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.
328
datasets available to search
ShareScore release 0.9.0
Dataset results
328 results for “segmentation dataset”
Dataset related to article "Deep learning and atlas-based models to streamline the segmentation workflow of Total Marrow and Lymphoid Irradiation"
<p>This record contains raw data related to article “Deep learning and atlas-based models to streamline the segmentation workflow of Total Marrow and Lymphoid Irradiation"</p> <p>Abstract:</p> <p><strong>Purpose: </strong>To improve the workflow of Total Marrow and Lymphoid Irradiation (TMLI) by enhancing the delineation of organs-at-risk (OARs) and clinical target volume (CTV) using deep learning (DL) and atlas-based (AB) segmentation models.</p> <p><strong>Materials and Methods:</strong> Ninety-five TMLI plans optimized in our institute were analyzed. Two commercial DL software were tested for segmenting 18 OARs. An AB model for lymph node CTV (CTV_LN) delineation was built using 20 TMLI patients. The AB model was evaluated on 20 independent patients and a semi-automatic approach was tested by correcting the automatic contours. The generated OARs and CTV_LN contours were compared to manual contours in terms of topological agreement, dose statistics, and time workload. A clinical decision tree was developed to define a specific contouring strategy for each OAR.</p> <p><strong>Results: </strong>The two DL models achieved a median Dice Similarity Coefficient (DSC) of 0.84 [0.73;0.92] and 0.84 [0.77;0.93] across the OARs. The absolute median dose (Dmedian) difference between manual and the two DL models was 2% [1%;5%] and 1% [0.2%;1%]. The AB model achieved a median DSC of 0.70 [0.66;0.74] for CTV_LN delineation, increasing to 0.94 [0.94;0.95] after manual revision, with minimal Dmedian differences. Since September 2022, our institution has implemented DL and AB models for all TMLI patients, reducing from 5 to 2 hours the time required to complete the entire segmentation process.</p> <p><strong>Conclusion: </strong>DL models can streamline the TMLI contouring process of OARs. Manual revision is still necessary for lymph node delineation using AB models.</p> <p> </p> <p><strong>Statements & Declarations</strong></p> <p><strong>Funding:</strong> This work was funded by the Italian Ministry of Health, grant AuToMI (GR-2019-12370739).</p> <p><strong>Competing Interests:</strong> The authors have no conflict of interests to disclose.</p> <p><strong>Author Contributions:</strong> All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by D.D., N.L., L.C., R.C.B., D.L., and P.M. The first draft of the manuscript was written by D.D. and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.</p> <p><strong>Ethics approval:</strong> The study was conducted in accordance with the Declaration of Helsinki and approved by the Institutional Ethics Committee of IRCCS Humanitas Research Hospital (ID 2928, 26 January 2021). ClinicalTrials.gov identifier: NCT04976205.</p> <p><strong>Consent to participate: </strong>Informed consent was obtained from all individual participants included in the study.</p>
Dataset for segmentation of multiple histopathology findings in rat liver
<p>Dataset_HistoPathology_DILIscreening_KIT folder</p> <p>- Histology images from rat tox study in Korea Institute of Toxicology (KIT)</p> <p>- Dataset for detecting multiple findings and normal features such as infiltration, inflammation, fibrosis, necrosis, vacuolation, portal triad, or connective tissue to screen drug-induced liver injury. </p> <p>- Each folders include about 1000 images and a json file.</p> <p>- Images are 448 by 448 pixel jpg format and 20X microscopic magnification.</p> <p>- A json file has coordinate information about every image and prepared for segmentation algorithm training. </p> <p> </p> <p>CropSlideImages_for_Inference folder</p> <p>- 5 images for inference test.</p> <p>- Image info: 10752 by 10752 pixel, jpg format, 20X magnification </p> <p> </p> <p> </p>
Dataset related to the article "Reduced Cardiorenal Function Accounts for Most of the In-Hospital Morbidity and Mortality Risk Among Patients With Type 2 Diabetes Undergoing Primary Percutaneous Coronary Intervention for ST-Segment Elevation Myocardial Infarction"
<p>This record contains raw data related to the article "Reduced Cardiorenal Function Accounts for Most of the In-Hospital Morbidity and Mortality Risk Among Patients With Type 2 Diabetes Undergoing Primary Percutaneous Coronary Intervention for ST-Segment Elevation Myocardial Infarction"</p> <p><strong>ABSTRACT</strong> ST-segment elevation myocardial infarction (STEMI) patients with diabetes mellitus<br> (DM) have higher in-hospital mortality than those without. Since cardiac and renal<br> functions are the main variables associated with outcome in STEMI, we hypothesized<br> that this prognostic disparity may depend on a higher rate of cardiac and<br> renal dysfunction in DM patients.<br> RESEARCH DESIGN AND METHODS<br> We retrospectively analyzed 5,152 STEMI patients treated with primary angioplasty.<br> Left ventricular ejection fraction (LVEF) and estimated glomerular filtration rate<br> (eGFR) were evaluated at hospital admission. The primary end point was in-hospital<br> mortality. A composite of in-hospital mortality, cardiogenic shock, and acute kidney<br> injury was the secondary end point.<br> RESULTS<br> There were 879 patients (17%) with DM. The incidence of LVEF £40% (30% vs. 22%),<br> eGFR £60 mL/min/1.73m2 (27% vs. 18%), or both (12% vs. 6%) was higher (P < 0.001<br> for all comparisons) inDMpatients. In-hospital mortality was higher inDMpatients<br> than in non-DM patients (6.1% vs. 3.5%; P = 0.002), with an unadjusted odds ratio<br> (OR) of 1.81 (95% CI 1.31–2.49; P < 0.001). However, DM was no longer associated<br> with an increased mortality risk after adjustment for cardiac and renal function (OR<br> 1.03, 95% CI 0.68–1.56; P = 0.89). A similar behavior was observed for the secondary<br> end point, with an unadjusted OR for DM of 1.52 (95% CI 1.25–1.85; P < 0.001) and<br> an OR after adjustment for cardiac and renal function of 1.07 (95% CI 0.85–1.36;<br> P = 0.53).<br> CONCLUSIONS<br> The study indicates that the increased in-hospital mortality and morbidity of DM<br> patients with STEMI is mainly driven by their underlying cardiorenal dysfunction.</p>
Dataset related to the article "Iron deficiency in patients with ST-segment elevation myocardial infarction undergoing primary percutaneous coronary intervention"
<p>This record contains raw data related to the article "Iron deficiency in patients with ST-segment elevation myocardial infarction undergoing primary percutaneous coronary intervention"</p> <p><strong>ABSTRACT</strong> Background: Iron deficiency (ID) is a known co-morbidity and a potential therapeutic target in heart failure.<br> Whether ID is frequent also in ST-segment elevation acute myocardial infarction (STEMI) patients and is associated<br> with worse in-hospital outcomes has never been evaluated.<br> Methods: We defined ID as a serum ferritin b 100 μg/L or transferrin saturation b 20% at hospital admission.We<br> assessed the association between ID and the primary endpoint (a composite of in-hospital mortality and Killip<br> class ≥ 3). We explored the potential association between ID, circulating cell-free mitochondrial DNA<br> (mtDNA), and cardiac magnetic resonance (CMR) parameters.<br> Results: Four-hundred-twenty STEMI patients undergoing primary percutaneous coronary intervention (pPCI)<br> were included. Of them, 237 (56%) had ID. They had significantly higher admission high-sensitivity troponin<br> and mtDNA levels as compared to non-ID patients (145 ± 35 vs. 231 ± 66 ng/L, P b 0.001; 917 [404–1748] vs.<br> 1368 [908–4260] copies/μL; P b 0.003, respectively). A lower incidence of the primary endpoint (10% vs. 18%, P<br> =0.01) was observed in ID patients (adjusted OR 0.50 [95% CI 0.27–0.93]; P=0.02). At CMR (n=192), ID patients<br> had a similar infarct size (21±18 vs. 21±19 g; P=0.95), but a higher myocardial salvage index (0.56±<br> 0.30 vs. 0.43 ± 0.27; P = 0.002), and a smaller microvascular obstruction extent (3.6 ± 2.2 vs. 6.9 ± 3.9 g; P b<br> 0.001).<br> Conclusions: Iron deficiency is frequent in STEMI patients, it is coupled with mitochondrial injury, and, paradoxically,<br> with a better in-hospital outcome. This unexpected clinical result seems to be associated with a smaller<br> myocardial reperfusion injury. The mechanisms underlying our findings and their potential clinical implications<br> warrant further investigation.</p>
SPARK 2024: Datasets for Spacecraft Semantic Segmentation and Spacecraft Trajectory Estimation
<p>SPARK 2024 dataset is part of SPARK challenge aims to design data-driven approaches for Spacecraft Semantic Segmentation and Trajectory Estimation. SPARK 2024 dataset will utilize data synthetically simulated with a state-of-the-art rendering engine in addition to the data collected from the Zero-Gravity Laboratory (Zero-G Lab) facility at SnT – Interdisciplinary Center for Security, Reliability, and Trust, University of Luxembourg.</p> <p>Stream 1 – Spacecraft Semantic Segmentation intended for segmenting space objects to classify pixel values based on which part of the object they belong to.</p> <p>Stream 2 – Spacecraft Trajectory Estimation intended to leveraging the knowledge of temporal data to estimate the 6DoF pose of the spacecraft.</p> <h4>Request access</h4> <p>If you would like to request access to the dataset, Please visit <a href="https://cvi2.uni.lu/spark2024/">https://cvi2.uni.lu/spark2024/</a> to register and get access to dataset.</p>
Aerial Segmentation Dataset
<p>Contains 277 aerial images (extracted from Bing Maps) and their corresponding aerial segmentation (binary and colored). Segmentation is built automatically from segmentation data downloaded from OpenStreeMaps.</p> <p>Data was downloaded from 4 cities in the US, 4 in Europe, 1 in Latin America, and 8 rural areas in the US, totalling 277 pairs of images (251 urban, 26 rural), each 1280x1280 pixels.</p> <p>In total, there are 13 classes (building, water, natural, highway, park, dirt road, tree, beach, parking, construction, industrial, footway and grass).</p> <p>The datasheet for this dataset is also provided, according to the instructions by Gebru, T., Morgenstern, J., Vecchione, B., Vaughan, J. W., Wallach, H., Iii, H. D., & Crawford, K. (2021). Datasheets for datasets. Communications of the ACM, 64(12), 86-92. For more information, please refer to the PDF file.<br> </p>
Large IA Segmentation dataset
<p>This is the official Large IA (intracranial aneurysm) Segmentation dataset for our Patterns paper - Toward human intervention-free clinical diagnosis of intracranial aneurysm via deep neural network (<a href="https://doi.org/10.1016/j.patter.2020.100197">https://doi.org/10.1016/j.patter.2020.100197</a>). </p> <p>The internal dataset includes 1338 3D CTA images/1489 IAs from 6 institutions. The external dataset includes 138 3D CTA images/101 IAs from 2 institutions.</p> <p>We provides voxel-wise IA segmentation annotations and additional information (age, sex, whether ruptured...) for each CTA image.</p> <p>The dataset is only available for non-commercial purposes. Please provide the user's name, affiliation, supervisor and usage purpose. Please use the email account of your institution to send the request. If you find it useful in your research, please cite our paper:</p> <pre><code>@article{bo2021toward, title={Toward human intervention-free clinical diagnosis of intracranial aneurysm via deep neural network}, author={Bo, Zi-Hao and Qiao, Hui and Tian, Chong and Guo, Yuchen and Li, Wuchao and Liang, Tiantian and Li, Dongxue and Liao, Dan and Zeng, Xianchun and Mei, Leilei and others}, journal={Patterns}, volume={2}, number={2}, pages={100197}, year={2021}, publisher={Elsevier} }</code></pre> <pre> </pre>
Inter-Fetus Membrane Segmentation Dataset
<p>The dataset presented in this work included intra-operative frames from fetoscopy for Twin-to-Twin Transfusion Syndrome (TTTS) patients where inter-fetal membrane has been annotated.</p> <p>Dataset consists of annotated images from 20 procedures of 20 patients acquired in the actual clinical practice at Istituto Giannina Gaslini, Genova, Italy.</p> <p> </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.