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”
NeurIPS 2022 Cell Segmentation Competition Dataset
<p>The official data set for the NeurIPS 2022 competition: cell segmentation in multi-modality microscopy images.</p> <p>https://neurips22-cellseg.grand-challenge.org/</p> <p>Please cite the following paper if this dataset is used in your research. </p> <p> </p> <pre><code><span>@article</span><span>{</span><span>NeurIPS</span><span>-</span><span>CellSeg</span><span>,</span> <span>title</span> <span>=</span> <span>{</span><span>The</span> <span>Multi</span><span>-</span><span>modality</span> <span>Cell</span> <span>Segmentation</span> <span>Challenge</span><span>:</span> <span>Towards</span> <span>Universal</span> <span>Solutions</span><span>}</span><span>,</span> <span>author</span> <span>=</span> <span>{</span><span>Jun</span> <span>Ma</span> <span>and</span> <span>Ronald</span> <span>Xie</span> <span>and</span> <span>Shamini</span> <span>Ayyadhury</span> <span>and</span> <span>Cheng</span> <span>Ge</span> <span>and</span> <span>Anubha</span> <span>Gupta</span> <span>and</span> <span>Ritu</span> <span>Gupta</span> <span>and</span> <span>Song</span> <span>Gu</span> <span>and</span> <span>Yao</span> <span>Zhang</span> <span>and</span> <span>Gihun</span> <span>Lee</span> <span>and</span> <span>Joonkee</span> <span>Kim</span> <span>and</span> <span>Wei</span> <span>Lou</span> <span>and</span> <span>Haofeng</span> <span>Li</span> <span>and</span> <span>Eric</span> <span>Upschulte</span> <span>and</span> <span>Timo</span> <span>Dickscheid</span> <span>and</span> <span>José</span> <span>Guilherme</span> <span>de</span> <span>Almeida</span> <span>and</span> <span>Yixin</span> <span>Wang</span> <span>and</span> <span>Lin</span> <span>Han</span> <span>and</span> <span>Xin</span> <span>Yang</span> <span>and</span> <span>Marco</span> <span>Labagnara</span> <span>and</span> <span>Vojislav</span> <span>Gligorovski</span> <span>and</span> <span>Maxime</span> <span>Scheder</span> <span>and</span> <span>Sahand</span> <span>Jamal</span> <span>Rahi</span> <span>and</span> <span>Carly</span> <span>Kempster</span> <span>and</span> <span>Alice</span> <span>Pollitt</span> <span>and</span> <span>Leon</span> <span>Espinosa</span> <span>and</span> <span>Tâm</span> <span>Mignot</span> <span>and</span> <span>Jan</span> <span>Moritz</span> <span>Middeke</span> <span>and</span> <span>Jan</span><span>-</span><span>Niklas</span> <span>Eckardt</span> <span>and</span> <span>Wangkai</span> <span>Li</span> <span>and</span> <span>Zhaoyang</span> <span>Li</span> <span>and</span> <span>Xiaochen</span> <span>Cai</span> <span>and</span> <span>Bizhe</span> <span>Bai</span> <span>and</span> <span>Noah</span> <span>F</span><span>.</span> <span>Greenwald</span> <span>and</span> <span>David</span> <span>Van</span> <span>Valen</span> <span>and</span> <span>Erin</span> <span>Weisbart</span> <span>and</span> <span>Beth</span> <span>A</span><span>.</span> <span>Cimini</span> <span>and</span> <span>Trevor</span> <span>Cheung</span> <span>and</span> <span>Oscar</span> <span>Brück</span> <span>and</span> <span>Gary</span> <span>D</span><span>.</span> <span>Bader</span> <span>and</span> <span>Bo</span> <span>Wang</span><span>}</span><span>,</span> <span>journal</span> <span>=</span> <span>{</span><span>Nature</span> <span>Methods</span><span>}</span><span>,</span><span><br> volume={21},<br> pages={1103–1113},<br> <span>year</span> <span>=</span> <span>{</span><span>2024</span><span>}</span>,</span> <span>doi</span> <span>=</span> <span>{</span><span>https</span><span>:</span><span>//</span><span>doi</span><span>.</span><span>org</span><span>/</span><span>10.1038</span><span>/</span><span>s41592</span><span>-</span><span>024</span><span>-</span><span>02233</span><span>-</span><span>6</span><span>}</span> <span>}</span></code></pre> <p> </p> <p>This is an instance segmentation task where each cell has an individual label under the same category (cells). The training set contains both labeled images and unlabeled images. You can only use the labeled images to develop your model but we encourage participants to try to explore the unlabeled images through weakly supervised learning, semi-supervised learning, and self-supervised learning.</p> <p> </p> <p>The images are provided with original formats, including tiff, tif, png, jpg, bmp... The original formats contain the most amount of information for competitors and you have free choice over different normalization methods. For the ground truth, we standardize them as tiff formats.</p> <p> </p> <p><strong>We aim to maintain this challenge as a sustainable benchmark platform. If you find the top algorithms (https://neurips22-cellseg.grand-challenge.org/awards/) don't perform well on your images, welcome to send us the dataset (neurips.cellseg@gmail.com)! We will include them in the new testing set and credit your contributions on the challenge website!</strong></p> <p> </p> <p><strong>Dataset License: CC-BY-NC-ND</strong></p>
lipid droplet training dataset for live cell anatomy segmentation
Open the record for dataset details and reuse information.
Golgi training dataset for live cell anatomy segmentation
Open the record for dataset details and reuse information.
DeepBacs – Bacillus subtilis fluorescence segmentation dataset
<p>Training and test images of live <em>B. subtilis </em>cells expressing FtsZ-GFP for the task of segmentation.</p> <p>Additional information can be found on this <a href="https://github.com/HenriquesLab/DeepBacs/wiki">github wiki</a>.</p> <p>The example shows the fluorescence widefield image of live <em>B. subtilis </em>cells expressing FtsZ-GFP and the manually annotated segmentation mask.</p> <p> </p> <p><strong>Data type</strong>: Paired fluorescence and segmented mask images</p> <p><strong>Microscopy data type</strong>: 2D widefield images (fluorescence) </p> <p><strong>Microscope</strong>: Custom-built 100x inverted microscope bearing a 100x TIRF objective (Nikon CFI Apochromat TIRF 100XC Oil); images were captured on a Prime BSI sCMOS camera (Teledyne Photometrics)</p> <p><strong>Cell type</strong>: <em>B. subtilis</em> strain SH130 grown under agarose pads</p> <p><strong>File format</strong>: .tiff (8-bit) or .png (8-bit)</p> <p>For segmented masks, binary masks are used for training of CARE/U-Net models, 8-bit .tif ROI maps for training of StarDist models and .png images for training of pix2pix models</p> <p><strong>Image size</strong>: 1024 x 1024 px² (Pixel size: 65 nm)</p> <p><strong>Image preprocessing</strong>: Images were denoised using PureDenoise and resulting 32-bit images were converted into 8-bit images after normalizing to 1% and 99.98% percentiles. Images were manually annotated using the Labkit Fiji plugin</p> <p> </p> <p><strong>Author(s)</strong>: Mia Conduit<sup>1,2</sup>, Séamus Holden<sup>1,3</sup></p> <p><strong>Contact email</strong>: <a href="mailto:Seamus.Holden@newcastle.ac.uk">Seamus.Holden@newcastle.ac.uk</a></p> <p> </p> <p><strong>Affiliation</strong>:</p> <p>1) Centre for Bacterial Cell Biology, Biosciences Institute, Newcastle University, NE2 4AX UK</p> <p>2) ORCID: 0000-0002-7169-907X</p> <p> </p> <p> <strong>Associated publications</strong>: Whitley <em>et al</em>., 2021, Nature Communications, https://doi.org/10.15252/embj.201696235</p>
DeepBacs – Staphylococcus aureus widefield segmentation dataset
<p>Training and test images of live <em>S. aureus</em> cells for the task of cell segmentation.</p> <p>Additional information can be found in the <a href="https://github.com/HenriquesLab/DeepBacs/wiki">github wiki</a>.</p> <p>The example shows the bright field and Nile Red fluorescence image of live <em>S. aureus </em>cells, as well as the manually annotated segmentation mask.</p> <p> </p> <p><strong>Data type</strong>: Paired DIC/fluorescence and segmented mask images</p> <p><strong>Microscopy data type</strong>: 2D widefield images (DIC and fluorescence)</p> <p><strong>Microscope</strong>: GE HealthCare Deltavision OMX system (with temperature and humidity control, 37°C) equipped with an Olympus 60x 1.42NA Oil immersion objective and 2 PCO Edge 5.5 sCMOS cameras (one for DIC, one for fluorescence)</p> <p><strong>Cell type</strong>: <em>S. aureus</em> strain JE2 grown under agarose pads</p> <p><strong>File format</strong>: .tif (16-bit)</p> <p><strong>Image size</strong>: 512 x 512 px² (80 nm/px)<br> <strong>Image preprocessing</strong>: Raw images were manually annotated by drawing ellipses in the NR fluorescence image and segmented images were created using the LOCI plugin (“ROI Map”). For training, images and masks were quartered into four 256 x 256 px² patches.</p> <p> </p> <p><strong>Author(s)</strong>: Pedro Matos Pereira<sup>1,2</sup>, Mariana Pinho<sup>1,3</sup></p> <p><strong>Contact email</strong>: <a href="mailto:pmatos@itqb.unl.pt">pmatos@itqb.unl.pt</a> and <a href="mailto:mgpinho@itqb.unl.pt">mgpinho@itqb.unl.pt</a></p> <p> </p> <p><strong>Affiliation</strong>: </p> <p>1) Bacterial Cell Biology, Instituto de Tecnologia Química e Biológica António Xavier, Universidade Nova de Lisboa, Oeiras, Portugal</p> <p>2) ORCID: https://orcid.org/0000-0002-1426-9540</p> <p>3) ORCID: https://orcid.org/0000-0002-7132-8842</p>
Dataset for "Deep Learning with remote sensing data for image segmentation: example of rice crop mapping using Sentinel-2 images"
<p>Dataset for "Deep Learning with remote sensing data for image segmentation: example of rice crop mapping using Sentinel-2 images". </p> <p> </p> <p>image_prediction_pt1 and _pt2 have the same content as image_prediction.zip but split in two parts for faster downloading with Google Colab (to avoid time out)</p> <p> </p> <p>Contact</p> <p>Ricardo Dalagnol</p> <p>ricds@hotmail.com</p>
Dataset in "Continent-continent Collision between the South and North China Plates Revealed by Seismic Refraction and Reflection at the Southern Segment of the Tanlu Fault Zone""
<p>This dataset contains:</p> <p> Field-data FWI Results<br> Deep Seismic Profiling Result<br> Post-stack Depth Migration<br> Source Signature<br> Misfit Reduction</p> <p>Descriptions:<br> 1. the unit of distance or depth is meter;<br> 2. the unit of time is ms;<br> 3. all the *.dat files are saved as plain text files;<br> 4. all the *.m files are the Matlab scripts for loading and plotting the data.</p>
Boston & Corniolo Datasets - road segmentation - described in "An Enhanced Loss Function for Semantic Road Segmentation in Remote Sensing Images""
<p>In Corniolo.rar the masks (values {0,1}) are saved in the png files</p>
NIBIO_MLS: a forest point cloud panoptic segmentation dataset from mobile laser scanning (Geoslam Horizon)
<h1>General description</h1> <p>This dataset consists of a ML-ready labelled mobile laser scanning (MLS) point cloud dataset including 16 manually labelled forest plots (approx. 250 m2) for forest panoptic segmentation and thus including both semantic and instance labels. The data was collected using a Geoslam Horizon RT and processed using Geoslam Hub.</p> <h1>Labels</h1> <p>The data were then labelled into the following semantic classes (<em>label</em>):</p> <ul> <li>1= ground</li> <li>2= vegetation: these include both branches, leaves, and low vegetation</li> <li>3= lying deadwood</li> <li>4= stems</li> </ul> <p>In addition for each tree, a unique tree identifier (<em>treeID</em>) was also assigned to each point.</p> <h1>Data split</h1> <p>Each plot was split into train (50%), validation (25%), and test (25%) sets by dividing the circular plot into four slices, out of which the first two were used for training, the third for validation, and the fourth for test. </p> <p>Thus the users might play around with merging the train and validation dataset as they prefer. These two sets can be used during model training, hyperparameter tuning, and model selection. However, the test set should be kept as an independent set to be used for benchmarking against the values reported in the two studies indicated below. </p> <h1>Citation</h1> <p>To cite this datasets and for a more detailed description use:</p> <p>Wielgosz, M., Puliti, S., Xiang, B., Schindler, K. and Astrup, R., 2024. SegmentAnyTree: A sensor and platform agnostic deep learning model for tree segmentation using laser scanning data. <em>Remote Sensing of Environment; </em></p> <h2>Other studies using these data</h2> <p>Wielgosz, M., Puliti, S., Wilkes, P. and Astrup, R., 2023. Point2Tree (P2T)—Framework for parameter tuning of semantic and instance segmentation used with mobile laser scanning data in coniferous forest. <em>Remote Sensing</em>, <em>15</em>(15), p.3737; available <a href="https://www.mdpi.com/2072-4292/15/15/3737" target="_blank" rel="noopener">here</a></p> <h1>Funding</h1> <p>This work is part of the Center for Research-based Innovation SmartForest: Bringing Industry 4.0 to<br>the Norwegian forest sector (NFR SFI project no. 309671, smartforest.no).</p> <h1>⚖️ Licensing</h1> <p>📄 Please refer to the specific licenses below for details on how the data can be used.</p> <h4>🔑 Key Licensing Principles:</h4> <ul> <li>✅ You may access, use, and share the dataset and models freely.</li> <li>🔄 Any derivative works (e.g., trained models, code for training, or prediction tools) must also be made publicly available under the same licensing terms.</li> <li>🌍 These licenses promote <strong>collaboration</strong> and <strong>transparency</strong>, ensuring that research using this dataset benefits the broader scientific and open-source community 🙌</li> </ul>
Test Dataset for 3D semantic image segmentation of the Liver and Tumor
Open the record for dataset details and reuse information.
Labelled Arabidopsis dataset for testing membrane segmentation models
<p>Labels of 3D dataset of confocal imaged arabidopsis for testing segmentation models.</p>
Arabidopsis dataset for testing membrane segmentation models
<p>3D dataset of confocal imaged arabidopsis for testing segmentation models.</p>
RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scans
<p>Manual rib inspections in computed tomography (CT) scans are clinically critical but labor-intensive, as 24 ribs are typically elongated and oblique in 3D volumes. Automatic rib segmentation methods can speed up the process through rib measurement and visualization. However, prior arts mostly use in-house labeled datasets that are publicly unavailable and work on dense 3D volumes that are computationally inefficient. To address these issues, we develop a labeled rib segmentation benchmark, named RibSeg, including 490 CT scans (11,719 individual ribs) from a public dataset. For ground truth generation, we used existing morphology-based algorithms and manually refined its results. Then, considering the sparsity of ribs in 3D volumes, we thresholded and sampled sparse voxels from the input and designed a point cloud-based baseline method for rib segmentation. The proposed method achieves state-of-the-art segmentation performance (Dice<span class="math-tex">\(\approx95\%\)</span>) with significant efficiency (<span class="math-tex">\(10\sim40\times\)</span> faster than prior arts). The RibSeg dataset, code, and model in PyTorch are available at <a href="https://github.com/M3DV/RibSeg">https://github.com/M3DV/RibSeg</a>.</p> <p> </p> <p><strong>Note:</strong> This repository provides rib segmentation ("RibFrac31-rib-seg.nii.gz") and centerline ("RibFrac31-rib-cl.nii.gz") <em>annotations</em> for 490 cases in RibFrac dataset. Please download the corresponding CT <em>images </em>("RibFrac31-image.nii.gz") at <a href="https://ribfrac.grand-challenge.org/">https://ribfrac.grand-challenge.org/</a> (1-click registration is needed via <em>"Join"</em>).</p>
Golden crucian carp segmentation dataset
<p>Golden crucian carp segmentation dataset</p>
Dataset for: Kidney abnormality segmentation in thorax-abdomen CT scans
<p>215 thoraxabdomen CT scans with segmentations of the kidney and abnormalities in the kidney.</p>
Dataset from "Synthetic Training Data for Semantic Segmentation of the Environment from UAV Perspective"
<p>This dataset contains the images and ground truth label masks for semantic segmentation created and described in "Hinniger, C.; Rüter, J. Synthetic Training Data for Semantic Segmentation of the Environment from UAV Perspective. Aerospace 2023, 10, 604. https://doi.org/10.3390/aerospace10070604".</p>
DLO Instance Segmentation dataset generated by Blender
<p>This dataset is released as part of the publication: "Adapter to facilitate Foundation Model Communication for DLO Instance Segmentation" - https://openreview.net/forum?id=EYBtzTQvdW</p> <pre><code><a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by-sa/4.0/80x15.png" /></a><br />This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/">Creative Commons Attribution-ShareAlike 4.0 International License</a>.</code></pre>
Dataset for "Comparing Neural Network Based Segmentation of Cardiomyocytes from Different Histology Data"
<p>This dataset contains the trained UNet TensorFlow network, the raw (tiled) histology images, and input and output inference data. The data was used for the work presented at the ISMRM Workshop on Machine Learning in 2018.</p>
Full sequencing dataset of payload segments for "A Base Multilayer DNA Storage Architecture Enables Real-Time Decoding to Overcome Latency" (Part 2, FASTA file)
<p><span lang="EN-US">This is the full sequencing dataset of payload segments for the manuscript "A Base Multilayer DNA Storage Architecture Enables Real-Time Decoding to Overcome Latency", which is submitted for review.</span></p> <p><span lang="EN-US">We successfully encoded the first color film "Becky Sharp" (54.79 MB) into ~10.08 million DNA strands, achieving a sustained readout throughput of 459 kbit/s.</span></p> <p><span lang="EN-US">This full sequencing dataset contains all base-called data (in BIN and FASTA) of the payload segments. It can be used for recovery of the 28-layer color film data with the <br>DNA-LC software. </span></p> <p><span lang="EN-US">Due to size limitations, the dataset is divided into two parts. Part 1 contains all the files in BIN format, and Part 2 contains the corresponding files in FASTA format. This link is for Part 2.</span></p>
Full sequencing dataset of payload segments for "A Base Multilayer DNA Storage Architecture Enables Real-Time Decoding to Overcome Latency" (Part 1, BIN file)
<p><span lang="EN-US">This is the full sequencing dataset of payload segments for the manuscript "A Base Multilayer DNA Storage Architecture Enables Real-Time Decoding to Overcome Latency", which is submitted for review.</span></p> <p><span lang="EN-US">We successfully encoded the first color film "Becky Sharp" (54.79 MB) into ~10.08 million DNA strands, achieving a sustained readout throughput of 459 kbit/s.</span></p> <p><span lang="EN-US">This full sequencing dataset contains all base-called data (in BIN and FASTA) of the payload segments. It can be used for recovery of the 28-layer color film data with the<br>DNA-LC software. </span></p> <p><span lang="EN-US">Due to size limitations, the dataset is divided into two parts. Part 1 contains all the files in BIN format, and Part 2 contains the corresponding files in FASTA format. This link is for Part 1.</span></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.