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.
9,302
datasets available to search
ShareScore release 0.9.0
Dataset results
9,302 results for “DETECT”
Detecting and stabilizing measurement-induced symmetry-protected topological phases in generalized cluster models
<p>This dataset contains the code and the data used for the corresponding publication.</p>
Supplementary Data for "Detection of peptide segments protruding from the MHC-I binding groove"
Open the record for dataset details and reuse information.
Dataset of Annotated Oral Cavity Images for Oral Cancer Detection
<h1>Citation</h1> <p><strong>When using this resource, please cite the original publication:</strong></p> <p><a href="https://doi.org/10.1016/j.oraloncology.2024.106946">N.S. Piyarathne, S.N. Liyanage, R.M.S.G.K. Rasnayaka, P.V.K.S. Hettiarachchi, G.A.I. Devindi, F.B.A.H. Francis, D.M.D.R. Dissanayake, R.A.N.S. Ranasinghe, M.B.D. Pavithya, I.B. Nawinne, R.G. Ragel, R.D. Jayasinghe, “A comprehensive dataset of annotated oral cavity images for diagnosis of oral cancer and oral potentially malignant disorders,” Oral Oncology, vol. 156, p. 106946, 2024</a>.</p> <p>Available at: <a href="https://doi.org/10.1016/j.oraloncology.2024.106946">https://doi.org/10.1016/j.oraloncology.2024.106946</a></p> <h1>Overview</h1> <p>The dataset consists of 3,000 high-quality images of oral cavities taken with mobile phone cameras from the Sri Lankan population. The images are categorized into healthy, benign, oral potentially malignant disorders (OPMD), and oral cancer (OCA) by domain experts. Each image contains annotations for oral cavity and lesion boundaries in COCO format. Additionally, patient metadata, such as age, sex, diagnosis, and risk factors like smoking, alcohol consumption, and betel quid chewing, is included in the meta-data files. The dataset contains the following files: </p> <ul> <li><strong>Images.zip</strong>: Folder of oral cavity images.</li> <li><strong>Annotation.json</strong>: Annotations for the images provided in the JSON (JavaScript Object Notation) file.</li> <li><strong>Imagewise_data.csv</strong>: File including the image ID, category, clinical diagnosis, and the number of annotated regions for each image.</li> <li><strong>Patientwise_data.csv</strong>: File containing patient-level metadata, including age, sex, and total image count per patient. Additionally, it includes binary indicators for risk factors such as smoking, chewing betel quid, and alcohol consumption.</li> </ul> <h1>Request Access</h1> <p>You need to satisfy these terms and conditions in order for this request to be accepted:</p> <ol> <li>Any request for access must be made through a Zenodo account associated with an official affiliation email address (e.g., institution, organization).</li> <li> <p><strong>The following details are required as the request message:</strong></p> <ul> <li>A brief description of the intended use of the dataset, outlining the purpose of their study (maximum 250 words).</li> <li> <p>Principal Investigator’s name and affiliation.</p> </li> <li> <p>Principal investigator’s page on the affiliation’s official website.</p> </li> </ul> </li> <li> <p>You may use this work <strong>only for non-commercial purposes</strong>. Any use intended for commercial gain or profit is strictly prohibited.</p> </li> <li> <p>Proper credit must be given to the creator by citing the original article associated with this dataset. </p> </li> <li> <p>No modifications, derivatives, or adaptations of this work are allowed.</p> </li> </ol> <p>Requests that adhere to the terms and conditions will be processed within 2-3 working days.</p> <h1>Authors' Publications</h1> <ol> <li> <p>A comprehensive dataset of annotated oral cavity images for diagnosis of oral cancer and oral potentially malignant disorders. DOI: <a href="https://doi.org/10.1016/j.oraloncology.2024.106946">10.1016/j.oraloncology.2024.106946</a></p> </li> <li> <p>Multimodal Deep Convolutional Neural Network Pipeline for AI-Assisted Early Detection of Oral Cancer. DOI: <a href="https://ieeexplore.ieee.org/document/10664507">10.1109/ACCESS.2024.3454338</a></p> </li> </ol>
Apple images for plant disease detection
Open the record for dataset details and reuse information.
Dataset of the Floating Objects Detection Notebook
<p>This dataset contains the data used in the notebook "Detecting floating objects using Deep Learning and Sentinel-2 imagery", published in the ocean modelling section of The Environmental Data Science Book.</p>
in-Vehicle Face Presentation Attack Detection (VFPAD)
<p><strong>Description</strong></p> <p>The in-Vehicle Face Presentation Attack Detection (VFPAD) dataset consists of 4046 bona-fide recordings from 40 subjects, and 1790 attack presentation videos from a total of 89 PAIs (presentation attack instruments). These presentations have been captured using an NIR camera (940 nm) placed on the steering wheel of the car, while NIR illuminators have been fixed on both front pillars (adjacent to the wind-shield) of the car. The bona-fide videos represent 24 male and 16 female subjects of various ethnicities. The PAI species used to construct this dataset include photo-prints, digital displays (for replay attacks), rigid 3D masks, and flexible 3D masks made of silicone.</p> <p> </p> <p><strong>Data Collection</strong></p> <p>The videos comprising this dataset represent bona-fide and attack presentations under a range of variations:</p> <ul> <li>Environmental variations: presentations have been recorded in four sessions, each under different environmental conditions (outdoor sunny; outdoor cloudy; indoor dimly-lit; and indoor brightly-lit)</li> <li>Different scenarios: bona-fide presentations for each subject have been captured with variety of appearances: with/without glasses, with/without hat, etc.</li> <li>Illumination variations: two illumination conditions have been used: ‘uniform’ (both NIR illuminators switched on), and ‘non-uniform’ (only the left NIR-illuminator switched on), and</li> <li>Pose variations: two poses (‘angles’) have been used: ‘front’: the subject looks ahead at the road; and ‘below’: subject looks straight into the camera.</li> </ul> <p> </p> <p><strong>Citation</strong></p> <p>If you use the dataset, please cite the following publication:</p> <p>@article{IEEE_TBIOM_2021,<br> author = {Kotwal, Ketan and Bhattacharjee, Sushil and Abbet, Philip and Mostaani, Zohreh and Wei, Huang and Wenkang, Xu and Yaxi, Zhao and Marcel, S\'{e}bastien},<br> title = {Domain-Specific Adaptation of CNN for Detecting Face Presentation Attacks in NIR},<br> journal = {IEEE Transactions on Biometrics, Behavior, and Identity Science},<br> publisher = {{IEEE}},<br> year={2022},<br> volume={4},<br> number={1},<br> pages={135--147},<br> doi={10.1109/TBIOM.2022.3143569}<br> }</p>
The chronometry of symmetry detection in the lateral occipital (LO) cortex
<p>We used a chronometric transcranial magnetic stimulation (TMS) approach to study at which specific time window the lateral occipital (LO) cortex is causally involved in symmetry encoding. Healthy individuals were presented with a series of dot configurations and instructed to judge whether they were symmetric or not while receiving a double pulse of TMS over either the rLO or the vertex (baseline) at different time windows. In the present dataset mean accuracy scores (expressed as percentage of correct responses) and mean response time for correct response (expressed in millisecond) are reported for each participant.</p> <p>The results show that LO is causally involved in symmetry perception in two distinct time windows: between 130-170ms and between 210-250ms from the target onset, thus providing a causal temporal link between LO and well-known ERP components related to symmetry.</p>
ECG-based score estimates the probability to detect Fabry Disease cardiac involvement
<p>Figliozzi S, Camporeale A, Boveri S, Pieruzzi F, Pieroni M, Lusardi P, Spada M, Mignani R, Burlina A, Graziani F, Pica S, Tondi L, Bernardini A, Chow K, Namdar M, Lombardi M. ECG-based score estimates the probability to detect Fabry Disease cardiac involvement. Int J Cardiol. 2021 Sep 15;339:110-117. doi: 10.1016/j.ijcard.2021.07.022. Epub 2021 Jul 16. PMID: 34274410.</p> <p>Abstract</p> <p><strong>Objectives: </strong>To elaborate an ECG-based nomogram estimating the probability to detect cardiac involvement by cardiac magnetic resonance (CMR) in Fabry Disease (FD).</p> <p><strong>Methods: </strong>119 FD patients and 26 healthy controls underwent ECG and CMR. Test (n = 88, 60%) and validation cohorts (n = 57, 40%) were randomly derived. Cardiac involvement was defined as the presence of low myocardial T1 value, a CMR-surrogate of myocardial glycosphingolipid storage. ECG changes associated with low T1 value were identified in the test cohort, included in the nomogram and then tested in the validation cohort.</p> <p><strong>Results: </strong>Sokolow-Lyon index (AUC = 0.769), ratio between P-wave and PR-segment durations (Pwave/PRsegment) (AUC = 0.778), QRS duration (AUC = 0.703), QT (AUC = 0.769) duration were independently associated with the presence of low T1 on CMR at multivariate analysis. An ECG-based nomogram including these four parameters was accurate in identifying patients with CMR evidence of glycosphingolipid storage (c-index of the derived-nomogram = 0.90 in the test group; 0.81 in the validation group).</p> <p><strong>Conclusion: </strong>We propose a practical ECG-based nomogram accurately estimating the probability to detect low T1 values by CMR in FD patients. The application of this tool in clinical practice could improve early detection of FD cardiac involvement.</p>
Dataset related to article "Subpopulations of Circulating Cells with Morphological Features of Malignancy Are Preoperatively Detected and Have Differential Prognostic Significance in Non-Small Cell Lung Cancer "
<p>This record contains raw data related to article “Subpopulations of Circulating Cells with Morphological Features of Malignancy Are Preoperatively Detected and Have Differential Prognostic Significance in Non-Small Cell Lung Cancer"</p> <p><strong>Background: </strong> Non-small cell lung cancer (NSCLC) frequently presents when surgical intervention is no longer feasible. Despite local treatment with curative intent, patients might experience disease recurrence. In this context, accurate non-invasive biomarkers are urgently needed. We report the results of a pilot study on the diagnostic and prognostic role of circulating tumor cells (CTCs) in operable NSCLC.</p> <p><strong>Methods: </strong> Blood samples collected from healthy volunteers (<em>n</em> = 10), nodule-negative high-risk individuals enrolled in a screening program (<em>n</em> = 7), and NSCLC patients (<em>n</em> = 74) before surgery were analyzed (4 mL) for the presence of cells with morphological features of malignancy enriched through the ISET<sup>®</sup> technology.</p> <p><strong>Results: </strong> CTC detection was 60% in patients, while no target cells were found in lung cancer-free donors. We identified single CTCs (sCTC, 46%) and clusters of CTCs and leukocytes (heterotypic clusters, hetCLU, 31%). The prevalence of sCTC (sCTC/4 mL ≥ 2) or the presence of hetCLU predicted the risk of disease recurrence within the cohort of early-stage (I-II, <em>n</em> = 52) or advanced stage cases (III-IVA, <em>n</em> = 22), respectively, while other tumor-related factors did not inform prognosis.</p> <p><strong>Conclusions: </strong> Cancer cell hematogenous dissemination occurs frequently in patients with NSCLC without clinical evidence of distant metastases, laying the foundation for the application of cell-based tests in screening programs. CTC subpopulations are fine prognostic classifiers whose clinical validity should be further investigated in larger studies.</p>
Clustering has a meaning: optimization of angular similarity to detect geometric anomalies in geological terrains - Input and processed data.
<p>This companion dataset relates to the manuscript "<strong>Clustering has a meaning: optimization of angular similarity </strong></p> <p><strong>to detect geometric anomalies in geological terrains</strong>", by</p> <p>Michał P. Michalak, Lesław Teper, Florian Wellmann, Jerzy Żaba, Krzysztof Gaidzik, Marcin Kostur, Yuriy P. Maystrenko, Paulina Leonowicz</p> <p>The archive contains the input and processed data. The input data contains XYZ coordinates of points documenting the investigated interfaces. The output files contains calculated orientations and coordinates of vectors. The output files can be processed in RStudio.</p>
Detection results of NMC particles in composite battery cathodes
<p>This dataset shows more examples of the NMC particles detection overlayed with the original images in composite battery cathodes.</p> <pre><code>@journal{li2022networkevolution, title={Dynamics of particle network in composite battery cathodes}, author={Li, Jizhou and Sharma, Nikhil and Jiang, Zhisen and Yang, Yang and Monaco, Federico and Xu, Zhengrui and Hou, Dong and Ratner, Daniel and Pianetta, Piero and Cloetens, Peter and Lin, Feng and Zhao, Kejie and Liu, Yijin}, year={2022}, journal={Science} }</code></pre>
Data for solid waste detection in Medellín.
<p>Accuracy Assessment of classifications of the 25 study sites of Medellín. Variables included: Building presence, Garbage type, segmentation factors, compactness value, User Accuracy, and Producer Accuracy for every class. </p> <p>Accuracy Assessment of the segmentation tests for each combination of segmentation values, for AOIs tested: 1, 6, 14, 17, 25. Variables included: segmentation factors, area of training segment [m2], area of intersection with reference data [m2], overSegmentation, underSegmentation, Area Fit Index, Root Square Mean, Quality Rate. </p> <p>Rate of segments being non squares for AOIs tested: 1, 6, 14, 17, 25.</p>
MuSe-Humor: Humor Detection Sub-Challenge (MuSe 2022)
<p><strong>Description</strong>: Predicting the presence of humor in football press conference recordings. Available modalities: audio and video, transcriptions.</p> <p><strong>Labels</strong>: windows of 2 seconds are given a binary label, indicating presence and absence of humor. 9 human annotators labelled each video.</p> <p><strong>Dataset</strong>: MuSe-Humor is based on the novel Passau-Spontaneous Football Coach Humor (Passau-SFCH) dataset. It includes press conference recordings of 10 different German Bundesliga football coaches collected in 2017. The data provided here only includes segments in which the respective coach is speaking. The training data set contains recordings of 4 coaches, development and test data each contain recordings of 3 coaches.</p> <p><strong>Change in Version 1.1</strong>: we added the manually corrected transcriptions and BERT features based on them.</p> <p><strong>General</strong>: The 3rd Multimodal Sentiment Analysis Challenge and Workshop (MuSe) 2022 adresses research questions that are of interest to affective computing, machine learning and multimodal signal processing communities and encourages a fusion of their disciplines. The goal of the MuSe workshop and challenge is to gain new insights into the merits of each of the core modalities and to serve as a stimulating environment for the development and evaluation of multimodal affect recognition approaches.</p>
SPARK 2022 Dataset : Spacecraft Detection and Trajectory Estimation
<p>SPARK2022 Challenge aims to design data-driven approaches for spacecraft detection and trajectory estimation. SPARK will utilise data synthetically simulated with a state-of-the-art rendering engine in addition to data collected from the Zero-Gravity Laboratory (Zero-G Lab) facility at the University of Luxembourg.</p> <p>Stream 1 – Spacecraft Detection</p> <p>Detecting space objects: localize and classify the object by estimating its bounding box and label.</p> <p>Stream 2 – Spacecraft Trajectory Estimation</p> <p>Leveraging the knowledge of temporal data to estimate the 6DoF pose of the spacecraft.</p> <p> </p>
Visual Function Score: A New Clinical Tool to Assess Visual Function and Detect Visual Disorders in Children
<p>The database contains in the first sheet the raw data derived from the administration of the Visual Function Score (VFS) to a sample of 100 visually impaired children. VFS is a quantitative tool conceived for the assessment of visual functions in children and is thoroughly described in the article.</p> <p>For each item of the VFS, the clinicians assigned a score according to the instructions provided with the template in the original article. The total score of a subject is defined as the weighted sum of the 51 items of the second section (columns L-BJ of the spreadsheet) which is normalized to obtain a score from 0 to 100. The scoring system is described in the second sheet (‘encoding’) together with the meaning of the items. </p>
Comparison of two RNA extraction methods for the molecular detection of SARS-CoV-2 from nasopharyngeal swab samples
<p>The database includes the raw data of the article “Comparison of two RNA Extraction Methods for the Molecular Detection of SARS-CoV-2 from nasopharyngeal swab samples”.</p> <p>Aim of this work was to compare a two commercially available kit for viral RNA extraction from human swab samples that differ mainly for time consuming (9 min. vs 35 min.) in order to improve SARS-CoV-2 diagnostic workflow.</p> <p>The database contains the data obtained by the following evaluations:</p> <p>a) RNA analysis for the evaluation of quality and quantity by nanodrop instrument</p> <p>b) Real Time PCR analysis of SARS-CoV-2 genes and internal control.</p> <p>The two procedures evaluated gave similar analytical results in terms of extracted RNA analysis and Real Time PCR data for gene expression.</p>
Dataset: Understanding and Detecting Hateful Content using Contrastive Learning
<p> </p> <p>This is the dataset released with the <a href="https://arxiv.org/abs/2201.08387">paper</a> titled: "<strong>Understanding and Detecting Hateful Content using Contrastive Learning</strong>".</p> <p>We release our dataset in four CSV files. These files contain the textual and visual dataset and the textual and visual ground truth we obtained after our manual annotations. For a detailed description of every <strong><em>column </em></strong>in the CSV structure, along with the type of the <strong><em>value</em></strong>, please read the readme.pdf file provided with this dataset.</p> <p>The images are stored in the zip files. </p> <p>If you find our dataset useful, please cite our paper:</p> <pre><code>@inproceedings{gonzalez2023understanding, title={Understanding and Detecting Hateful Content using Contrastive Learning}, author={Gonz{\'a}lez-Pizarro, Felipe and Zannettou, Savvas}, booktitle={17th International AAAI Conference On Web And Social Media (ICWSM), 2023}, year={2023} } </code></pre> <p>In case of questions, please do not hesitate to contact us: felipegp[at]cs.ubc.ca (<a href="https://gonzalezf.github.io">https://gonzalezf.github.io</a>)</p>
Dataset for "Analytical and clinical performances of seven direct detection assays for SARS-CoV-2"
<p>This dataset represent raw data for the unpublished article "Analytical and clinical performances of seven direct detection assays for SARS-CoV-2".</p>
Anomaly Detection in Semiconductor Wafer Fabrication Using Stream Processing Systems: A Case Study - Dataset
Open the record for dataset details and reuse information.
Dataset for "The Good, the Bad and the Bait: Detecting and Characterizing Clickbait on YouTube"
<p>This is the dataset used for the research "The Good, the Bad and the Bait: Detecting and Characterizing Clickbait on YouTube", with DOI: <a href="http://10.1109/SPW.2018.00018">10.1109/SPW.2018.00018</a>.</p> <p>The dataset consists of three files:</p> <p>1. groundtruth.json: This is the groundtruth dataset. We have 3443 manually annotated videos (we manually annotated more after the acceptance of the paper), and 17,648 videos that were obtained from channels that post clickbait or not. You can distinguish the method of annotation by observing the field "comments" in "clickbaitClassification" (the ones that have the comment "channels" are the ones obtained from the channels).</p> <p>2. videos.json: Contains the data for 206K videos that were obtained as described in the paper.</p> <p>3. predictions.json: It contains the mapping between the video id and the probability of our classifier. In our paper, we treat a video as clickbait if the probability is larger than 0.5.</p> <p> </p> <p>The related software produced for this study may be found <a href="https://zenodo.org/record/3405484#.XXk7bigzaUk">here</a>.</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.