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.
155
datasets available to search
ShareScore release 0.9.0
Dataset results
155 results for “2D images”
EchoPT: A Pretrained Transformer Architecture for Predicting 2D In-Air Sonar Images in Mobile Robotics
<h1>EchoGPT</h1> <p>This folder contains the supplementary data and code for the submission "EchoPT: A Pretrained Transformer Architecture for Predicting 2D In-Air Sonar Images in Mobile Robotics" to the NeurIPS 2024 conference.</p> <h2>Dependencies</h2> <p>Matlab 2024a or higher is needed with the following toolboxes:</p> <ul> <li>Image Processing Toolbox</li> <li>Parallel Computing Toolbox</li> <li>Deep Learning Toolbox</li> <li>Signal Processing Toolbox</li> <li>System Identification Toolbox</li> </ul> <h2>Data</h2> <h3>Simulation</h3> <p>This folder contains the saved sonar images (energyscapes) as well as the motion data for each frame from a particular simulation run (LongRun1). These are saved into batches and saved as compressed .mat files within the <em>\DataCalculated\SimulationData\LongRun1\Raw</em> folder.</p> <h3>Trained model</h3> <p>The model used in the experiments of this submission is saved in <em>\DataCalculated\Networks</em> as a Matlab dlnetwork object. There is a trained (with weights) and an untrained version available.</p> <h2>Code</h2> <h3>Data pre-processing</h3> <p>To extract the data from the batch .mat files into seperate frames a script <strong>preprocessEchoPT.m</strong> is available in the main folder. This will save these individual frames once again to individual .mat files into a folder <em>\DataCalculated\ESSequences</em> by default.</p> <h3>Training</h3> <p>To train the model a Matlab script <strong>trainEchoPT.m</strong> is provided.</p> <h3>Evaluation</h3> <p>To generate the figures of the submission as well as additional outputs such as GIFs three different evaluation scripts are available:</p> <ul> <li><strong>evaluateEchoPT.m</strong>: Evaluate the trained model on the dataset.</li> <li><strong>evaluateEchoPT_ComparisonAccFlow_ARLoop.m</strong>: Evaluate the trained model on the dataset and compare it to acoustic flow with autoregressive prediction.</li> <li><strong>evaluateEchoPT_ComparisonAccFlow_NoAR.m</strong>: Evaluate the trained model on the dataset and compare it to acoustic flow without autoregressive prediction.</li> </ul> <h3>Source</h3> <p>Within the folder <em>\Source</em> all additional Matlab functions and classes can be found.</p> <h2>Open-Source libraries included in this project</h2> <ul> <li>Progress bar by HyunGwang Cho <a href="https://www.mathworks.com/matlabcentral/fileexchange/121363-progress-bar-cli-gui-parfor?s_tid=srchtitle">(link)</a></li> </ul>
Ratiometric Near Infrared Fluorescence Imaging of Dopamine with 1D and 2D nanomaterials - Raw Data
Open the record for dataset details and reuse information.
Is Any Additional Information Gained Regarding Margins Using 3D Tomosynthesis Vs 2D Conventional Digital Imaging When Imaging Operative Breast Specimens?
ClinicalTrials.gov study NCT02096185. IPD Sharing: Not stated. Countries: 1. Publications: 0.
A Study on the Acquisition of 2D ICE Images With the CHORUS IDx System in Subjects Undergoing an Ablation Procedure
ClinicalTrials.gov study NCT07353710. IPD Sharing: NO. Countries: 0. Publications: 0.
2D and Tissue Doppler Imaging Echocardiography Analysis of Left Ventricular Regional Wall Motion and Prognosis
ClinicalTrials.gov study NCT01092429. IPD Sharing: Not stated. Countries: 1. Publications: 0.
Transcranial Ultrasonography Using Linear 2D Imaging of the Brain
ClinicalTrials.gov study NCT01980186. IPD Sharing: Not stated. Countries: 1. Publications: 0.
Superb Microvascular Imaging (SMI) and Two-Dimensional Endoscopic Ultrasound Guided Shear Wave Elastography (2D-SWE-EUS) in Differential Diagnosis of Pancreatic Adenocarcinoma (PA) From Other Pancreat
ClinicalTrials.gov study NCT07274657. IPD Sharing: NO. Countries: 1. Publications: 0.
The Reproducibility of Microvascular Flow Imaging in Fibroids and Its Correlation With 2D and 3D Power Doppler Outcomes
ClinicalTrials.gov study NCT05643339. IPD Sharing: NO. Countries: 1. Publications: 0.
Project 1: Self-Triage by 2D Full-field Digital Mammography or Synthetic Images
ClinicalTrials.gov study NCT05960188. IPD Sharing: YES. Countries: 1. Publications: 0.
A Pilot Study Investigating the Impact of Different IOL Designs on Subjective 2D and 3D Image Quality
ClinicalTrials.gov study NCT02409641. IPD Sharing: Not stated. Countries: 1. Publications: 0.
2D high-resolution synthetic MR images of Alzheimer's patients and healthy subjects using PACGAN
<p>This dataset encompasses a NIfTI file containing a collection of 500 images, each capturing the central axial slice of a <strong>synthetic brain MRI</strong>. </p> <p>Accompanying this file is a CSV dataset that serves as a repository for the corresponding <strong>labels</strong> linked to each image:</p> <ul> <li><em>Label 0</em>: Healthy Controls (HC)</li> <li><em>Label 1</em>: Alzheimer's Disease (AD)</li> </ul> <p> </p> <p>Each image within this dataset has been generated by <a href="https://github.com/aiformedresearch/PACGAN">PACGAN</a> (Progressive Auxiliary Classifier Generative Adversarial Network), a framework designed and implemented by the <a href="https://aiformedresearch.github.io/aiformedresearch/">AI for Medicine Research Group</a> at the University of Bologna.</p> <p>PACGAN is a generative adversarial network trained to generate high-resolution images belonging to different classes. In our work, we trained this framework on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, which contains brain MRI images of AD patients and HC.</p> <p>The implementation of the training algorithm can be found within our <a href="https://github.com/aiformedresearch/PACGAN">GitHub</a> repository, with <a href="https://hub.docker.com/r/aiformedresearch/pacgan">Docker</a> containerization.</p> <p>For further exploration, the pre-trained models are available within the <a href="https://codeocean.com/capsule/6317229/tree">Code Ocean capsule</a>. These models can facilitate the generation of synthetic images for both classes and also aid in classifying new brain MRI images.</p>
2D&3D images - profile scans dataset
<p>2D and 3D images of PCBs showing the gap 2D and 3D information. Moreover, profile measurements are also included in x and y axes.</p>
Head-Neck-PET-CT combined GTVs 2D images
<p>This dataset contains 2D images of the combined Gross Tumour Volumes (GTVs) of a Head and Neck cancer public dataset created from four different institutions in Canada. 298 images were created by using the CT and the combined GTV masks extracted from the RTSTRUCTs associated with the patient study. The dataset was orginally collected from https://wiki.cancerimagingarchive.net/display/Public/Head-Neck-PET-CT into an Orthanc server. Patient studies were then processed into 3d numpy arrays. The central slices representing the slice with the highest number of contoured pixels were selected and extracted into 2d numpy arrays. </p>
Carotid Phase-Contrast Magnetic Resonance before Treatment: 4D-Flow versus Standard 2D Imaging
<p>Secchi F, Monti CB, Capra D, Vitale R, Mazzaccaro D, Conti M, Jin N, Giese D, Nano G, Sardanelli F, Marrocco-Trischitta MM. Carotid Phase-Contrast Magnetic Resonance before Treatment: 4D-Flow versus Standard 2D Imaging. Tomography. 2021 Sep 28;7(4):513-522. doi: 10.3390/tomography7040044. PMID: 34698250; PMCID: PMC8544659.</p> <p>Abstract</p> <p>The purpose of this study was to evaluate the level of agreement between flow/velocity data obtained from 2D-phase-contrast (PC) and 4D-flow in patients scheduled for treatment of carotid artery stenosis. Image acquisition was performed using a 1.5 T scanner. We compared mean flow rates, vessel areas, and peak velocities obtained during the acquisition with both techniques in 20 consecutive patients, 15 males and 5 females aged 69 ± 5 years (mean ± standard deviation). There was a good correlation between both techniques for the CCA flow (<em>r</em> = 0.65, <em>p</em> < 0.001), whereas for the ICA flow and ECA flow the correlation was only moderate (<em>r</em> = 0.4, <em>p</em> = 0.011 and <em>r</em> = 0.45, <em>p</em> = 0.003, respectively). Correlations of peak velocities between methods were good for CCA (<em>r</em> = 0.56, <em>p</em> < 0.001) and moderate for ECA (<em>r</em> = 0.41, <em>p</em> = 0.008). There was no correlation for ICA (<em>r</em> = 0.04, <em>p</em> = 0.805). Cross-sectional area values between methods showed no significant correlations for CCA (<em>r</em> = 0.18, <em>p</em> = 0.269), ICA (<em>r</em> = 0.1, <em>p</em> = 0.543), and ECA (<em>r</em> = 0.05, <em>p</em> = 0.767). Conclusion: the 4D-flow imaging provided a good correlation of CCA and a moderate correlation of ICA flow rates against 2D-PC, underestimating peak velocities and overestimating cross-sectional areas in all carotid segments.</p>
Prognostic value of left atrial strain quantification from 2D ultrasound imaging in post-ischemic heart failure patients: evidence from the REMODEL-HF study.
<p>Frigelli M, Sturla F, Milani V, Ramputi L, Citarella M, Menicanti L, Votta E, Castelvecchio S. Prognostic value of left atrial strain quantification from 2D ultrasound imaging in post-ischemic heart failure patients: evidence from the REMODEL-HF study. Int J Cardiol. 2022 Sep 1;362:183-189. doi: 10.1016/j.ijcard.2022.04.071. Epub 2022 Apr 30. PMID: 35504452.</p> <p>Abstract</p> <p><strong>Background: </strong>Left atrial (LA) function can be effectively assessed by measuring longitudinal LA strain (LAS) via two-dimensional speckle tracking echocardiography (2DSTE). Here, we test 2DSTE-based LAS as marker of different left ventricle (LV) remodeling patterns and as prognostic index in ischemic heart failure (HF) candidates to surgical ventricular reconstruction.</p> <p><strong>Methods: </strong>We retrospectively considered ischemic HF patients with anterior (group A, n=130) or posterior (group P, n=48) LV remodeling. Based on 2D ultrasound, LV and LA morpho-functional parameters were quantified including reservoir (LAS<sub>Res</sub>), conduit (LAS<sub>Cond</sub>) and booster (LAS<sub>Boost</sub>) LAS. We tested their capability to discriminate between groups A and P, and their group-specific prognostic significance for the composite end-point of death or HF re-hospitalization at follow-up (mean follow-up time=40 months, range 3-101 months).</p> <p><strong>Results: </strong>Group A and group P displayed similar end-diastolic (p=0.89) and end-systolic (p=0.33) LV volume index, and LA volume index LAVi (p=0.44) corrected for the degree of mitral regurgitation. As compared to group P, group A revealed a significant reduction in LAS<sub>Boost</sub> (9.2±0.4% vs. 11.1±0.7%, p=0.04) and a non-significant reduction in LAS<sub>Res</sub> (16.9±0.7% vs. 19.3±1.1%, p=0.06). Kaplan-Meier curves showed that the median LAS<sub>Res</sub> and LAS<sub>Boost</sub> values effectively stratified patients based on their prognosis in the overall study population (Log-rank p=0.002 and Log_rank p<0.0001) and in group A, where the association was stronger for LAS<sub>Boost</sub> (Log-rank p<0.001) than for LAS<sub>Res</sub> (Log-rank p=0.013).</p> <p><strong>Conclusions: </strong>2DSTE-based LAS assessment is affordable, repeatable and non-invasive, and could add clinically-relevant mechanistic insight and prognostic value in the stratification of ischemic HF patients.</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.