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.
314
datasets available to search
ShareScore release 0.9.0
Dataset results
314 results for “Ultrasound imaging”
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 of B-mode fatty liver ultrasound images
<p>The dataset used and described in: M. Byra, G. Styczynski, C. Szmigielski, P. Kalinowski. Ł. Michałowski4. R. Paluszkiewicz. B. Ziarkiewicz-Wróblewska, K. Zieniewicz. P. Sobieraj, A. Nowicki. Transfer learning with deep convolutional neural network for liver steatosis assessment in ultrasound images. International Journal of Computer Assisted Radiology and Surgery, 2018. DOI: 10.1007/s11548-018-1843-2. </p> <p>Please refer to the above work if you use the dataset in your research. </p> <p>Contact:<br> Michal Byra<br> Department of Ultrasound<br> Institute of Fundamental Technological Research<br> Polish Academy of Sciences, Warsaw, Poland<br> mbyra@ippt.pan.pl<br> byra.michal@gmail.com</p>
Maternal fetal ultrasound planes from low-resource imaging settings in five African countries
<p>This resource is a dataset of routinely acquired maternal-fetal screening ultrasound images collected in five centers of five countries in Africa (Malawi, Egypt, Uganda, Ghana and Algeria) that is associated to the journal article Sendra-Bacells et al. "Generalisability of fetal ultrasound deep learning models to low-resource imaging settings in five African countries", <em>Scientific Reports</em>. The images correspond to the four most common fetal planes: abdomen, brain, femur and thorax. A CSV file is provided where image filenames are associated to plane types and patient number as well as the partitioning in training and testing splits as used in the associated publication.</p>
Annotated MRI and ultrasound volume images of the prostate
<p><strong>Introduction</strong></p> <p>The <em>Surgical Planning Laboratory (SPL) </em>and the <em>National Center for Image Guided Therapy (NCIGT) </em>are making this dataset available as a resource to aid in the development of algorithms and tools for deformable registration, segmentation and analysis of prostate magnetic resonance imaging (MRI) and ultrasound (US) images. </p> <p><strong>Description</strong></p> <p>This dataset contains anonymized images of the human prostate (N=3 patients) collected during two sessions for each patient:</p> <ol> <li>MRI examination of the prostate for the purposes of disease staging.</li> <li>US examination of the prostate for the purposes of volumetric examination in preparation to the brachytherapy implant.</li> </ol> <p>These are three-dimensional (multi-slice) scalar images.</p> <p>Image files are stored using NRRD file format (files with .nrrd extension), see details at http://teem.sourceforge.net/nrrd/format.html. Each image file includes a code for the case number (internal numbering at the research site) and the modality (US or MR).</p> <p>Image annotations were prepared by Dr. Fedorov (no professional training in radiology) and Dr. Tuncali (10+ in prostate imaging interpretation). Annotations include</p> <ol> <li>Manual contouring (segmentation) of the whole prostate gland, performed in 3D Slicer software. These segmentation images are coded in the same fashion as the image files, and saved in NRRD format, with "-label" suffix.</li> <li>Manually placed points (fiducials) corresponding to the location of urethra entry into the prostate at base (coded as UB), verumontanum (VM), urethra entry into the prostate at apex (UA), as well as centroids of cysts and calcifications. UB, UA and VM locations are annotated both in MR and US for all cases, while cysts and calcifications are annotated when applicable. Fiducial points are stored in comma-separated CSV-style format adopted by 3D Slicer software (.fcsv file extension). There is one row per point in these files, encoding the location of the point in RAS coordinate space relative to the image data, and the name of the point.</li> </ol> <p><strong>Viewing the collection</strong></p> <p>We tested visualization of images, segmentations and fiducials in 3D Slicer software, and thus recommend 3D Slicer as the platform for visualization. 3D Slicer is a free open source platform (see http://slicer.org), with the pre-compiled binaries available for all major operating systems. You can download 3D Slicer at http://download.slicer.org.</p> <p><strong>Acknowledgments </strong></p> <p>Preparation of this data collection was made possible thanks to the funding from the National Institutes of Health (NIH) through grants R01 CA111288 and P41 RR019703.</p> <p>If you use this dataset in a publication, please cite the following manuscript. You can also learn more about this dataset from the publication below.</p> <p>Fedorov, A., Khallaghi, S., Antonio Sánchez, C., Lasso, A., Fels, S., Tuncali, K., Sugar, E. N., Kapur, T., Zhang, C., Wells, W., Nguyen, P. L., Abolmaesumi, P. & Tempany, C. Open-source image registration for MRI–TRUS fusion-guided prostate interventions. <em>Int J CARS</em> <strong>10,</strong> 925–934 (2015). https://pubmed.ncbi.nlm.nih.gov/25847666/</p> <p><strong>Contact</strong></p> <p>Andrey Fedorov, fedorov@bwh.harvard.edu</p>
Off-Grid Ultrasound Imaging by Stochastic Optimization
<p>These are the data files used in the paper "Off-Grid Ultrasound Imaging by Stochastic Optimization".</p> <p>The code for the paper can be found in the corresponding <a title="github repository" href="https://github.com/vincentvdschaft/off-grid-ultrasound" target="_blank" rel="noopener">github repository</a>.</p> <table> <tbody> <tr> <td><strong>File name</strong></td> <td><strong>Description</strong></td> <td><strong>Transmit scheme</strong></td> <td><strong>Transducer</strong></td> </tr> <tr> <td>L11-5v_carotid1.hdf5</td> <td>Crossectional view of a carotid artery.</td> <td>128 synthetic aperture transmissions and 21 plane wave transmissions.</td> <td>Verasonics L11-5V</td> </tr> <tr> <td>L11-5v_carotid2.hdf5</td> <td>Crossectional view of a carotid artery.</td> <td>128 synthetic aperture transmissions and 21 plane wave transmissions.</td> <td>Verasonics L11-5V</td> </tr> <tr> <td>L11-5v_carotid3.hdf5</td> <td>Crossectional view of a carotid artery.</td> <td>128 synthetic aperture transmissions.</td> <td>Philips S5-1</td> </tr> <tr> <td>S5-1_cirs.hdf5</td> <td>Acquisition of the CIRS-040 phantom in the low attenuation zone.</td> <td>80 synthetic aperture transmissions and 21 plane wave transmissions.</td> <td>Philips S5-1</td> </tr> <tr> <td>cirs_simulated.hdf5</td> <td>Simulated data similar to CIRS-040 phantom.</td> <td>3 synthetic aperture transmissions.</td> <td>Similar to Philips S5-1</td> </tr> </tbody> </table> <p>A description and unit for the datasets in these files is provided in the dataset attributes.</p>
Validation experiments of Ultrasound Image Velocimetry (UIV) applied in cohesive sediments (fluid mud)
<p>A standard ultrasound imaging transducer was towed trough mud at known velocities. During this movement ultrasound images were acquired at high frequency (+/- 350 Hz). Based on these images the relative velocity between the transducer and the mud was deduced using the OpenPIV script (Python version). The output was compared to the imposed velocity of the transducer to validate the accurcy of the UIV technique applied in mud. This was done for various velocities ranging from 500 mm/s to 1750 mm/s in increments of 250 mm/s. The density of the mud was fixed at 1.15 g/cm³ and the ultrasound frequency to 3.5 MHz. The combination of PIV algorithm applied to ultrasound images is referred to as Ultrasound Image Velocimetry (UIV).</p>
Three-Dimensional Ultrasound Matrix Imaging
<p><strong>Ultrasound data associated to the paper "Three-Dimensional Ultrasound Matrix Imaging",<em> Nature Communications</em>, 2023. </strong></p> <p>--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------</p> <p><strong>Abstract :</strong> "Matrix imaging paves the way towards a next revolution in wave imaging.<br>Based on the response matrix recorded between a set of sensors, it enables<br>an optimized compensation of aberration phenomena and multiple scattering<br>events that usually drastically hinder the focusing process in heterogeneous<br>media. Although it gave rise to spectacular results in optical microscopy or<br>seismic imaging, the success of matrix imaging has been so far relatively lim-<br>ited with ultrasonic waves because wave control is generally only performed<br>with a linear array of transducers. In this paper, we extend ultrasound ma-<br>trix imaging to a 3D geometry. Switching from a 1D to a 2D probe enables<br>a much sharper estimation of the transmission matrix that links each trans-<br>ducer and each medium voxel. Here, we first present an experimental proof<br>of concept on a tissue-mimicking phantom through ex-vivo tissues and then,<br>show the potential of 3D matrix imaging for transcranial applications."</p> <p>--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------</p> <p>Data corresponding to the <strong>pork tissue experiment</strong>: <br>- Raw data: "1_PorkChop_on_Phantom.mat" [Fig. 1, 2, 3 and Supplementary Fig. S3, S4, S5]<br>- Focused reflection matrix (after beamforming): "1bis_PorkChop_on_Phantom_Focused_reflection_Matrix_Rdrr.mat" </p> <p>Raw data corresponding to the<strong> head phantom experiment</strong>: <br>- "2_HeadPhantom_position1.mat" [Fig. 4 & 5, S6, S7]<br>- "2_HeadPhantom_position2.mat" [Fig. 6]</p> <p>Raw data corresponding to the tissue mimicking phantom without aberrations: <br>- "4_Phantom_withtout_aberrations.mat" [supplementary Fig. S8]</p> <p>In each case : <br>- <strong>"rfr"</strong> contains the raw ultrasound data;<br>- <strong>"p"</strong> is a structure that contains all the parameters used during acquisition.<br> </p>
Evaluation of ultrasound sensors for transcranial photoacoustic sensing and imaging - Data
<p>Raw data and simulation code for the paper "Evaluation of ultrasound sensors for transcranial photoacoustic sensing and imaging"</p>
FETAL_PLANES_DB: Common maternal-fetal ultrasound images
<p>A large dataset of routinely acquired maternal-fetal screening ultrasound images collected from two different hospitals by several operators and ultrasound machines. All images were manually labeled by an expert maternal fetal clinician. Images are divided into 6 classes: four of the most widely used fetal anatomical planes (Abdomen, Brain, Femur and Thorax), the mother’s cervix (widely used for prematurity screening) and a general category to include any other less common image plane. Fetal brain images are further categorized into the 3 most common fetal brain planes (Trans-thalamic, Trans-cerebellum, Trans-ventricular) to judge fine grain categorization performance. Meta information (patient number, us machine, operator) is also provided, as well as the training-test split used in the Nature Sci Rep paper.</p>
Sonography display demonstrating intra-operative ultrasound imaging guidance for the localization of the foreign body (dental implant) in the soft tissues of the floor of the mouth via navigation with a spinal needle.
<p>This video demonstrates the intraoperative navigation system with using sonography to localize foreign bodies in the soft tissues of the floor of the mouth with the help of a spinal needle</p>
Four-dimensional computational ultrasound imaging of brain hemodynamics
<p><span>Four-dimensional ultrasound imaging of complex biological systems such as the brain is technically challenging because of the spatiotemporal sampling requirements. We present computational ultrasound imaging (cUSi), an imaging method that uses complex ultrasound fields that can be generated with simple hardware and a physical wave prediction model to alleviate the sampling constraints. cUSi allows for high-resolution four-dimensional imaging of brain haemodynamics in awake and anesthetized mice.</span></p>
Converting Pixel into millimeter in ultrasound images: Technique and dataset
<p>A new dataset available for the public research community; our dataset includes 2835 images representing three fetal head plans (Trans-cerebellum, Trans-thalamic, and Trans-ventricular). Further, the dataset is large and more diverse regarding fetal planes in various gestational ages (GA). Table 1. provides a descriptive analysis of the dataset that includes the number of samples (N), mean, median, standard deviation (S), the minimum and maximum pixel value in mm, and three percentiles.</p> <p><strong>Please cite the original conference paper of this work.</strong></p> <table align="center"> <thead> <tr> <th> <p><strong>Table 1</strong>: Descriptive analysis for our dataset</p> </th> </tr> </thead> </table> <table align="center"> <thead> <tr> <th> <p><strong>N</strong></p> </th> <th> <p><strong>Mean</strong></p> </th> <th> <p><strong>Median</strong></p> </th> <th> <p><strong>SD</strong></p> </th> <th> <p><strong>Minimum</strong></p> </th> <th> <p><strong>Maximum</strong></p> </th> <th> <p><strong>25th</strong></p> </th> <th> <p><strong>50th</strong></p> </th> <th> <p><strong>75th</strong></p> </th> </tr> </thead> <tbody> <tr> <td> <p>2835</p> </td> <td> <p>0.144</p> </td> <td> <p>0.130</p> </td> <td> <p>0.0441</p> </td> <td> <p>0.0600</p> </td> <td> <p>0.330</p> </td> <td> <p>0.110</p> </td> <td> <p>0.130</p> </td> <td> <p>0.180</p> </td> <td> <p> </p> </td> </tr> </tbody> </table> <p> </p> <p> </p>
Schlieren images of Ultrasound
Open the record for dataset details and reuse information.
Automated measurement of fetal head circumference using 2D ultrasound images
<p>For more information about this dataset go to: <a href="https://hc18.grand-challenge.org/">https://hc18.grand-challenge.org/</a></p>
Predicting Location and Extent of Prostate Cancer Using Micro-Ultrasound Imaging
ClinicalTrials.gov study NCT04981223. IPD Sharing: NO. Countries: 1. Publications: 1.
Ultrasound and Near Infrared Imaging for Predicting and Monitoring Neoadjuvant Treatment
ClinicalTrials.gov study NCT02891681. IPD Sharing: NO. Countries: 1. Publications: 1.
Study of Ultrasound Imaging to Predict Time and Outcome in Pregnancies With Induced Labor
ClinicalTrials.gov study NCT00465998. IPD Sharing: Not stated. Countries: 1. Publications: 6.
Evaluation of Imaging of Peripheral Arteries by Optical Coherence Tomography and Intravascular Ultrasound Imaging
ClinicalTrials.gov study NCT03480685. IPD Sharing: NO. Countries: 1. Publications: 1.
Determining the Validity of ThinkSono Guidance for Ultrasound Image Acquisition and Remote Detection
ClinicalTrials.gov study NCT06652568. IPD Sharing: NO. Countries: 1. Publications: 8.
Ultrasound Liver Intraoperative Imaging With SonoVue®
ClinicalTrials.gov study NCT01880554. IPD Sharing: Not stated. Countries: 1. Publications: 1.
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.