="https://luna16.grand-challenge.org/Data/">2016 Lung Nodule Analysis (LUNA) challenge</a> false positive reduction track data set:</p> <pre><code>Setio AAA, Traverso A, de Bel T, Berens MSN, Bogaard CVD, Cerello P, Chen H, Dou Q, Fantacci ME, Geurts B, Gugten RV, Heng PA, Jansen B, de Kaste MMJ, Kotov V, Lin JY, Manders JTMC, Sóñora-Mengana A, García-Naranjo JC, Papavasileiou E, Prokop M, Saletta M, Schaefer-Prokop CM, Scholten ET, Scholten L, Snoeren MM, Torres EL, Vandemeulebroucke J, Walasek N, Zuidhof GCA, Ginneken BV, Jacobs C. Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge. Med Image Anal. 2017 Dec;42:1-13. doi: 10.1016/j.media.2017.06.015. Epub 2017 Jul 13. PMID: 28732268.</code></pre> <p> </p>
Supplementary material S3. Henoticus groehni sp. nov., holotype, No. 5087 [GPIH], X-ray micro-CT volume rendering of the left antenna.
<p>Supplementary material S3 in paper: Bukejs A., Lyubarsky G.Yu., Alekseev V.I. The oldest fossil species of the genus Henoticus Thomson (Coleoptera: Cryptophagidae) from Eocene Baltic amber. Historical Biology.</p> <p> </p>
Measurement Data for CT of Battery Pouch Cell with Defects
<p>These are the raw radiography images used to calculate the CT volume of a battery pouch cell with defects.</p> <p> </p> <p>Measured on a diondo d2 CT (using XWT-190 CT, Varex 4343DX-I) at TU Dresden.</p> <p>Tube: 150 KV, 100 µA</p> <p>Geometry: FOD 160 mm, FDD 1000 mm</p> <p>Detector: 3000 x 3000 px², 3000 Frames, 5x Framebinning, 3000 ms per Frame</p> <p>Data: 16bit unsigned integer, little endian</p> <p> </p> <p>The sample was prepared by Johannes Münch. For further details see the following paper:</p> <p><a href="https://doi.org/10.1002/ente.202300323">https://doi.org/10.1002/ente.202300323</a></p>
TCIA/TGCA-LIHC portal venous phase CT-scans for cirrhosis classification
<p>These are the scans provided by The Cancer Genome Atlas Liver Hepatocellular Carcinoma (TCGA-LIHC) data collection, published by The Cancer Imaging Archive <a href="https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=6885436">here</a> and used in our <a href="https://arxiv.org/abs/2307.04617">MICCAI 2023 paper</a>. You can find the GitHub of the paper <a href="https://arxiv.org/abs/2307.04617">here</a>.</p> <p>All the data are submitted to <a href="https://wiki.cancerimagingarchive.net/display/Public/Data+Usage+Policies+and+Restrictions">TCIA data usage policy</a> and must be strictly respected by future users.</p> <p>The selected scans are in portal venous phase, which is the phase that is clinically used to identify cirrhosis. In this list, you will find all the patients available in the TCGA-LIHC database, regardless of the availability of the annotations or the duplicated patients at different dates. In the dataframe provided in the Git repo, you will find the dataframe with one scan per patient (only at the first date), and with the Ishak score for each patient provided in the TCIA/TGCA database, which are the exact ones that we used in the paper. The names of the scans in the dataframe match exactly the ones below, to ease reproducibility. </p> <p>The scans are already pre-processed and are the exact ones that we use in evaluation phase in the published paper.</p>
Example input dataset for thoracic CT-based body composition assessment
<p>The uploaded archive file (tar.gz) contains an example dataset to demonstrate the input data arrangement for the thoracic CT-based body composition assessment pipeline described at <a href="https://github.com/MASILab/S-EFOV">https://github.com/MASILab/S-EFOV</a>. The dataset consists of four chest CT scans selected from the <a href="https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=70226443">TCIA COVID-19-AR dataset</a>. The CT scans were converted from DICOM format to NIfTI format using <a href="https://github.com/rordenlab/dcm2niix">https://github.com/rordenlab/dcm2niix</a>.</p> <p>The original TCIA dataset were published under <a href="https://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International License</a> and the <a href="https://wiki.cancerimagingarchive.net/x/c4hF">TCIA Data Usage Policy</a>. The usage of this derived subset should follow the same guidelines.</p>
Lung CT Deformable Image Registration Validation Dataset
<p>This dataset contains 30 different cases of CT image pairs, with a high number of vessel bifurcation landmark pairs identified in each case. These landmarks can be used for deformable image registration (DIR) algorithm validation and quality assurance. Images are obtained from several publicly available image repositories as well as clinical scans from Barnes Jewish Hospital.</p> <p> </p> <p>Guidelines for loading and visualizing data can be found on our Github at </p> <p>https://github.com/deshanyang/Lung-DIR-QA</p> <p> </p> <p>If you use our dataset, please cite the paper at </p> <p>https://doi.org/10.1002/mp.17026</p>
Evaluation of a Carbon Nanotube Enabled Solid-State Head CT
ClinicalTrials.gov study NCT04495634. IPD Sharing: YES. Countries: 1. Publications: 0.
SYNTAX III REVOLUTION Trial: A Randomized Study Investigating the Use of CT Scan and Angiography of the Heart to Help the Doctors Decide Which Method is the Best to Improve Blood Supply to the Heart i
ClinicalTrials.gov study NCT02813473. IPD Sharing: YES. Countries: 5. Publications: 2.
Morphology of Pulleniatina (planktonic foraminifera): Micro-CT internal volumes
Open the record for dataset details and reuse information.
Camera-based badger density estimation using the REM, CT-DS, and SMR
Open the record for dataset details and reuse information.
Use of Deep Learning for structural analysis of CT-images of soil samples
Open the record for dataset details and reuse information.
Micro-CT data and associated MATLAB scripts from the skeleton of the sea urchin Cidaris rugosa at four different resolutions
Open the record for dataset details and reuse information.
A database for benchmarking organ dose estimates and uncertainties in CT
<p>This database includes patient images and associated verified Monte Carlo based estimates of organ doses that may be used for benchmarking different organ dose estimation techniques against a reference standard.</p>
Fig. 3 in A new species of Copionodon representing a relictual occurrence of the Copionodontinae (Siluriformes: Trichomycteridae), with a CT-scan imaging survey of key subfamilial features
Fig. 3. Copionodon exotatos, holotype, MZUSP 120631, 45.0 mm SL. Lateral view of head.
Medical Concept Embeddings for SNOMED-CT (Jan 2019 version)
<p>This dataset contains the SNOMED-CT medical concept embeddings trained using the following text and graph embedding methods.</p> <ul> <li>Averaged Word Embedding (300)</li> <li>ELMo (1024)</li> <li>Universal Sentence Encoder (512)</li> <li>BERT (768)</li> <li>Deepwalk (128)</li> <li>Node2Vec (128)</li> <li>HARP (128)</li> <li>LINE (128)</li> </ul> <p>The tar file contains eight JSON files corresponding to the aforementioned embedding techniques. The number (in parenthesis) besides each embedding method represents the dimensionality of the embedding. Each JSON file contains a python dictionary of the form</p> <p>SNOMED concept ID (String): Embedding (List).</p> <p>If you find this resource useful in your research, please consider citing our paper:</p> <p>"Pattisapu, N., Patil, S., Palshikar, G. and Varma, V., Medical Concept Normalization by Encoding Target Knowledge, Proceedings of Machine Learning Research 116:246–259, 2020 Machine Learning for Health (ML4H) at NeurIPS 2019"</p> <p>Warning: The dataset size is large (~12 GB). Please ensure that you have sufficient network bandwidth and disk space before requesting a download.</p>
LoDoPaB-CT Challenge Set
<p>Observation data for the <a href="https://lodopab.grand-challenge.org/">LoDoPaB-CT challenge</a>, which asks to reconstruct CT images of the human lung from (simulated) low photon count measurements.</p> <p>The setting is identical to the one of the <a href="https://zenodo.org/record/3384092">LoDoPaB-CT dataset</a> (documented in this <a href="https://www.nature.com/articles/s41597-021-00893-z">Data Descriptor article</a>), which is supposed to be employed for training learned methods. This challenge set contains observations for a separate set of patients.</p> <p>Python utilities for accessing this challenge set and creating the submission file are available at <a href="https://github.com/jleuschn/lodopab_challenge">github.com/jleuschn/lodopab_challenge</a>. The LoDoPaB-CT dataset for training can be accessed using the <a href="https://zenodo.org/record/3970517">DIVal</a> python library (<a href="https://github.com/jleuschn/dival">github.com/jleuschn/dival</a>).</p> <p>Like for the LoDoPaB-CT dataset, reconstructions from the <a href="http://doi.org/10.7937/K9/TCIA.2015.LO9QL9SX">LIDC/IDRI dataset</a> are used as a basis for this challenge set.</p> <p> </p> <p>The ZIP file contains multiple <a href="https://www.hdfgroup.org/HDF5/">HDF5</a> files. Each HDF5 file contains one HDF5 dataset named <code>"data"</code>, that provides a number of samples (128 except for the last file). For example, the <code>n</code>-th observation sample is stored in the file <code>"observation_challenge_%03d.hdf5"</code> where <code>"%03d"</code> is <code>floor(n / 128)</code>, at row <code>(n mod 128)</code> of <code>"data"</code>.</p> <p>For this challenge set no patient IDs are provided (in contrast to the fully public parts of the LoDoPaB-CT dataset), since the reconstruction algorithm should not rely on this information.</p> <p><em>Acknowledgements</em></p> <p>Johannes Leuschner, Maximilian Schmidt and Daniel Otero Baguer acknowledge the support by the Deutsche<br> Forschungsgemeinschaft (DFG) within the framework of GRK 2224/1 “π3: Parameter Identification – Analysis,<br> Algorithms, Applications”. We thank Simon Arridge, Ozan Öktem, Carola-Bibiane Schönlieb and Christian<br> Etmann for the fruitful discussion about the procedure, and Felix Lucka and Jonas Adler for their ideas and<br> helpful feedback on the simulation setup. The authors acknowledge the National Cancer Institute and the Foundation for the National Institutes of Health, and their critical role in the creation of the free publicly available LIDC/IDRI Database used in this study.</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.