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.
16
datasets available to search
ShareScore release 0.9.0
Dataset results
16 results for “bioimage.io”
bioimage.io upload: ilastik/vnc
<p><a href="" title="https://bioimage.io/#/?id=ilastik/vnc">View on bioimage.io</a> # Segmented anisotropic ssTEM dataset of neural tissue </p> <h1>Segmented anisotropic ssTEM dataset of neural tissue</h1> <p>Training data for segmentation of neuron boundaries, mitochondria and synapses in neural tissue of Drosophila imaged in EM.</p>
bioimage.io upload: ilastik/covid_if_training_data
<p><a href="" title="https://bioimage.io/#/?id=ilastik/covid_if_training_data">View on bioimage.io</a> # Covid-IF Training Data </p> <h1>Covid-IF Training Data</h1> <p>Training data for cell and nucleus segmentation as well as infected cell classification of Covid19 in immunofluorescence. The images are taken with a high-throughput microscope and were used as training data to set up an IF based CoV19 antibody assay <a href="https://doi.org/10.1002/bies.202000257">here</a>.</p>
bioimage.io upload: ilastik/plantseg_root
<p><a href="" title="https://bioimage.io/#/?id=ilastik/plantseg_root">View on bioimage.io</a> # Arabidopsis Lateral Root Traning Data </p> <h1>Arabidopsis lateral root training data</h1> <p>Training data for cell segmentation in Arabidopsis lateral root from <a href="https://github.com/hci-unihd/plant-seg">plantseg</a>.</p>
bioimage.io upload: hpa/hpa-kaggle-2021-dataset
<p><a href="" title="https://bioimage.io/#/?id=hpa/hpa-kaggle-2021-dataset">View on bioimage.io</a> # HPA Single Cell Classification Dataset 2021 </p> <h2>Training dataset for the Human Protein Atlas - Single Cell Classification competition 2021</h2> <p>More information: https://www.kaggle.com/competitions/hpa-single-cell-image-classification/data</p> <h2>What files do I need?</h2> <p>On the data page below, you will find a set of full size original images (a mix of 1728x1728, 2048x2048 and 3072x3072 PNG files) in train.zip and test.zip. (Please note that since this is a code competition, part of test data will be hidden)</p> <p>You will also need the image level labels from train.csv and the filenames for the test set from sample_submission.csv. As many Kagglers made use of all public images in HPA for previous classification challenge, we made the public HPA images available to download as instructed in this notebook. Note also that there are TFRecords available if competitors would like to use TPUs.</p> <p>The 16-bit version of the training images are available here. Additional training images are available here.</p> <h2>What should I expect the data format to be?</h2> <p>The training image-level labels are provided for each sample in train.csv. The bulk of the data for images - train.zip. Each sample consists of four files. Each file represents a different filter on the subcellular protein patterns represented by the sample. The format should be [filename]_[filter color].png for the PNG files. Colors are red for microtubule channels, blue for nuclei channels, yellow for Endoplasmic Reticulum (ER) channels, and green for protein of interest.</p> <h2>What am I predicting?</h2> <p>You are predicting protein organelle localization labels for each cell in the image. Border cells are included when there is enough information to decide on the labels.</p> <p>There are in total 19 different labels present in the dataset (18 labels for specific locations, and label 18 for negative and unspecific signal). The dataset is acquired in a highly standardized way using one imaging modality (confocal microscopy). However, the dataset comprises 17 different cell types of highly different morphology, which affect the protein patterns of the different organelles. All image samples are represented by four filters (stored as individual files), the protein of interest (green) plus three cellular landmarks: nucleus (blue), microtubules (red), endoplasmic reticulum (yellow). The green filter should hence be used to predict the label, and the other filters are used as references. The labels are represented as integers that map to the following:</p> <p><code>0. Nucleoplasm 1. Nuclear membrane 2. Nucleoli 3. Nucleoli fibrillar center 4. Nuclear speckles 5. Nuclear bodies 6. Endoplasmic reticulum 7. Golgi apparatus 8. Intermediate filaments 9. Actin filaments 10. Microtubules 11. Mitotic spindle 12. Centrosome 13. Plasma membrane 14. Mitochondria 15. Aggresome 16. Cytosol 17. Vesicles and punctate cytosolic patterns 18. Negative</code></p> <h2>What is meant by weak image-level labels?</h2> <p>The labels you will get for training are image level labels while the task is to predict cell level labels. That is to say, each training image contains a number of cells that have collectively been labeled as described above and the prediction task is to look at images of the same type and predict the labels of each individual cell within those images.</p> <p>As the training labels are a collective label for all the cells in an image, it means that each labeled pattern can be seen in the image but not necessarily that each cell within the image expresses the pattern. This imprecise labeling is what we refer to as weak.</p> <p>During the challenge you will both need to segment the cells in the images and predict the labels of those segmented cells.</p> <p>Files: - train - training images (in .tif) - test - test images (in .png) - the task of the competition is to segment and label the images in this folder - train.csv - filenames and image level labels for the training set - sample_submission.csv - filenames for the test set, and a guide to constructing a working submission.</p> <p>Columns: - ID - The base filename of the sample. As noted above all samples consist of four files - blue, green, red, and yellow. - Label - in the training data, this represents the labels assigned to each sample; in submission, this represent the labels assigned to each cell.</p>
bioimage.io upload: ilastik/stardist_dsb_training_data
<p><a href="" title="https://bioimage.io/#/?id=ilastik/stardist_dsb_training_data">View on bioimage.io</a> # DSB Nucleus Segmentation Training Data </p> <h1>Nucleus Segmentation Training Data</h1> <p>Traning data for instance segmentation of nuclei. This data is a subset of the data from the <a href="https://bioimage.io/#/?type=application&id=notebook_stardist_2d_zerocostdl4mic">2018 Kaggle Data Science Bowl dataset for nucleus segmentation</a>. This subset has been used for training the <a href="https://github.com/stardist/stardist">StarDist</a> nucleus segmentation model and other nucleus segmentation models on bioimagei.io.</p>
bioimage.io upload: zero/Dataset_YOLOv2_ZeroCostDL4Mic
<p><a href="" title="https://bioimage.io/#/?id=zero/Dataset_YOLOv2_ZeroCostDL4Mic">View on bioimage.io</a> # YoloV2 example training and test dataset - ZeroCostDL4Mic </p> <p>documentation at <a href="https://doi.org/10.5281/zenodo.3941908">https://doi.org/10.5281/zenodo.3941908</a></p>
bioimage.io upload: zero/Dataset_CARE_2D_coli_DeepBacs
<p><a href="" title="https://bioimage.io/#/?id=zero/Dataset_CARE_2D_coli_DeepBacs">View on bioimage.io</a> # Escherichia coli nucleoid denoising dataset - DeepBacs </p> <p>documentation at <a href="https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki">https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki</a></p>
bioimage.io upload: ilastik/tnbc
<p><a href="" title="https://bioimage.io/#/?id=ilastik/tnbc">View on bioimage.io</a> # Segmentation of Nuclei in Histopathology Images </p> <h1>Nucleus Segmentation Training Data</h1> <p>Traning data for instance segmentation of nuclei in H&E brightfield images. This dataset was published in https://doi.org/10.1109/TMI.2018.2865709.</p>
bioimage.io upload: hpa/hpa-cell-image-segmentation-dataset
<p><a href="" title="https://bioimage.io/#/?id=hpa/hpa-cell-image-segmentation-dataset">View on bioimage.io</a> # HPA Cell Image Segmentation Dataset </p> <p>This dataset includes annotated cell images obtained from the Human Protein Atlas (http://www.proteinatlas.org), each image contains 4 channels (Microtubules, ER, Nuclei and Protein of Interest). The cells in each image are annotated with polygons and saved into GeoJSON format produced with Kaibu(https://kaibu.org) annotation tool.</p> <ul> <li>hpa_cell_segmentation_dataset_v2_512x512_4train_159test.zip is an example dataset for running a deep learning-based interactive annotation tools in ImJoy (https://github.com/imjoy-team/imjoy-interactive-segmentation).</li> <li>hpa_dataset_v2.zip is a full annotate image segmentation dataset</li> </ul> <p>Utility functions in Python for reading the GeoJSON annotation can be found here: https://github.com/imjoy-team/kaibu-utils/blob/main/kaibu_utils/<strong>init</strong>.py</p>
bioimage.io upload: zero/Dataset_fnet_3D_ZeroCostDL4Mic
<p><a href="" title="https://bioimage.io/#/?id=zero/Dataset_fnet_3D_ZeroCostDL4Mic">View on bioimage.io</a> # Label-free prediction (fnet) example training and test dataset - ZeroCostDL4Mic </p> <p>documentation at <a href="https://doi.org/10.5281/zenodo.3748967">https://doi.org/10.5281/zenodo.3748967</a></p>
data for BioImage.IO workflows
<p>Test data and cover images for workflows implemented in https://github.com/bioimage-io/workflows-bioimage-io-python</p> <p><br> References:<br> stardist_chatty_frog.npy derived from https://doi.org/10.5281/zenodo.6338615<br> dask_inference_cover.svg/png: raw data from https://cremi.org/, predictions from https://bioimage.io/#/?id=10.5281%2Fzenodo.5874741, dask icon: https://dask.org</p> <p> </p>
bioimage.io upload: uplifting-ice-cream
<p><a href="" title="https://bioimage.io/#/?id=uplifting-ice-cream">View on bioimage.io</a> # Hatchling Medaka Heart (HyLFM) </p>
bioimage.io upload: imjoy/LuCa-7color
<p><a href="" title="https://bioimage.io/#/?id=imjoy/LuCa-7color">View on bioimage.io</a> # LuCa-7color </p> <p>documentation at <a href="https://imjoy.io/docs">https://imjoy.io/docs</a></p>
bioimage.io upload: ilastik/plantseg_ovules
<p><a href="" title="https://bioimage.io/#/?id=ilastik/plantseg_ovules">View on bioimage.io</a> # Arabidopsis Ovules Traning Data </p> <h1>Arabidopsis ovules training data</h1> <p>Training data for cell segmentation in Arabidopsis ovules from <a href="https://github.com/hci-unihd/plant-seg">plantseg</a>.</p>
bioimage.io upload: ilastik/platynereis_em_training_data
<p><a href="" title="https://bioimage.io/#/?id=ilastik/platynereis_em_training_data">View on bioimage.io</a> # Platynereis EM Traning Data </p> <h1>Platynereis EM Segmentation Training Data</h1> <p>Training data for segmentation of cellular membranes, nuclei, cuticle and cilia in Platynereis dumerilii. The training data is extracted from a whole body EM volume of a Platynereis larva that was used to train networks for segmentation in <a href="https://doi.org/10.1016/j.cell.2021.07.017">Whole-body integration of gene expression and single-cell morphology</a>. For each organelle several blocks of training data are available, extracted at dfferent resolutions: 20x20x25nm for cellular membranes, 80x80x100nm for nuclei, 40x40x50nm for cuticle and 10x10x25nm for cilia.</p>
bioimage.io upload: ilastik/livecell_dataset
<p><a href="" title="https://bioimage.io/#/?id=ilastik/livecell_dataset">View on bioimage.io</a> # LIVECell </p> <h1>Livecell Training Data</h1> <p>Traning data for cell segmentation in live-cell / phase-contrast imaging. From <a href="https://doi.org/10.1038/s41592-021-01249-6">LIVECell—A large-scale dataset for label-free live cell segmentation</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.