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.
217
datasets available to search
ShareScore release 0.9.0
Dataset results
217 results for “image contrast”
Efficacy and Safety Study to Evaluate Gadavist (Gadobutrol) as Contrast Agent in Magnetic Resonance Imaging (MRI) of Brain or Spine Diseases in Chinese Patients
ClinicalTrials.gov study NCT00395460. IPD Sharing: Not stated. Countries: 1. Publications: 0.
Images of individual strawberries (entire fruit, flesh and calyx) with contrasting background
Open the record for dataset details and reuse information.
Phase contrast images of Hierodula membranacea spermatocytes in metaphase I
Open the record for dataset details and reuse information.
Data from: Label-free imaging of intracellular structures in living mammalian cells via external apodization phase-contrast microscopy
Open the record for dataset details and reuse information.
Deep Brain Image Contrast Classification
<p>Deep Brain Image Contrast Classification</p>
Deep Brain Image Contrast Classification
<p>Deep Brain Image Contrast Classification</p>
FIGURES 8–21 in A new species of anapid spider (Araneae: Araneoidea, Anapidae) in Eocene Baltic amber, imaged using phase contrast X-ray computed micro-tomography
FIGURES 8–21. CT reconstructions of Balticoroma wheateri new species (male holotype, GPIH). (8) frontal view showing chelicerae and labral spur; (9) view of right pedipalp showing embolus; (10–14) various views of right metatarsus 1, showing y-shaped clasping structure; (15) anterior view of specimen showing the section taken through the chelicerae to produce the raw data slice in Figure 16; (16) raw data slice demonstrating that the chelicerae and clypeal extentions are clearly separated; (20–21) various views of the right pedipalp. C, chelicera; ce, clypeal extension; co, dorsal cymbial outgrowth; cy, cymbium; e, embolus; eb, embolic base; ec, embolic coil;?fc, functional conductor sensu Wunderlich (2004); ls, labral spur; t, tegulum.
FIGURE 1 in A new species of anapid spider (Araneae: Araneoidea, Anapidae) in Eocene Baltic amber, imaged using phase contrast X-ray computed micro-tomography
FIGURE 1. Microphotograph of Balticoroma wheateri new species (male holotype, GPIH). Body length = 1.8 mm.
FIGURES 2–7 in A new species of anapid spider (Araneae: Araneoidea, Anapidae) in Eocene Baltic amber, imaged using phase contrast X-ray computed micro-tomography
FIGURES 2–7. CT reconstructions of Balticoroma wheateri new species (male holotype, GPIH). (2) right lateral view; (3) left lateral view; (4) dorsal view; (5) ventral view; (6) anterior view; (7) posterior view. Body length = 1.8 mm. Mt1, metatarsus 1; ta1, tarsus 1; ti1, tibia 1.
2D phase contrast HeLa cells images with ground truth annotations
<p>Original images are from http://www.robots.ox.ac.uk/~vgg/software/cell_detection/. This software is associated with the publication "Learning to Detect Cells Using Non-overlapping Extremal Regions", MICCAI 2012. (DOI: 10.1007/978-3-642-33415-3_43)</p> <p>Here, we provide the ground truth labels of: cell centers and segmentation, which are used in the publications:</p> <ul> <li>"Learning to Segment: Training Hierarchical Segmentation under a Topological Loss", MICCAI 2015. (DOI: 10.1007/978-3-319-24574-4_32)</li> <li>"Cell Detection and Segmentation Using Correlation Clustering", MICCAI 2014. (DOI: 10.1007/978-3-319-10404-1_2)</li> </ul>
"Contrast based circular approximation for accurate and robust optic disc segmentation in retinal images" - Code
<p>A new method for automatic optic disc localization and segmentation is presented. The localization procedure combines vascular and brightness information to provide the best estimate of the optic disc center which is the starting point for the segmentation algorithm. A detection rate of 99.58% and 100% was achieved for the Messidor and ONHSD databases, respectively. A simple circular approximation to the optic disc boundary is proposed based on the maximum average contrast between the inner and outer ring of a circle centered on the estimated location. An average overlap coefficient of 0.890 and 0.865 was achieved for the same datasets, outperforming other state of the art methods. The results obtained confirm the advantages of using a simple circular model under non ideal conditions as opposed to more complex deformable models.</p>
Change-Aware Sampling and Contrastive Learning for Satellite Images
<p><strong>Instructions</strong></p> <div>Change-Aware Sampling and Contrastive Learning for Satellite Images</div> <div>The 1 million sized dataset in compressed format.</div> <div>This dataset is split in 4 parts due to Zenodo's size restictions.</div> <div>Each part can be downloaded using the following link.</div> <p><strong>Part 1: </strong><a href="../records/10913216">https://zenodo.org/records/10913216</a></p> <p><strong>Part 2: </strong><a href="../records/10914902">https://zenodo.org/records/10914902</a></p> <p><strong>Part 3: </strong><a href="10915715">https://zenodo.org/uploads/10915715</a></p> <p><strong>Part 4: </strong><a href="../records/10916979">https://zenodo.org/records/10916979</a></p> <p> </p> <div>Use the following commands to combine and extract the compressed file.</div> <blockquote> <div>cat clean_1m_geography_part* > clean_1m_geography.tar.gz</div> <div>tar -xvf clean_1m_geography.tar.gz</div> </blockquote> <p> </p> <p><strong>Paper Abstract</strong></p> <p>Automatic remote sensing tools can help inform many large-scale challenges such as disaster management, climate change, etc. While a vast amount of spatio-temporal satellite image data is readily available, most of it remains unlabelled. Without labels, this data is not very useful for supervised learning algorithms. Self-supervised learning instead provides a way to learn effective representations for various downstream tasks without labels. In this work, we leverage characteristics unique to satellite images to learn better self-supervised features. Specifically, we use the temporal signal to contrast images with long-term and short-term differences, and we leverage the fact that satellite images do not change frequently. Using these characteristics, we formulate a new loss contrastive loss called Change-Aware Contrastive (CACo) Loss. Further, we also present a novel method of sampling different geographical regions. We show that leveraging these properties leads to better performance on diverse downstream tasks. For example, we see a 6.5% relative improvement for semantic segmentation and an 8.5% relative improvement for change detection over the best-performing baseline with our method.<br><br><br></p> <div> <div> </div> </div>
Time-Resolved X-ray Phase-Contrast Video Imaging of Continuous Anti-Solvent Crystallisation
<p>X-ray phase-contrast video showing early crystal growth in a continuous anti-solvent crystalliser. Data was collected on the Diamond Light source I13-2 beamline. For further information see the paper:</p> <p>@article{das_pallipurath_leng_wanelik_mcginty_miller_kathyola_chang_al-madhagi_marathae_et<br> al._2020,<br> place={Cambridge},<br> title={Time-Resolved X-ray Phase-Contrast Imaging (XPCI) of Nucleation and Crystal Growth in the Anti-Solvent Crystallization of Lovastatin},<br> DOI={10.26434/chemrxiv.12911168.v1},<br> journal={ChemRxiv},<br> publisher={Cambridge Open Engage},<br> author={Das, Gunjan and Pallipurath, Anuradha and Leng, Joanna and Wanelik, Kazimir<br> and McGinty, John and Miller, Russell and Kathyola, Thokozile and Chang,<br> Sin-Yuen and Al-Madhagi, Laila H. and Marathae, Shashidhara and et<br> al.},<br> year={2020},<br> note={This content is a preprint and has not been peer-reviewed.}<br> }</p>
The impact from the contrast of the generated images
<p>The contrast of the generated images was dull for the S2IGAN code, as given. By enhancing brightness and contrast, this problem could be solved. However, we found this is only needed for human evaluation: On 20 selected images, the IS score for S2IGAN was the same for the raw (greyish) output and the enhanced output samples. </p>
Contrastive Learning for Fine-Grained Ship Classification in Remote Sensing Images
<p>Dataset for Contrastive Learning for Fine-Grained Ship Classification in Remote Sensing Images from https://github.com/WindVChen/Push-and-Pull-Network?tab=readme-ov-file</p>
On the effect of precession for magnetic differential phase contrast imaging
<p>4D-STEM datasets and processing scripts used for the journal publication "<strong>On the effect of precession for magnetic differential phase contrast imaging</strong>".</p> <p>DOI link to publication: <a href="https://doi.org/10.1016/j.micron.2024.103761">10.1016/j.micron.2024.103761</a></p> <p> </p> <p><strong>Prerequisites</strong></p> <p>The scripts presented below were created using open-source Python packages with specific versions:</p> <ul> <li>hyperspy 1.7.1</li> <li>pyxem 0.14.2</li> <li>fpd 0.2.5 (with scikit-image 0.18)</li> <li>jupyterlab 4.0.7</li> </ul> <p>There is no guarantee that other versions of the listed packages will run the code.</p> <p><strong>Data files</strong></p> <p>In total five zipped (.7z extension) files are included in this repository. The files contain data from the different samples studied with different precession electron diffraction calibrations where applicable. The three samples studied are LSMO, and the corresponding 4D-STEM datasets taken away from a high-symmetry zone axis (<em>LSMO_LZ_data.7z</em>) and on the zone axis (<em>LSMO_HZ_data.7z</em>), FeAl sample (<em>FeAl_data.7z</em>), and scans from an Au TEM alignment grid (<em>AuGrid_data.7z</em>). The <em>precession_azimuths.7z</em> files contains the precession azimuthal circles from the three precession calibrations performed.</p> <p><strong>Processing scripts</strong></p> <p>Three scripts are included in the IPython notebook format (.ipynb extension). The <em>Precession_azimuth_plot.ipynb</em> script plots the precession azimuth for comparison. The <em>Segmentation_script.ipynb</em> is used to process the precession path segmented 4D-STEM datasets, and the <em>DPC_processing.ipynb</em> includes code to perform center of mass and phase correlation processing on the 4D-STEM data to extract differential phase contrast signals.</p>
Multimodal contrastive learning for spatial gene expression prediction using histology images
<p>we employed two human breast cancer datasets and one human cutaneous squamous cell carcinoma (cSCC) dataset.</p>
Digital breast tomosynthesis and contrast-enhanced dual-energy digital mammography alone and in combination compared to 2D digital synthetized mammography and MR imaging in breast cancer detection and classification
<p>We uploaded the dataset of included patients of manuscript: Petrillo A, Fusco R, Vallone P, Filice S, Granata V, Petrosino T, Rosaria Rubulotta M, Setola SV, Mattace Raso M, Maio F, Raiano C, Siani C, Di Bonito M, Botti G. Digital breast tomosynthesis and contrast-enhanced dual-energy digital mammography alone and in combination compared to 2D digital synthetized mammography and MR imaging in breast cancer detection and classification. Breast J. 2020 May;26(5):860-872. doi: 10.1111/tbj.13739. Epub 2019 Dec 30. PMID: 31886607.</p>
Magnetic resonance imaging in the assessment of pancreatic cancer with quantitative parameter extraction by means of dynamic contrast-enhanced magnetic resonance imaging, diffusion kurtosis imaging and intravoxel incoherent motion diffusion-weighted imaging
<p>We uploaded IVIM and DKI parameters values of included patients in the manuscript: Fusco, Roberta, Adele Piccirillo, Mario Sansone, Vincenza Granata, Paolo Vallone, Maria L. Barretta, Teresa Petrosino, Claudio Siani, Raimondo Di Giacomo, Maurizio Di Bonito, Gerardo Botti, and Antonella Petrillo. 2021. "Radiomic and Artificial Intelligence Analysis with Textural Metrics, Morphological and Dynamic Perfusion Features Extracted by Dynamic Contrast-Enhanced Magnetic Resonance Imaging in the Classification of Breast Lesions" Applied Sciences 11, no. 4: 1880. https://doi.org/10.3390/app11041880</p>
Radiomic and Artificial Intelligence Analysis with Textural Metrics, Morphological and Dynamic Perfusion Features Extracted by Dynamic Contrast-Enhanced Magnetic Resonance Imaging in the Classification of Breast Lesions
<p>We uploaded the 15 morphological features of 91 samples of 85 patients analyzed in the manuscript: Fusco, Roberta, Adele Piccirillo, Mario Sansone, Vincenza Granata, Paolo Vallone, Maria L. Barretta, Teresa Petrosino, Claudio Siani, Raimondo Di Giacomo, Maurizio Di Bonito, Gerardo Botti, and Antonella Petrillo. 2021. "Radiomic and Artificial Intelligence Analysis with Textural Metrics, Morphological and Dynamic Perfusion Features Extracted by Dynamic Contrast-Enhanced Magnetic Resonance Imaging in the Classification of Breast Lesions" Applied Sciences 11, no. 4: 1880. https://doi.org/10.3390/app11041880</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.