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.
979
datasets available to search
ShareScore release 0.9.0
Dataset results
979 results for “image dataset”
Image Dataset and Trained Detection Models (based on YOLOv5 and EfficientNet) of Mangrove Crabs of China
<p>A manually annotated image dataset of crabs collected from 16 mangrove forests in China, and a set of trained detection models based on YOLOv5 and EfficientNet. We provide a simple UI that is designed by us, please cite it if helpful.</p>
UTOM dataset: whole-slide pathological images of various kinds of cancers
<p>UTOM dataset: whole-slide pathological images of various kinds of cancers</p>
Dataset related to article "Assessing the Feasibility and Accuracy of High-resolution Microultrasound Imaging for Bladder Cancer Detection and Staging"
<p>BACKGROUND:</p> <p>Magnetic resonance imaging (MRI) has been proposed as a staging tool for bladder cancer (BC), but its use has been limited by its high costs and limited availability. Microultrasound (mUS) is a novel technology capable of providing high-resolution images of the prostate.</p> <p>OBJECTIVE:</p> <p>To test the feasibility of high-resolution mUS in patients diagnosed with BC and its ability to differentiate between non-muscle-invasive BC (NMIBC) and muscle-invasive BC (MIBC).</p> <p>DESIGN, SETTING, AND PARTICIPANTS:</p> <p>This is an observational prospective study performed in 23 patients with a diagnosis of primary BC scheduled for an endoscopic treatment.</p> <p>SURGICAL PROCEDURE:</p> <p>Micro-US was performed before transurethral resection of bladder tumor using the ExactVu system with an EV29L 29-MHz side-fire transducer (Exact Imaging, Markham, Canada).</p> <p>MEASUREMENTS:</p> <p>The endpoints were to test the feasibility, describe the normal bladder wall anatomy, identify the lesions, and compare the mUS findings with the histopathological results.</p> <p>RESULTS AND LIMITATIONS:</p> <p>Micro-US was accurate in differentiating the three layers of the bladder wall in all cases. Bladder cancers were clearly identified as heterogeneous structures protruding from the normal bladder wall. In 14 cases the lesions appeared confined to the lamina propria, and in all cases NMIBC was confirmed by the final pathological report. In the other patients, the lesions seemed to extend into the muscular layer, but MIBC was confirmed in five out of seven cases (71.4%) from the pathologist. The small sample size was the main limitation of the current study.</p> <p>CONCLUSIONS:</p> <p>Our findings showed that mUS is able to differentiate the bladder wall layers and identify the bladder cancer stage. Further studies with a larger population and imaging correlation with MRI are warranted before its introduction in clinical practice.</p> <p>PATIENT SUMMARY:</p> <p>In this report, a new imaging technique was tested for the characterization of bladder cancer. Microultrasound appears to be feasible and capable of discriminating between superficial and invasive tumors</p>
Dataset related to article "Contrast imaging techniques to diagnose hepatocellular carcinoma in cirrhotics outside regular surveillance."
<p>I</p> <p>NTRODUCTION AND AIM:</p> <p>The American Association for the Study of the Liver (AASLD) recommends contrast computerized tomography (CT-scan) and magnetic resonance (MRI) to diagnose hepatocellular carcinoma (HCC) arising in cirrhotic patients under semiannual surveillance with abdominal ultrasound (US). A US guided fine needle biopsy (FNB) serves the same purpose in radiologically undiagnosed tumors and incidentally detected nodules in cirrhotics outside surveillance. In this population, we evaluated the performance of radiological diagnosis of HCC according to 2010 AASLD recommendations.</p> <p>MATERIALS AND METHODS:</p> <p>All cirrhotic patients with a liver nodule incidentally detected by US were prospectively investigated with a sequential application of CT-scan/MRI examination and a FNB.</p> <p>RESULTS:</p> <p>Between 2011 and 2015, 94 patients (mean age 67 years) had a liver nodule (total 120) detected by US in the context of histologically confirmed cirrhosis. Mean nodules diameter was 40 (10-160) mm, 87 (73%) <5cm. At histology, 84 (70%) nodules were HCC, 8 (7%) intrahepatic cholangiocarcinoma, 6 (5%) metastases, 2 (2%) neuroendocrine tumors and 20 (16%) benign lesions. Hyperenhancement in arterial phase followed by wash-out in venous phases on at least one radiological technique was demonstrated in 62 nodules (61 HCC, 1 high grade dysplastic nodule), with a specificity of 97% (IC95%: 85-100%), sensitivity 73% (IC95%: 62-81%) and diagnostic accuracy 80%, being 64% for ≥5cm HCC. Sensitivity of AFP >200ng/mL was 12% (IC95%: 6-23%).</p> <p>CONCLUSION:</p> <p>A single contrast imaging technique showing a typical contrast pattern confidently identifies HCC also in cirrhotic patients with an incidental liver nodule, thereby reducing the need for FNB examinations.</p>
Imaging dataset acquired by PCAT
<p>The "concave" and "convex" contain 8*8 time-series signals of ultrasonic bulk wave array inspection by the 8-element PCAT with concave and convex surfaces (Figure 7c and d), respectively. The "resonance" contains frequency spectra of the ultrasonic local resonances excited by a single PCAT element with scanning lateral distance (Figure 11a). The imaging algorithms are easy to reproduce. Other data will be made available on request.</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>
Agricultural Crop Disease Image Dataset from Tanzania
<p>A comprehensive Crop Disease Image Dataset meticulously curated to aid in the study and advancement of agricultural research and plant pathology within Tanzania. This dataset encompasses a diverse array of classes, each representing distinct diseases and health states affecting a variety of crops commonly cultivated in Tanzanian agriculture. Classes include American Poppy, Bean Angular Leaf Spot, Bean Healthy, Bean Leaf Miner, Bean Light Yellow, Bean Rust, Bell Pepper Early Bright, Bell Pepper Fusarium Wilt, Bell Pepper Healthy, Black Nightshade Healthy, Black Nightshade Leaf Miner, Cabbage CP Deficiency, Cabbage Healthy, Chinese Botanical Leaf Spot, Chinese Healthy, Maize Faw, Maize Health, Maize Leaf Aphid, Maize Streak Virus, Okra Health, Okra Leaf Miner, Okra Powderly, Onions Healthy, Onions Powderly, Spinach Anthracnose, Spinach Health, Tomato Health, and Tomato Leaf Miner. Each class represents a distinct disease or health state commonly observed in crops grown throughout Tanzania, providing a valuable resource for researchers, agronomists, and machine learning practitioners alike. With a diverse range of classes meticulously labeled and organized, this dataset facilitates the development and evaluation of algorithms for disease detection, classification, and mitigation strategies specific to Tanzanian agricultural contexts.</p>
A comprehensive dataset of magnetic resonance enterography images with bowel segment annotations
<p>Inflammatory bowel disease (IBD) is a kind of recurrent bowel disease and usually requires magnetic resonance enterography (MRE) examinations for diagnosis and monitoring. However, radiologists’ recognition of bowel segments from MRE images is challenging and time-consuming. Deep learning-based medical image segmentation has shown the potential to reduce manual efforts and provide automated tools to assist in the management of disease, but it requires a large-scale fine<span>-</span>annotated dataset for training. To address this gap, we collected MRE data from 114 IBD patients. The bowel images per patient were contoured and annotated as ten segments (stomach, duodenum, small intestine, appendix, cecum, ascending colon, transverse colon, descending colon, sigmoid colon, and rectum), with fine pixel-level annotations labeled by experienced radiologists. Further, we <span>validated</span> the efficiency of several state-of-the-art segmentation methods on this dataset. This work established a high quality, publicly available whole bowel segment MR dataset with benchmark results and laid a groundwork for IBD’s AI research.</p>
A Dataset of Questionnaire on the Domestic Image of China and Media Use for China's Post-90s Generation
<p><a name="OLE_LINK1"></a><span>The dataset consists of 5 files:</span></p> <p><span><span>(1) Readme-China-Post90s.pdf</span></span></p> <p><span><span>(2) Questionnaire-China-Post90s.pdf</span></span></p> <p><span><span>(3) Questionnaire-China-Post90s-CN.pdf</span></span></p> <p><span><span>(4) SurveyData-China-Post90s.csv</span></span></p> <p><span><span>(5) SurveyData-China-Post90s.xlsx</span></span></p> <p>Please see Readme file “Readme-China-Post90s.pdf”.</p>
Training and testing labelled dataset of human faces for different indoor visual comfort and glare visual discomfort situations - images
<p>The image dataset is generated from experimental tests on 23 different participants and includes a certain variety in characteristics: age, gender, face feature, glasses, etc. The original dataset was generated from experimental tests on 24 different participants but all the data of one of the participants was entirely excluded as this participant did not want his/her data to be publically available.</p> <p>After synchronization of the video footages with the answers of the participants regarding their visual discomfort at the different phases of the experiment to label the video dataset, the video footages are resampled at a 0.5 FPS rate, and the YOLOFace extraction algorithm is used to crop the image down to the face of the occupants only and generate the labelled image dataset. </p>
A semantic segmentation dataset consisting of soil-root images with multiple growth stages.
<p> A semantic segmentation dataset consisting of soil-root images with multiple growth stages.</p> <blockquote> <p><strong>Last Update: 2022.08.10</strong></p> </blockquote>
Self-Supervised Learning Cell Image Dataset of Master Thesis "Enhancing Cell Instance Segmentation in 3D Microscopy using Self-Supervised ViTs"
<p>This is the self-supervised learning cell image dataset of master thesis "Enhancing Cell Instance Segmentation in 3D Microscopy using Self-Supervised ViTs". We gather images from datasets such as the LIVECell dataset, the EVICAN dataset, as well as datasets available on Image Data Resource (https://idr.openmicroscopy.org/) and the Broad Bioimage Benchmark Collection (https://bbbc.broadinstitute.org/). Only images with sizes larger than 512x512 are collected. For datasets containing more than 1000 images, we randomly select 1000 images. Otherwise, we retain all images in the dataset. </p> <p> </p> <p>After download, please put all compressed folders of subdatasets in the "image" folder under the root directory.</p>
H2OPM Image Registration Dataset
<p>The H2OPM Image Registration Dataset is a dataset for the evaluation of (groupwise) registration methods. It consists of 8 reference ortho-photo maps (OPMs) of urban and non-urban areas in Austria. For each reference image, 3-11 historical aerial images captured between May 1943 and May 1945 are available, leading to a total of 42 image pairs. In order to evaluate the registration accuracy, manually selected ground truth correspondences between the historical images and the OPM are provided.</p> <p>Technical Details</p> <p>All images have been scale-normalized to a spatial resolution of 1m . However, for the historical images scale information could only approximated, the actual scale of the images might be actually off up to 30%.</p> <p>Reference OPM images are named “ref_i.png” (i=reference image number, 1..8).<br> Corresponding historical images are named “image_i_j.png” (j=historical image number). For example, “image_2_4.png” is the fourth out of five historical images that could be registered to reference image “ref_2.png”.</p> <p>Ground truth control points are given in the text files “CP_i_j.txt”. Each row of the text file describes one control point pair with values x1,y1,x2,y2. The origin of the coordinate system is the top left of the image, x-axis points right, y-axis points down.</p> <p>The dataset is used for evaluation in the following paper:</p> <p><strong>Zambanini S. </strong>“<a href="https://doi.org/10.1016/j.patcog.2019.01.024">Feature-based groupwise registration of historical aerial images to present-day ortho-photo maps</a>“, <em>Pattern Recognition</em>, 90:66-77, June 2019. (<a href="https://arxiv.org/abs/1811.09081">arXiv</a>)</p> <p>Please cite this paper when publishing results on the dataset.</p>
Dataset related to article: "68Ga-PSMA Positron Emission Tomography/Computerized Tomography for Primary Diagnosis of Prostate Cancer in Men with Contraindications to or Negative Multiparametric Magnetic Resonance Imaging: A Prospective Observational Study"
<p>This record contains raw data related to article 68Ga-PSMA Positron Emission Tomography/Computerized Tomography for Primary Diagnosis of Prostate Cancer in Men with Contraindications to or Negative Multiparametric Magnetic Resonance Imaging: A Prospective Observational Study</p> <p>PURPOSE:</p> <p><sup>68</sup>Ga labeled prostate specific membrane antigen positron emission tomography/computerized tomography may represent the most promising imaging modality to identify and risk stratify prostate cancer in patients with contraindications to or negative multiparametric magnetic resonance imaging.</p> <p>MATERIALS AND METHODS:</p> <p>In this prospective observational study we analyzed <sup>68</sup>Ga labeled prostate specific membrane antigen positron emission tomography/computerized tomography in a select group of patients with persistently elevated prostate specific antigen and/or Prostate Health Index suspicious for prostate cancer, negative digital rectal examination and at least 1 negative biopsy. The cohort comprised men with equivocal multiparametric magnetic resonance imaging (Prostate Imaging-Reporting and Data System, version 2 score of 2 or less), or an absolute or relative contraindication to multiparametric magnetic resonance imaging. Sensitivity, specificity and CIs were calculated compared to histopathology findings. ROC analysis was applied to determine the optimal cutoff values of <sup>68</sup>Ga labeled prostate specific membrane antigen uptake to identify clinically significant prostate cancer (Gleason score 7 or greater).</p> <p>RESULTS:</p> <p>A total of 45 patients with a median age of 64 years were referred for <sup>68</sup>Ga labeled prostate specific membrane antigen positron emission tomography/computerized tomography between January and August 2017. The 25 patients (55.5%) considered to have positive positron emission tomography results underwent software assisted fusion biopsy. We determined the uptake values of regions of interest, including a median maximum standardized uptake value of 5.34 (range 2.25 to 30.41) and a maximum-to-background standardized uptake value ratio of 1.99 (range 1.06 to 14.42). Mean and median uptake values on <sup>68</sup>Ga labeled prostate specific membrane antigen positron emission tomography/computerized tomography (ie the maximum standardized uptake value or the maximum-to-background standardized uptake value ratio) were significantly higher for Gleason score 7 lesions than for Gleason score 6 or benign lesions (p <0.001). On ROC analysis a maximum standardized uptake value of 5.4 and a maximum-to-background standardized uptake value ratio of 2 discriminated clinically relevant prostate cancer with 100% overall sensitivity in each case, and 76% and 88% specificity, respectively.</p> <p>CONCLUSIONS:</p> <p>Our findings support the use of <sup>68</sup>Ga labeled prostate specific membrane antigen positron emission tomography/computerized tomography for primary detection of prostate cancer in a specific subset of men.</p>
Jet-images of R-parity violating neutralino decays (Background Dataset)
<p><strong>i</strong> enumerates the three jets in descending order of P_T<br><strong>obs</strong> enumerates the observables (E_T, Eh_T, Em_T, TrackP_T) where Eh and Em are hadronic and electromagnetic callorimeter depositions</p> <p>mass/Mass : Generator level neutralino mass<br>Jet/info<strong>i</strong> : \Delta R_1, \Delta R_2, P_T, \eta, \phi, M, M_{SD} with \Delta R_1 / R_2 are distances to the generator level neutralinos 1 and 2 and M_{SD} is the softdropped mass.<br>Jet/<strong>obs</strong>/values<strong>i</strong>: Values of depositions in the torch.sparse_coo_tensor format<br>Jet/<strong>obs</strong>/index<strong>i</strong>: Indices of depositions in the torch.sparse_coo_tensor format</p>
Jet-images of R-parity violating neutralino decays (Signal Dataset)
<p>$i enumerates the three jets in descending order of P_T<br>$obs enumerates the observables (E_T, Eh_T, Em_T, TrackP_T) where Eh and Em are hadronic and electromagnetic callorimeter depositions</p> <p>mass/Mass : Generator level neutralino mass<br>Jet/info$i : \Delta R_1, \Delta R_2, P_T, \eta, \phi, M, M_{SD} with \Delta R_1 / R_2 are distances to the generator level neutralinos 1 and 2 and M_{SD} is the softdropped mass.<br>Jet/$obs/values$i: Values of depositions in the torch.sparse_coo_tensor format<br>Jet/$obs/index$i: Indices of depositions in the torch.sparse_coo_tensor format</p>
Demo dataset for publication "Development of image analysis tool to evaluate Langerhans cell migration after exposure to isothiazolinones"
<p>This dataset consists of a QuPath project and two images that can be used to test the scripts produced by the publication </p> <p>"Development of image analysis tool to evaluate Langerhans cell migration after exposure to isothiazolinones"</p>
Dataset for "Muscle mass and Vitamin B6 are linked to negative body image in women with anorexia nervosa: a retrospective study."
<p>This is the dataset associated with the article "Muscle mass and Vitamin B6 are linked to negative body image in women with anorexia nervosa: a retrospective study."</p> <p>These data cannot be made publicly available because they include sensitive information, but they can be made available upon reasonable request of interested researchers to the Corresponding Author, who will forward a transfer agreement request to the relevant Ethical Committee.</p> <p>Requests should be addressed to Federica Scarpina (<a href="mailto:f.scarpina@auxologico.it">f.scarpina@auxologico.it</a>).</p>
Blastoid images dataset for classification
Open the record for dataset details and reuse information.
Dataset related to the article "Head to Head Comparison between Different 3-Dimensional Echocardiographic Rendering Tools in the Imaging of Percutaneous Edge-to-Edge Mitral Valve Repair"
<p>This record contains raw data related to the article "Head to Head Comparison between Different 3-Dimensional Echocardiographic Rendering Tools in the Imaging of Percutaneous Edge-to-Edge Mitral Valve Repair"</p> <p>MitraClip (MC) is the most common percutaneous treatment for severe mitral regurgitation<br> (MR). An accurate two-dimensional and three-dimensional echocardiographic (3DTEE) imaging is<br> mandatory for the optimal procedural result. Recently transillumination 3DTEE rendering (3DTr) has<br> been introduced integrating a virtual light source into the dataset and with the addition of glass effect<br> (3DGl) allows to adjust tissue transparency improving depth perception and anatomical structure<br> delineation in comparison with the standard 3DTEE (3DSt). The aim of this retrospective study in<br> 30 patients undergoing MC, was to compare 3DSt, 3DTr, and 3DGl in mitral valve (MV) evaluation<br> and procedural result assessment. 3DTEE acquisitions obtained before and after MC were processed<br> with 3DSt, 3DTr, and 3DGl rendering. Each reconstruction was scored for quality and for ability<br> to recognize MV anatomy, MR origin, clip position, dimension and grasping. Imaging quality was<br> judged good or optimal in 52%, 76%, and 96% in 3DSt, 3DTr, and 3DGl reconstructions respectively.<br> In 26/30 patients a diagnostic incremental value was found with 3DTr vs. 3DSt and in 15/26 with<br> 3DGl vs. 3DTr and 3DSt. Only 3DGl with perpendicular cropping of the clip allowed to visualize and<br> measure the grasped portion of each mitral leaflets. 3DTEE imaging during MC may be improved<br> by 3DTr and 3DGl providing a better evaluation of MV, of leaflet grasping and of residual MR jets<br> after MC.</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.