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”
Detection of COVID-19 Infection from Routine Blood Exams with Machine Learning: a Feasibility Study
<p>This upload consists of the dataset employed in the publication "Detection of COVID-19 Infection from Routine Blood Exams with Machine Learning: a Feasibility Study". The paper was accepted for publication at Journal of Medical Systems (Springer), and a pre-print version is also available on MedRXiv and has been attached to the upload for further reference. If you decide to use or reference this dataset (or the related work) please cite the journal version (details will be added as soon as available).</p> <p>The dataset consists of 280 records of patients admitted to the San Raffaele Hospital (Milan, Italy), annotated with a collection of hematochemical values from routine blood exams (namely: white blood cells counts, and the platelets, CRP, AST, ALT, GGT, ALP, LDH plasma levels), and a target variable that describes COVID-19 positivity/negativity (in the target column, class 2 and class 1 can both be treated as COVID-19 positive patients)</p> <p> </p> <p>The abstract of the supporting publication follows:</p> <p> </p> <p><strong>Background</strong> - The COVID-19 pandemia due to the SARS-CoV-2 coronavirus, in its first 4 months since its outbreak, has to date reached more than 200 countries worldwide with more than 2 million confirmed cases (probably a much higher number of infected), and almost 200,000 deaths. Amplification of viral RNA by (real time) reverse transcription polymerase chain reaction (rRT-PCR) is the current gold standard test for confirmation of infection, although it presents known shortcomings: long turnaround times (3-4 hours to generate results), potential shortage of reagents, false-negative rates as large as 15-20%, the need for certified laboratories, expensive equipment and trained personnel. Thus there is a need for alternative, faster, less expensive and more accessible tests.</p> <p><strong>Material and methods</strong> - We developed two machine learning classification models using hematochemical values from routine blood exams (namely: white blood cells counts, and the platelets, CRP, AST, ALT, GGT, ALP, LDH plasma levels) drawn from 279 patients who, after being admitted to the San Raffaele Hospital (Milan, Italy) emergency-room with COVID-19 symptoms, were screened with the rRT-PCR test performed on respiratory tract specimens. Of these patients, 177 resulted positive, whereas 102 received a negative response.</p> <p><strong>Results</strong> - We have developed two machine learning models, to discriminate between patients who are either positive or negative to the SARS-CoV-2: their accuracy ranges between 82% and 86%, and sensitivity between 92% e 95%, so comparably well with respect to the gold standard. We also developed an interpretable Decision Tree model as a simple decision aid for clinician interpreting blood tests (even off-line) for COVID-19 suspect cases.</p> <p><strong>Discussion</strong> - This study demonstrated the feasibility and clinical soundness of using blood tests analysis and machine learning as an alternative to rRT-PCR for identifying COVID-19 positive patients. This is especially useful in those countries, like developing ones, suffering from shortages of rRT-PCR reagents and specialized laboratories. We made available a Web-based tool for clinical reference and evaluation. This tool is available at https://covid19-blood-ml.herokuapp.com.</p>
Datasets: New technologies in the mix: Assessing N-mixture models for abundance estimation using automated detection data from drone surveys
<p>These data set contains data from 11 surveys of radio-collared using remotely piloted aircraft systems (RPAS), thermal <br> imaging and automated detection.The MODELDEV .csv contains data points used to develop the modified Horvitz Thompson estimator models in the paper "New technologies in the mix: Assessing N-mixture models for abundance estimation using automated detection data from drone surveys" which is accepted into publication in the journal Ecology and Evolution as of 11/06/2020. The TESTING .csv contains data points used for model testing in in the same publication. </p>
RibFrac Dataset: A Benchmark for Rib Fracture Detection, Segmentation and Classification (Tuning/Validation Set)
<p>RibFrac dataset is a benchmark for developping algorithms on rib fracture detection, segmentation and classification. We hope this large-scale dataset could facilitate both clinical research for automatic rib fracture detection and diagnoses, and engineering research for 3D detection, segmentation and classification.</p> <p>This is the Tuning Set (a.k.a. Validation Set in machine learning terminology) of RibFrac dataset, including 80 CTs and the corresponding annotations. Files include:</p> <ol> <li>ribfrac-val-images.zip: 80 chest-abdomen CTs in NII format (nii.gz).</li> <li>ribfrac-val-labels.zip: 80 annotations in NII format (nii.gz).</li> <li>ribfrac-val-info.csv: labels in the annotation NIIs. <ul> <li>public_id: anonymous patient ID to match images and annotations.</li> <li>label_id: discrete label value in the NII annotations.</li> <li>label_code: 0, 1, 2, 3, 4, -1 <ul> <li>0: it is background</li> <li>1: it is a displaced rib fracture</li> <li>2: it is a non-displaced rib fracture</li> <li>3: it is a buckle rib fracture</li> <li>4: it is a segmental rib fracture</li> <li>-1: it is a rib fracture, but we could not define its type due to ambiguity, diagnosis difficulty, etc. Ignore it in the classification task. </li> </ul> </li> </ul> </li> </ol> <p> </p> <p>If you find this work useful in your research, please acknowledge the RibFrac project teams in the paper and cite this project as:</p> <p><em>Liang Jin, Jiancheng Yang, Kaiming Kuang, Bingbing Ni, Yiyi Gao, Yingli Sun, Pan Gao, Weiling Ma, Mingyu Tan, Hui Kang, Jiajun Chen, Ming Li. Deep-</em><em>Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet. EBioMedicine (2020). (<a href="https://doi.org/10.1016/j.ebiom.2020.103106">DOI</a>)</em></p> <p>or using bibtex</p> <p><em>@article{ribfrac2020,<br> title={Deep-Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet},<br> author={Jin, Liang and Yang, Jiancheng and Kuang, Kaiming and Ni, Bingbing and Gao, Yiyi and Sun, Yingli and Gao, Pan and Ma, Weiling and Tan, Mingyu and Kang, Hui and Chen, Jiajun and Li, Ming},<br> journal={EBioMedicine},<br> year={2020},<br> publisher={Elsevier}<br> }</em></p> <p> </p> <p>The RibFrac dataset is a research effort of thousands of hours by experienced radiologists, computer scientists and engineers. We kindly ask you to respect our effort by appropriate citation and keeping data license.</p> <p> </p> <p>This work is licensed under a <a href="http://creativecommons.org/licenses/by-nc/4.0/">Creative Commons Attribution-NonCommercial 4.0 International License</a>.</p>
RibFrac Dataset: A Benchmark for Rib Fracture Detection, Segmentation and Classification (Training Set Part 2)
<p>RibFrac dataset is a benchmark for developping algorithms on rib fracture detection, segmentation and classification. We hope this large-scale dataset could facilitate both clinical research for automatic rib fracture detection and diagnoses, and engineering research for 3D detection, segmentation and classification.</p> <p>Due to size limit of zenodo.org, we split the whole RibFrac Training Set into 2 parts; This is the Training Set Part 2 of RibFrac dataset, including 120 CTs and the corresponding annotations. Files include:</p> <ol> <li>ribfrac-train-images-2.zip: 120 chest-abdomen CTs in NII format (nii.gz).</li> <li>ribfrac-train-labels-2.zip: 120 annotations in NII format (nii.gz).</li> <li>ribfrac-train-info-2.csv: labels in the annotation NIIs. <ul> <li>public_id: anonymous patient ID to match images and annotations.</li> <li>label_id: discrete label value in the NII annotations.</li> <li>label_code: 0, 1, 2, 3, 4, -1 <ul> <li>0: it is background</li> <li>1: it is a displaced rib fracture</li> <li>2: it is a non-displaced rib fracture</li> <li>3: it is a buckle rib fracture</li> <li>4: it is a segmental rib fracture</li> <li>-1: it is a rib fracture, but we could not define its type due to ambiguity, diagnosis difficulty, etc. Ignore it in the classification task. </li> </ul> </li> </ul> </li> </ol> <p> </p> <p>If you find this work useful in your research, please acknowledge the RibFrac project teams in the paper and cite this project as:</p> <p><em>Liang Jin, Jiancheng Yang, Kaiming Kuang, Bingbing Ni, Yiyi Gao, Yingli Sun, Pan Gao, Weiling Ma, Mingyu Tan, Hui Kang, Jiajun Chen, Ming Li. Deep-</em><em>Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet. EBioMedicine (2020). (<a href="https://doi.org/10.1016/j.ebiom.2020.103106">DOI</a>)</em></p> <p>or using bibtex</p> <p><em>@article{ribfrac2020,<br> title={Deep-Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet},<br> author={Jin, Liang and Yang, Jiancheng and Kuang, Kaiming and Ni, Bingbing and Gao, Yiyi and Sun, Yingli and Gao, Pan and Ma, Weiling and Tan, Mingyu and Kang, Hui and Chen, Jiajun and Li, Ming},<br> journal={EBioMedicine},<br> year={2020},<br> publisher={Elsevier}<br> }</em></p> <p> </p> <p>The RibFrac dataset is a research effort of thousands of hours by experienced radiologists, computer scientists and engineers. We kindly ask you to respect our effort by appropriate citation and keeping data license.</p> <p> </p> <p>This work is licensed under a <a href="http://creativecommons.org/licenses/by-nc/4.0/">Creative Commons Attribution-NonCommercial 4.0 International License</a>.</p>
RibFrac Dataset: A Benchmark for Rib Fracture Detection, Segmentation and Classification (Training Set Part 1)
<p>RibFrac dataset is a benchmark for developping algorithms on rib fracture detection, segmentation and classification. We hope this large-scale dataset could facilitate both clinical research for automatic rib fracture detection and diagnoses, and engineering research for 3D detection, segmentation and classification.</p> <p>Due to size limit of zenodo.org, we split the whole RibFrac Training Set into 2 parts; This is the Training Set Part 1 of RibFrac dataset, including 300 CTs and the corresponding annotations. Files include:</p> <ol> <li>ribfrac-train-images-1.zip: 300 chest-abdomen CTs in NII format (nii.gz).</li> <li>ribfrac-train-labels-1.zip: 300 annotations in NII format (nii.gz).</li> <li>ribfrac-train-info-1.csv: labels in the annotation NIIs. <ul> <li>public_id: anonymous patient ID to match images and annotations.</li> <li>label_id: discrete label value in the NII annotations.</li> <li>label_code: 0, 1, 2, 3, 4, -1 <ul> <li>0: it is background</li> <li>1: it is a displaced rib fracture</li> <li>2: it is a non-displaced rib fracture</li> <li>3: it is a buckle rib fracture</li> <li>4: it is a segmental rib fracture</li> <li>-1: it is a rib fracture, but we could not define its type due to ambiguity, diagnosis difficulty, etc. Ignore it in the classification task. </li> </ul> </li> </ul> </li> </ol> <p> </p> <p>If you find this work useful in your research, please acknowledge the RibFrac project teams in the paper and cite this project as:</p> <p><em>Liang Jin, Jiancheng Yang, Kaiming Kuang, Bingbing Ni, Yiyi Gao, Yingli Sun, Pan Gao, Weiling Ma, Mingyu Tan, Hui Kang, Jiajun Chen, Ming Li. Deep-</em><em>Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet. EBioMedicine (2020). (<a href="https://doi.org/10.1016/j.ebiom.2020.103106">DOI</a>)</em></p> <p>or using bibtex</p> <p><em>@article{ribfrac2020,<br> title={Deep-Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet},<br> author={Jin, Liang and Yang, Jiancheng and Kuang, Kaiming and Ni, Bingbing and Gao, Yiyi and Sun, Yingli and Gao, Pan and Ma, Weiling and Tan, Mingyu and Kang, Hui and Chen, Jiajun and Li, Ming},<br> journal={EBioMedicine},<br> year={2020},<br> publisher={Elsevier}<br> }</em></p> <p> </p> <p>The RibFrac dataset is a research effort of thousands of hours by experienced radiologists, computer scientists and engineers. We kindly ask you to respect our effort by appropriate citation and keeping data license.</p> <p> </p> <p>This work is licensed under a <a href="http://creativecommons.org/licenses/by-nc/4.0/">Creative Commons Attribution-NonCommercial 4.0 International License</a>.</p>
Data for "Wave anomaly detection in wave buoy measurements"
<p>Data used for the production of figures in the manuscript "Wave anomaly detection in wave buoy measurements" submitted for review.</p>
List of the main marine and coastal habitats detected in Marine Protected Areas and Key Biodiversity Areas of countries around the Alboran Sea, with annotations on the year on which the habitat was listed or publications related on the habitats
<p>List of the main marine and coastal habitats detected in Marine Protected Areas and Key Biodiversity Areas of countries around the Alboran Sea, with annotations on the year on which the habitat was listed or publications related on the habitats. Biosph Res: Biosphera Reserve; MP: Management Plan; NA: Natural Area; NatP: National Park; NP: Natural Park; RCP: Réserve de Chasse Permanenten; RH: Permanent Reserve of Hunting; RN: Réserve Naturelle; SAC: Special Area of Conservation; SBEI: Sites of Biological and Ecological Interest; SCI: Site of Community Importance of Natura 2000; SPAMI: Specially Protected Areas of Mediterranean Importance; LIC: Lugar de Importancia Comunitaria; ZEC: Zona de Especial Conservación; ZEPIM: Zona Especialmente Protegida de Importancia para el Mediterráne; ASPIM: Aires Spécialement Protégées d’Importance Méditerranéenne; SIBE: Sites d’Intérêt Biologique et Ecologique</p>
The diurnal cycle of the horizontal wind field over complex terrain detected with coplanar Doppler lidar scans
<p>This data set contains a 24-h movie (21:00 UTC 23 July to 21:00 UTC 24 July) of the horizontal wind field in a horizontal plane of about 5 km x 5 km in size about 62 m above the city of Stuttgart in south-western Germany. The horizontal wind fields are retrieved from coplanar horizontal scans from three Doppler lidars positioned on opposing slopes and are available with 1-min temporal resolution and 100 m horizontal resolution. The data shows the diurnal cycle of the horizontal wind. During nighttime, downvalley wind establishes in the Neckar Valley and during daytime convective cells moving downstream are visible.<br> The measurements were conducted within the the framework of the Urban Climate under Change [UC]^2 program.</p>
Microfluidics system for the entrapment and detection of oocysts of Cryptosporidium
<p><em>Cryptosporidium</em> is an obligate intracellular protozoan parasite of great public health concern. Oocysts, the infectious form of <em>Cryptosporidium</em> species are ubiquitous in environmental sources such as soil and water all over the world and can stay viable up to six months. Several outbreaks of Cryptosporidiosis, a diarrheal illness in healthy and immunocompromised humans and in agriculturally important livestock species have been reported over the years owing to contaminated drinking water and recreational water supplies. Also, it has been a source of contaminants in salad vegetables and other raw leafy fruits and vegetables. A method for rapid monitoring of oocysts of <em>Cryptosporidium</em> species in water treatment plants and outside eateries will help to protect the public from incidences of Cryptosporidiosis. In the present study, Microfluidics device has been developed to entrap and detect the oocysts from environmental samples. The prepared device entraps and detects the oocysts at Micron level. The entire device is established on small chip sized area (2 cm x 2cm) utilizing less volume of samples and reagents. The device is cost effective and rapid in its action. Oocysts are detected by using FITC-labeled antibodies. The sensitivity of detection method is 35 %. Efficiency of trapping of positive oocysts is 0.078 % and oocysts from sample is 0.47% .</p>
Supplementary material 4 from: Rusch JC, Mojžišová M, Strand DA, Svobodová J, Vrålstad T, Petrusek A (2020) Simultaneous detection of native and invasive crayfish and Aphanomyces astaci from environmental DNA samples in a wide range of habitats in Central Europe. NeoBiota 58: 1-32. https://doi.org/10.3897/neobiota.58.49358
Table S4
Supplementary material 2 from: Rusch JC, Mojžišová M, Strand DA, Svobodová J, Vrålstad T, Petrusek A (2020) Simultaneous detection of native and invasive crayfish and Aphanomyces astaci from environmental DNA samples in a wide range of habitats in Central Europe. NeoBiota 58: 1-32. https://doi.org/10.3897/neobiota.58.49358
Table S2
Supplementary material 3 from: Rusch JC, Mojžišová M, Strand DA, Svobodová J, Vrålstad T, Petrusek A (2020) Simultaneous detection of native and invasive crayfish and Aphanomyces astaci from environmental DNA samples in a wide range of habitats in Central Europe. NeoBiota 58: 1-32. https://doi.org/10.3897/neobiota.58.49358
Table S3
Supplementary material 1 from: Rusch JC, Mojžišová M, Strand DA, Svobodová J, Vrålstad T, Petrusek A (2020) Simultaneous detection of native and invasive crayfish and Aphanomyces astaci from environmental DNA samples in a wide range of habitats in Central Europe. NeoBiota 58: 1-32. https://doi.org/10.3897/neobiota.58.49358
Table S1
Public Dataset for the Paper "Using Hybrid Bayesian Networks to Detect Audience Behaviour Changes in Youtube"
<p>This is the dataset used in the production of the paper "Using Hybrid Bayesian Networks to Detect Audience Behaviour Changes in Youtube" to be published in the EMSS 2020. Official site: http://www.msc-les.org/conf/emss2020/</p>
yolokamon v1.0 A Yolov5 Japanese Kamon detection Model
<p>A Yolov5 Japanese Kamon detection Model.</p>
On-site plant pathogen detection methods and introduction to microfluidics
<p>On June 24, 2020, IPANEMA organized the fourth Scientific online lecture (SOL4). The lesson was held by Dr. Cor Schoen from <a href="https://www.wur.nl/">Wageningen University & Research</a>, who brought us closer to different possible approaches for pathogen detection on the field.</p>
LiaoSteve/Trash-Dataset-and-object-detection: Trash-Dataset-and-object-detection
<p>Create my trash dataset and use hexacopter to detect trash pollution with YOLOV3.</p> <pre><code>Trash dataset : 1. bottle 2. bag 3. plastic_bag YOLOV3 weight : 1. anchor.txt 2. classes.txt 3. weight.h5 </code></pre>
Non-detection of radio emissions from Titan lightning by Cassini RPWS
<p>Supplementary material with list of Titan flybies (Excel table) for publication "Non-detection of radio emissions from Titan lightning by Cassini RPWS" by Fischer et al., submitted to JGR-Planets. Additionally, there is a Matlab file which can be run to produce the figures of this paper (titanflybies.dat needs to be in same directory).</p>
Data from: Factors affecting carcass detection at wind farms using dogs and human searchers
<p>1. The use of detection dogs to effectively monitor bird and bat fatalities at wind farms is becoming increasingly popular. All studies to date agree that dogs outperform human searchers at finding bird and bat carcasses around wind turbines; however, it remains unclear how particular conditions during the search may influence carcass detection.</p> <p>2. We investigate the effect of carcass size, habitat characteristics and weather conditions on carcass detection probability, for both dogs and humans, using data from the monitoring program of a wind farm in Spain.</p> <p>3. A generalized linear model reveals a high performance of dogs (~80% detection probability), with no clear influence of any of the variables analysed. Humans, on the contrary, were markedly affected by the size of the carcass and to some extent, by the vegetation structure. Humans performed poorly at detecting small carcasses (~20% detection probability), more so in dense vegetation.</p> <p>4. Synthesis and applications. Our results provide evidence that dogs perform at a high level under a wide range of environmental conditions. They are particularly well-suited for the monitoring of fatalities of small, rare or inconspicuous species in cluttered environments. Humans, by contrast, are very poor at detecting all but the largest carcasses.16-Jun-2020</p>
Noninvasive fecal sampling in Itatiaia National Park, Brazil: wild mammal identification and parasite detection
<p class="CAPA3"><b>Background</b>: Noninvasive collection of feces is a cost-effective strategy for monitoring free-living wild mammals. The aim of this study was to search for carnivore and artiodactyl species and investigate the gastrointestinal parasites in their feces, in Itatiaia National Park, Brazil.</p> <p class="CAPA3"><b>Methodology/Main Findings:</b> Between 2017 and 2018, feces from carnivores and artiodactyls were collected along trails in the park. Host species were identified from these feces through macroscopic and trichological examination and through molecular biology using mitochondrial gene fragments. To investigate parasites, the Faust, Lutz and modified Ritchie and Sheather techniques and enzyme immunoassays were used to detect <i>Cryptosporidium</i> sp. antigens. A total of 244 stools were collected in three regions of the park. The species identified were <i>C. brachyurus</i> (39.7%), <i>L. guttulus</i> (21.3%), <i>C. familiaris</i> (5.3%), <i>C. thous</i> (0.8%), <i>Puma</i> <i>yagouaroundi</i> (0.8%), <i>L. pardalis</i> (0.4%), <i>P</i>. <i>concolor</i> (0.4%) and <i>S. scrofa</i> (4.9%). The overall positivity for parasites was 81.1%. Helminths were more frequently detected in carnivore feces (70.9%), especially eggs of the family Ascarididae and <i>Toxocara</i> sp. Protozoa presented higher frequency in artiodactyl feces (87.1%), especially coproantigens of<i> Cryptosporidium</i> sp. This zoonotic protozoon was detected in eight mammal species, including one that may be invasive: animals from crossbreeding of domestic pig with wild boar. High values for parasite structural richness (R'), Shannon (H') and Simpson (D) parasite diversity indices were observed, especially in the feces of <i>C. brachyurus</i> (R' = 12, H' = 2.2761, D = 0.887). Significant differences in parasite diversity were observed between <i>C. brachyurus </i>and <i>C. familiaris</i>; and between <i>C. brachyurus</i> and <i>S. scrofa</i> (pooled t test = 0.01 and 0.03, respectively). The highest values for parasite similarity (Sorensen test ≥ 0.8) were found among species that are taxonomically close, such as <i>C. brachyurus</i> and <i>L. guttulus</i>.</p> <p class="CAPA3"><b>Conclusions/Significance</b>: This was the first parasitological survey on carnivore and artiodactyl feces collected noninvasively in Brazil. It enabled animal identification through correlations using three techniques and diagnosis of highly frequent parasite structures that can infect these animals.</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.