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.
944
datasets available to search
ShareScore release 0.9.0
Dataset results
944 results for “Edema”
Diabetic Macular Edema VQA Dataset
<p>Medical VQA dataset built from the <a href="https://ieee-dataport.org/open-access/indian-diabetic-retinopathy-image-dataset-idrid">IDRiD</a> and <a href="https://www.adcis.net/en/third-party/e-ophtha/">eOphta</a> datasets. The dataset contains both healthy and unhealthy fundus images. For each image, a set of pre-defined questions is generated, including questions about regions (e.g. are there hard exudates in this region?), for which an associated mask denotes the location of the region.</p> <p>The motivation for this dataset includes the lack of public medical VQA datasets with related questions. In our dataset, questions are related because there is a high-level question about the DME grade of the image, and associated low-level questions that can lead to the answer of the high-level question. This allows to study the consistency of a VQA model i.e. how often the model produces contradictory answers to questions about a given image. Questions about regions are also a novel feature of this dataset.</p> <p>The dataset can be used for general VQA purposes, and also for the more specific purpose of consistency improvement.</p> <p>Number of images : Train: 433 Val: 112 Test: 134</p> <p>Number of QA pairs: Train: 9779 Val: 2380 Test: 1311</p> <p>More details can be found <a href="https://github.com/sergiotasconmorales/consistency_vqa/blob/master/DATA.md">here</a>.</p> <p>If you use this dataset, please make sure you cite <a href="https://arxiv.org/abs/2206.13296">our paper</a>:</p> <p><em>@inproceedings{tascon2022consistency,<br> title={Consistency-Preserving Visual Question Answering in Medical Imaging},<br> author={Tascon-Morales, Sergio and Márquez-Neila, Pablo and Sznitman, Raphael},<br> booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},<br> pages={386--395},<br> year={2022},<br> organization={Springer}<br> }</em></p> <p>Do you need annotations about logical relations? No problem; check out our <a href="https://zenodo.org/record/7777849">DME VQA dataset with logical relations</a>.</p>
Dataset for Detection and Segmentation of the Radiographic Features of Pulmonary Edema
<p><strong>Objectives:</strong> This comprehensive dataset is well suited for training, evaluating, and using machine learning models to detect, segment, and analyze radiological features associated with pulmonary edema in chest X-ray images.</p> <p><strong>Description:</strong> This dataset consists of a collection of chest X-rays extracted from the <a href="https://physionet.org/content/mimic-cxr-jpg/2.0.0/" target="_blank" rel="noopener">MIMIC database</a>, carefully collected at the Beth Israel Deaconess Medical Center. In total, it comprises 1000 chest X-rays obtained from 741 patients with features suggestive of edema. These X-rays were carefully selected for manual annotation. The annotations are rich and detailed, covering specific radiological features commonly associated with pulmonary edema, including cephalization, Kerley lines, pleural effusions, bat wings, and infiltrates. The dataset includes a wide variety of radiological features, with a total of 4263 annotations (<em>Table 1</em>). Furthermore, each chest radiograph is thoughtfully assigned a severity category, categorizing it as "no edema", "vascular congestion", "interstitial edema", or "alveolar edema".</p> <p><strong>Annotation Method:</strong> The annotation process was meticulously performed by a highly qualified clinician with over 10 years of radiology experience, utilizing both frontal and lateral views for each chest X-ray study. Cephalization and Kerley lines were delineated using polylines, while other features were delineated using binary masks. This methodological approach was carefully chosen to provide a comprehensive data set that would ensure accuracy in subsequent analyses and label assignments. </p> <p>Notably, all features are represented as bounding boxes, meticulously defined by their respective upper-left (x1; y1) and lower-right (x2; y2) corners. In addition, selected features are provided with masks encoded in base 64 format. To facilitate seamless decoding, we provide a conversion script called "mask_converter.py" that allows the transformation of encoded masks into a versatile numpy array format. This feature improves the usability of the dataset for precise analysis and deep learning applications.</p> <p><strong>Datasets:</strong></p> <ol> <li><strong>SLY dataset:</strong> The dataset contains chest X-ray images labeled by clinicians, including both stacked frontal and lateral images. We obtained this dataset by annotating it on the <a href="https://supervisely.com/" target="_blank" rel="noopener">Supervisely platform</a>, and it is stored in JSON and PNG formats.</li> <li><strong>Source dataset:</strong> The dataset is a transformed version of the SLY dataset. In this dataset, all annotations are consolidated into a single spreadsheet, and only frontal view images are represented.</li> <li><strong>Processed dataset: </strong>The dataset focuses exclusively on the lung area for analysis, as other areas surrounding the lung typically contain extraneous information that clinicians do not use in their decision-making process.</li> <li><strong>COCO dataset:</strong> A collection of subsets prepared in the <a href="https://towardsdatascience.com/how-to-work-with-object-detection-datasets-in-coco-format-9bf4fb5848a4" target="_blank" rel="noopener">COCO format</a> and suitable for training and testing. It includes subsets for each feature and for all features evaluated in this study.</li> </ol> <div> <p><strong>Access to the Study:</strong> Further information about this study, including curated source code, dataset details, and trained models, can be accessed through the following repositories:</p> <ul> <li><strong>Source code:</strong> <a href="https://github.com/ViacheslavDanilov/edema_quantification" target="_blank" rel="noopener">https://github.com/ViacheslavDanilov/edema_quantification</a></li> <li><strong>Dataset:</strong> <a href="https://doi.org/10.5281/zenodo.8383776" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.8383776</a></li> <li><strong>Lung segmentation models:</strong> <a href="https://doi.org/10.5281/zenodo.8393555" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.8393555</a></li> <li><strong>Radiographic feature detection models:</strong> <a href="https://doi.org/10.5281/zenodo.8393565" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.8393565</a></li> </ul> <p> </p> <p><em><strong>Table 1.</strong> Summary of annotated radiological features and severity labels</em></p> <table> <tbody> <tr> <td> <p><strong>Radiological feature</strong></p> </td> <td> <p><strong>Number </strong><strong>of objects</strong></p> </td> <td> <p><strong>Severity </strong><strong>l</strong><strong>abel</strong></p> </td> <td> <p><strong>Number of cases</strong></p> </td> </tr> <tr> <td> <p>Cephalization</p> </td> <td> <p>1656</p> </td> <td> <p>No edema</p> </td> <td> <p>21</p> </td> </tr> <tr> <td> <p>Kerley line</p> </td> <td> <p>609</p> </td> <td> <p>Vascular congestion</p> </td> <td> <p>74</p> </td> </tr> <tr> <td> <p>Pleural effusion</p> </td> <td> <p>317</p> </td> <td> <p>Interstitial edema</p> </td> <td> <p>51</p> </td> </tr> <tr> <td> <p>Bat wing</p> </td> <td> <p>1604</p> </td> <td> <p>Alveolar edema</p> </td> <td> <p>595</p> </td> </tr> <tr> <td> <p>Infiltrate</p> </td> <td> <p>77</p> </td> <td> <p> </p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p>TOTAL</p> </td> <td> <p>4263</p> </td> <td> <p>TOTAL</p> </td> <td> <p>741</p> </td> </tr> </tbody> </table> <p> </p> </div>
MyD88-TLR4-dependent choroid plexus activation precedes perilesional inflammation and secondary brain edema in a mouse model of intracerebral hemorrhage
<p>Supplementary data and code of the article "MyD88-TLR4-dependent choroid plexus activation precedes perilesional inflammation and secondary brain edema in a mouse model of intracerebral hemorrhage".</p>
Efficacy and Safety of Brolucizumab vs Aflibercept in Patients With Visual Impairment Due to Diabetic Macular Edema
ClinicalTrials.gov study NCT03917472. IPD Sharing: YES. Countries: 5. Publications: 1.
Data from: Association between total dose of ritodrine hydrochloride and pulmonary edema in twin pregnancy: a retrospective cohort study in Japan
Objective Pulmonary edema is recognized as a severe side effect of ritodrine hydrochloride. Recently, the number of twin pregnancies has been increasing. Few studies have reported the association between total dose of ritodrine hydrochloride prior to delivery and pulmonary edema in twin pregnancy. We aimed to examine this association and determine the optimal cutoff threshold of total ritodrine hydrochloride dose to predict the incidence of pulmonary edema in twin pregnancy, based on obstetric records. Design Retrospective cohort study. Setting Yamanashi Prefectural Central Hospital, Japan Participants Two hundred twenty-six women with twin pregnancy who delivered at Yamanashi Prefectural Central Hospital between September 2009 and November 2016 Methods The obstetric records of the participants were analyzed. We defined one unit of ritodrine hydrochloride as 72 mg per 24 h continuous transfusion at 50 µg/min to calculate the dose of ritodrine used for tocolysis. Outcome measures Multivariable logistic regression analysis was performed to examine the association between total dose of ritodrine hydrochloride used for threatened preterm labor and pulmonary edema, while controlling for potential confounding factors. Then, a receiver-operating characteristic curve was used to determine the optimal cutoff of total ritodrine dose to predict pulmonary edema incidence. Results Mean maternal age was 32 (range, 18-46) years; 143 participants were nulliparous (63.3%), 109 had (48.2%) term deliveries, and 194 (85.8%) had cesarean deliveries. The overall incidence of pulmonary edema was 13.7% (31/226). Multivariable analysis showed that the total dose of ritodrine was significantly associated with pulmonary edema (adjusted odds ratio 1.02; 95% confidence interval, 1.004-1.03). The best cut-off point to predict the incidence of pulmonary edema was 26 units (1872 mg) (sensitivity, 61.3%; specificity, 87.8%). Conclusion Our results suggest that consideration of the total dose of ritodrine hydrochloride is helpful in the management of patients with threatened preterm labor in twin pregnancy.
Skin eruptions in acute hemorrhagic edema of young children: systematic review of the literature
<p><strong>Background:</strong> Acute hemorrhagic edema is a skin limited small-vessel leukocytoclastic vasculitis, which affects infants 4 weeks to 2 years of age and remits within 3 weeks. The diagnosis is made clinically in not-ill appearing children with acute onset of raised annular or nummular eruptions and edema. In this vasculitis, type, distribution and evolution of the rash have never been systemically investigated. To address this issue, we employed the data contained in the Acute Hemorrhagic Edema Bibliographic Database, which incorporates all reports on acute hemorrhagic edema. <strong>Summary:</strong> Key features of rash were documented in 383 children. Annular eruptions in strict sense, usually targetoid, were reported in 375 (98%) cases (many children also presented polycyclic or arciform eruptions). Nummular eruptions were also very common (N=358; 93%). Purpuric eruptions and ecchymoses were reported in the vast majority of cases. Macules and wheals were described in a minority of cases. Edema, detected in all cases, was mostly painful, indurated and non-pitting. Following regions were affected, in decreasing order, by annular or nummular eruptions: legs, feet, face, arms, ears, trunk, and genitals. With the exception of feet, which were very often affected, the same distribution was reported for edema. The initial eruption was often a wheal or a macule that evolved into a nummular or an annular eruption. Nummular eruptions successively evolved into annular ones<strong>. Key message</strong>: this study carefully characterizes type, distribution and evolution of skin eruption in acute hemorrhagic edema. The data help physicians to rapidly and noninvasively make the clinical diagnosis of this vasculitis.</p>
Diabetic Macular Edema VQA Dataset with Logical Relations
<p>Same as <a href="https://zenodo.org/record/6784358">Diabetic Macular Edema VQA Dataset</a>, but logical relations are added between pairs of questions.</p> <p>If you use this dataset, please cite our paper:</p> <pre>@inproceedings{tascon2023logical, title={Logical Implications for Visual Question Answering Consistency}, author={Tascon-Morales, Sergio and M{\'a}rquez-Neila, Pablo and Sznitman, Raphael}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={6725--6735}, year={2023} }</pre>
Fluocinolone Acetonide Implant Compared to Sham Injection in Patients With Diabetic Macular Edema
ClinicalTrials.gov study NCT00344968. IPD Sharing: Not stated. Countries: 1. Publications: 2.
Clinical Study to Evaluate PRO-169 for Diabetic Macular Edema
ClinicalTrials.gov study NCT05217680. IPD Sharing: NO. Countries: 2. Publications: 2.
A Pilot Study for the Evaluation of Minocycline as a Microglia Inhibitor in the Treatment of Diabetic Macular Edema
ClinicalTrials.gov study NCT01120899. IPD Sharing: Not stated. Countries: 1. Publications: 4.
A Study to Evaluate the Efficacy and Safety of Faricimab in Participants With Macular Edema Secondary to Branch Retinal Vein Occlusion
ClinicalTrials.gov study NCT04740905. IPD Sharing: YES. Countries: 22. Publications: 1.
Transfoveal Micropulse Laser for Center Involving Diabetic Macular Edema
ClinicalTrials.gov study NCT04359771. IPD Sharing: YES. Countries: 1. Publications: 2.
Safety and Efficacy of a New Treatment in Vitrectomized Subjects With Diabetic Macular Edema
ClinicalTrials.gov study NCT00799227. IPD Sharing: Not stated. Countries: 2. Publications: 1.
Safety, Tolerability and Evidence of Activity Study of UBX1325 in Patients With Diabetic Macular Edema (BEHOLD)
ClinicalTrials.gov study NCT04857996. IPD Sharing: NO. Countries: 2. Publications: 1.
A Study to Evaluate the Long-Term Safety and Tolerability of Faricimab in Participants With Diabetic Macular Edema
ClinicalTrials.gov study NCT04432831. IPD Sharing: YES. Countries: 30. Publications: 1.
A Study of Faricimab (RO6867461) in Participants With Center-Involving Diabetic Macular Edema
ClinicalTrials.gov study NCT02699450. IPD Sharing: Not stated. Countries: 1. Publications: 1.
A Study in Patients With Neovascular Age Related Macular Degeneration or Macular Edema Secondary To Retinal Vein Occlusion to Evaluate Usability of the Ranibizumab (Lucentis®) Prefilled Syringe (PFS)
ClinicalTrials.gov study NCT02698566. IPD Sharing: Not stated. Countries: 1. Publications: 1.
Study of Oral Minocycline in Treating Bilateral Cystoid Macular Edema Associated With Retinitis Pigmentosa
ClinicalTrials.gov study NCT02140164. IPD Sharing: NO. Countries: 1. Publications: 4.
A Safety and Efficacy Trial of a Treat and Extend Protocol Using Ranibizumab With and Without Laser Photocoagulation for Diabetic Macular Edema
ClinicalTrials.gov study NCT01934556. IPD Sharing: Not stated. Countries: 1. Publications: 3.
Evaluation of Macugen Treatment of Macular Edema Due to Branch Retinal Vein Occlusion
ClinicalTrials.gov study NCT00406107. IPD Sharing: Not stated. Countries: 1. Publications: 6.
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.