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”
Amazon Rainforest dataset for semantic segmentation
<p>This database contains images used for the semantic segmentation of forest and non-forest areas from a fully convolutional neural network U-Net .</p> <p>1. <strong>Training dataset: </strong>it contains 30 GeoTIFF images with 512x512 pixels and associated PNG masks (forest indicated in white and non-forest in black color).</p> <p>2. <strong>Validation dataset</strong>: it contains 15 GeoTIFF images with 512x512 pixels and associated PNG masks used for U-Net validation step.</p> <p>3. <strong>Test dataset: </strong>it contains 15 GeoTIFF images 512x512 pixels for testing.</p>
ProstateZones - Segmentations of the prostatic zones and urethra for the PROSTATEx dataset
<p>Segmentations of the prostatic zones and urethra for 200 patients from the publicly avaliable PROSTATEx image dataset [1-3]. The dataset is intended for research purposes in the field of medical imaging and to enable training and evaluation of autmatic segmentation methods.</p> <p>The prostatic zones and urethra were manually segmented slice by slice on axial T2w MRIs by two experienced radiologists in collaboration with three junior colleagues. All delineations by junior colleagues has been checked, and if necessary, corrected by one of the more experienced radiologists. The two most experienced radiologists have independently delineated duplicate segmentations for 40 patients, for a total of 240 segmentations. This is intended as a test set where automatic methods can compare their performance with the inter-reader variability of the two radiologists.</p> <p>To ease the use of the dataset, help with structuring the data can be found in the linked GitHub repository.</p> <p> </p> <p>For more information about the dataset, see the dataset publication:</p> <p>Holmlund, W., Simkó, A., Söderkvist, K. <em>et al.</em> ProstateZones – Segmentations of the prostatic zones and urethra for the PROSTATEx dataset. <em>Sci Data</em> <strong>11</strong>, 1097 (2024). https://doi.org/10.1038/s41597-024-03945-2</p> <p> </p> <p> </p> <div> <h4>PROSTATEx</h4> </div> <p>[1] Geert Litjens, Oscar Debats, Jelle Barentsz, Nico Karssemeijer, and Henkjan Huisman. "ProstateX Challenge data", The Cancer Imaging Archive (2017). DOI: 10.7937/K9TCIA.2017.MURS5CL</p> <p>[2] Litjens G, Debats O, Barentsz J, Karssemeijer N, Huisman H. "Computer-aided detection of prostate cancer in MRI", IEEE Transactions on Medical Imaging 2014;33:1083-1092. DOI: 10.1109/TMI.2014.2303821</p> <p>[3] Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, Moore S, Phillips S, Maffitt D, Pringle M, Tarbox L, Prior F. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository, Journal of Digital Imaging, Volume 26, Number 6, December, 2013, pp 1045-1057. DOI: 10.1007/s10278-013-9622-7</p>
Semantic2D: A Semantic Dataset for 2D Lidar Semantic Segmentation: Dataset
<p>The 2D lidar semantic segmentation datasets for the paper titled "Semantic2D: A Semantic Dataset for 2D Lidar Semantic Segmentation" by Zhanteng Xie and Philip Dames.</p> <p>The relevant code is available at: https://github.com/TempleRAIL/semantic2d</p> <p> </p>
Test Dataset for 3D semantic image segmentation of the Breast, Fibrograndular Tissue, and Breast Carcinoma
Open the record for dataset details and reuse information.
Segmentation Dataset for Periorbital Segmentation and Distance Prediction
<p>High quality segmentation of the eyes and lids is an essential step in developing clinically relevant deep learning models for oculoplastic and craniofacial surgery. However, there are currently no publicly available datasets suitable for this purpose. As such, we have developed and validated a novel dataset for oculoplastic segmentation and periorbital distance prediction. Using images from two open-source datasets, we segmented the iris, sclera, lid, caruncle, and brow from cropped eye images. Five trained annotators performed the segmentations, and intergrader reliability was assessed on 100 randomly selected images aftera two-week forgetting period, yielding an average Dice score of 0.82 ± 0.01. Intragrader reliability on 20 images averaged a Dice score of 0.81 ± 0.08. To demonstrate the dataset's utility, we trained three DeepLabV3 models following standard procedures. This first-of-its-kind dataset, along with a toolkit for periorbital distance prediction, is publicly available to support the development of clinically useful segmentation models for oculoplastic and craniofacial applications.</p>
Corridor Segmentation Dataset
<p>Corridor segmentation dataset in indoor setups composed of 1,193 images. Labels are represented by segmentation masks.</p> <p>Part of the dataset is obtained from the following sources:</p> <p><em> - CMU Corridor Data Set </em>(n.d.) The Air Lab, <a href="http://theairlab.org/cmu-corridor-dataset/">http://theairlab.org/cmu-corridor-dataset/</a> </p> <p> - Yang, S., Maturana, D., & Scherer, S. (2016, May 1). <em>Real-time 3D scene layout from a single image using Convolutional Neural Networks</em>. IEEE Conference Publication | IEEE Xplore. <a href="https://ieeexplore.ieee.org/document/7487368">https://ieeexplore.ieee.org/document/7487368</a></p>
Mouse thorax segmentation dataset
<p>This repository contains reference segmentations of the heart, spinal cord, right lung and left lung for native and contrast-enhanced mouse CT images. The CTs were drawn from a publicly available preclinical micro-CT database<sup>1</sup>. Annotations are provided for the entire native CT dataset (140 images) and for a subset (35 images) of the contrast-enhanced CT dataset. Annotations by a second observer are also available for 35 native CTs and contrast-enhanced CTs.</p> <p>This dataset was used to train a nnU-Net 3d_fullres model for automated mouse thorax segmentation. The pre-trained model can be downloaded from https://doi.org/10.5281/zenodo.5786839 and more details about the dataset and training can be found in the publication. In case you find these annotations useful for your research, please cite the original work:</p> <p>Malimban, J., Lathouwers, D., Qian, H. <em>et al.</em> Deep learning-based segmentation of the thorax in mouse micro-CT scans. <em>Sci Rep</em> 12, 1822 (2022). https://doi.org/10.1038/s41598-022-05868-7</p> <p> </p> <p><sup>1</sup>Rosenhain S, Magnuska Z A, Yamoah G G, Rawashdeh W A, Kiessling F and Gremse F 2018 A preclinical micro-computed tomography database including 3D whole body organ segmentations Online: https://springernature.figshare.com/collections/A_preclinical_micro-computed_tomography_database_including_3D_whole_body_organ_segmentations/4224377/1 </p>
Annotated quantitative phase microscopy cell dataset of various adherent cell lines for segmentation purposes
<p>This dataset contains microscopic images of multiple cell lines captured by quantitative phase microscopy (QPI) without use of any fluorescent labeling and a manually annotated ground truth for subsequent use in segmentation algorithms. Dataset also includes images reconstructed according to the methods described below in order to ease further segmentation. </p> <p>Our data consist of quantitative phase microscopy images:</p> <ul> <li>244 labelled images of PC-3 (7,907 cells), 205 labelled PNT1A (9,288 cells), 25 labelled images of G361, 25 labelled images of A2050 and 25 labelled images of HOB cells , in the paper designated as "<em>labelled"</em>, and</li> <li>1,819 unlabelled images with a mixture of 22Rv1, A2058, A2780, DU145, Fadu, G361, HOB and LNCaP used for pretraining, in the paper designated as "<em>unlabelled"</em>.</li> </ul> <ul> <li>See Vicar et al. XXXX 2021 DOI XXX (TBA after publishing)</li> <li>Code using this dataset is available at <a href="https://github.com/tomasvicar/Deep-QPI-Cell-Segmentation">github.com/tomasvicar/Deep-QPI-Cell-Segmentation</a></li> </ul> <p><strong>Materials and methods </strong></p> <p>A set of adherent cell lines of various origins, tumorigenic potential, and morphology were used in this paper (PC-3, PNT1A, 22Rv1, DU145, LNCaP, A2058, A2780, Fadu, G361, HOB). PC-3, PNT1A, 22Rv1, DU145, LNCaP, A2780, and G361 cell lines were cultured in RPMI-1640 medium, A2058, FaDu, and HOB cell lines were cultured in DMEM-F12 medium, all supplemented with antibiotics (penicillin 100 U/ml and streptomycin 0.1 mg/ml), and with 10% fetal bovine serum (FBS). Prior to microscopy acquisition, the cells were maintained at 37 °C in a humidified (60%) incubator with 5% CO\textsubscript{2} (Sanyo, Japan). For acquisition purposes, the cells were cultivated in the Flow chamber µ-Slide I Luer Family (Ibidi, Martinsried, Germany). To maintain standard cultivation conditions during time-lapse experiments, cells were placed in the gas chamber H201 - for Mad City Labs Z100/Z500 piezo Z-stage (Okolab, Ottaviano NA, Italy). For the acquisition of QPI, a coherence-controlled holographic microscope (Telight, Q-Phase) was used. Objective Nikon Plan 10×/0.3 was used for hologram acquisition with a CCD camera (XIMEA MR4021MC). Holographic data were numerically reconstructed with the Fourier transform method (described in Slaby, 2013 and phase unwrapping was used on the phase image. QPI datasets used in this paper were acquired during various experimental setups and treatments. In most cases, experiments were conducted with the time-lapse acquisition. The final dataset contains images acquired at least three hours apart.</p> <p><strong>Folder structure and file and filename description</strong></p> <p><strong>labelled </strong><em>(labelled)</em>: cells with segmentation labels, e.g.<br> 00001_PC3_img.tif - 32bit tiff image (in pg/um2 values)<br> 00001_PC3_mask.png - 8bit image with mask with unique grayscale value corresponding to single cell in FOV.</p> <p><strong>unlabelled </strong><em>(unlabelled)</em>: 11 varying cell lines, total 1819 FOVs, 32bit tiff image (in pg/um2 values)</p> <p> </p>
Breakfast Dataset with I3D features for Action Segmentation Using MuCon
<p>Breakfast Dataset with I3D features for Action Segmentation Using MuCon</p> <p> </p> <p>Visit: https://github.com/yassersouri/MuCon</p>
Building Object and Outdoor Scene Segmentation (BOOSS) - Multi-channel (RGB + Thermal) Aerial Imagery Datasets
<p>The dataset of <em>Building Object and Outdoor Scene Segmentation (BOOSS)</em> is based on multi-channel aerial imagery data. It covers </p> <p>- Ground Truth</p> <p>- RGB</p> <p>- Thermal</p> <p>The annotations in version 1.0 include roofs, facades, cars, roof equipment, and ground equipment</p> <p>Please cite as:</p> <p>Hou, Yu, Meida Chen, Rebekka Volk, and Lucio Soibelman. "An Approach to Semantically Segmenting Building Components and Outdoor Scenes Based on Multichannel Aerial Imagery Datasets." <em>Remote Sensing</em> 13, no. 21 (2021): 4357.</p>
Segmented DAPS (Device and Produced Speech) Dataset
<p>This is a modified version of a subset of the Device and Produced Speech (DAPS) dataset. The original dataset can be found <a href="https://zenodo.org/record/4660670#.YKuxgKhKhPZ">here</a>. This dataset contains text-aligned audio of the first script of the "clean" partition of the DAPS dataset for all 20 speakers. Phoneme and word alignments are provided as JSON files. We segment the audio and alignments into single sentences. For each sentence, we additionally provide the raw text in a txt file. Audio is provided as 44.1 kHz WAV files.</p> <p>If you use this work as part of an academic publication, please cite the paper corresponding to the original dataset:</p> <blockquote> <p>Gautham J. Mysore, <a href="https://ieeexplore.ieee.org/document/6981922">“Can We Automatically Transform Speech Recorded on Common Consumer Devices in Real-World Environments into Professional Production Quality Speech? - A Dataset, Insights, and Challenges”</a>, in the IEEE Signal Processing Letters, Vol. 22, No. 8, August 2015</p> </blockquote>
Dataset for: Synthetic Micrographs of Bacteria (SyMBac) Allows Accurate Segmentation of Bacterial Cells Using Deep Neural Networks
<p>Datasets for the paper Synthetic Micrographs of Bacteria (SyMBac) Allows Accurate Segmentation of Bacterial Cells Using Deep Neural Networks, published in BMC Biology.</p>
Datasets of "Influence of contrast and texture based image modifications on the performance and attention shift of U-Net models for brain tissue segmentation" Part 1 of 14
<p>This dataset is part of the work <a href="https://www.frontiersin.org/articles/10.3389/fnimg.2022.1012639/full">https://www.frontiersin.org/articles/10.3389/fnimg.2022.1012639/full</a>. This is the first part of 14 parts of the full dataset (1/14). It contains 3 sets of simulated T1 weighted brain volumes in 3 simulated scanning sequences of spin-echo. The parameters of simulated scanning sequences are respectively repetition time (TR) = 300ms, 400ms, 500ms, and echo time (TE) = 10ms. Under <strong>each</strong> simulated scanning sequence, there are 500 brain volumes.</p> <p>Within this part, we also include the segmentation labels for each tissue.</p> <p>The simulation process of this dataset involves two processes. The first is to simulate one brain under different simulated scanning sequences. For this, we use BrainWeb <a href="https://brainweb.bic.mni.mcgill.ca/cgi/bw/submit_request">https://brainweb.bic.mni.mcgill.ca/cgi/bw/submit_request</a>. In the custom setting, we use spin-echo and apply image artifact the same as the default setting of this page. The second process is to transform each simulated brain from BrainWeb to different anatomical shapes. We use Human Connectome Project (HCP) 1200 subject data <a href="https://www.humanconnectome.org/study/hcp-young-adult">https://www.humanconnectome.org/study/hcp-young-adult</a> and randomly select 500 brains as anatomical references.</p> <p>Other details of this dataset can be found at <a href="https://www.frontiersin.org/articles/10.3389/fnimg.2022.1012639/full">https://www.frontiersin.org/articles/10.3389/fnimg.2022.1012639/full</a> where the details of the data construction are discussed.</p> <p>All parts of the whole dataset can be found at:</p> <p>Part 1: <a href="https://zenodo.org/record/7294916">https://zenodo.org/record/7294916</a></p> <p>Part 2: <a href="https://zenodo.org/record/7389550">https://zenodo.org/record/7389550</a></p> <p>Part 3: <a href="https://zenodo.org/record/7390382">https://zenodo.org/record/7390382</a></p> <p>Part 4: <a href="https://zenodo.org/record/7390741">https://zenodo.org/record/7390741</a></p> <p>Part 5: <a href="https://zenodo.org/record/7391205">https://zenodo.org/record/7391205</a></p> <p>Part 6: <a href="https://zenodo.org/record/7393060">https://zenodo.org/record/7393060</a></p> <p>Part 7: <a href="https://zenodo.org/record/7393174">https://zenodo.org/record/7393174</a></p> <p>Part 8: <a href="https://zenodo.org/record/7393347">https://zenodo.org/record/7393347</a></p> <p>Part 9: <a href="https://zenodo.org/record/7394250">https://zenodo.org/record/7394250</a></p> <p>Part 10: <a href="https://zenodo.org/record/7394667">https://zenodo.org/record/7394667</a></p> <p>Part 11: <a href="https://zenodo.org/record/7394939">https://zenodo.org/record/7394939</a></p> <p>Part 12: <a href="https://zenodo.org/record/7395031">https://zenodo.org/record/7395031</a></p> <p>Part 13: <a href="https://zenodo.org/record/7395620">https://zenodo.org/record/7395620</a></p> <p>Part 14: <a href="https://zenodo.org/record/7395622">https://zenodo.org/record/7395622</a></p>
Datasets of "Influence of contrast and texture based image modifications on the performance and attention shift of U-Net models for brain tissue segmentation" Part 9 of 14
<p>This dataset is part of the work <a href="https://www.frontiersin.org/articles/10.3389/fnimg.2022.1012639/full">https://www.frontiersin.org/articles/10.3389/fnimg.2022.1012639/full</a>. This is the ninth part of 14 parts of the full dataset (9/14). It contains 3 sets of simulated T1 weighted brain volumes in 3 simulated scanning sequences of spin-echo. The parameters of simulated scanning sequences are respectively repetition time (TR) = 600ms, 700ms, 800ms, and echo time (TE) = 15ms. Under <strong>each</strong> simulated scanning sequence, there are 500 brain volumes.</p> <p>The segmentation labels for each tissue are contained in the first part which you may find at <a href="https://zenodo.org/record/7294916">https://zenodo.org/record/7294916</a></p> <p>The simulation process of this dataset involves two processes. The first is to simulate one brain under different simulated scanning sequences. For this, we use BrainWeb <a href="https://brainweb.bic.mni.mcgill.ca/cgi/bw/submit_request">https://brainweb.bic.mni.mcgill.ca/cgi/bw/submit_request</a>. In the custom setting, we use spin-echo and apply image artifact the same as the default setting of this page. The second process is to transform each simulated brain from BrainWeb to different anatomical shapes. We use Human Connectome Project (HCP) 1200 subject data <a href="https://www.humanconnectome.org/study/hcp-young-adult">https://www.humanconnectome.org/study/hcp-young-adult</a> and randomly select 500 brains as anatomical references.</p> <p>Other details of this dataset can be found at <a href="https://www.frontiersin.org/articles/10.3389/fnimg.2022.1012639/full">https://www.frontiersin.org/articles/10.3389/fnimg.2022.1012639/full</a> where the details of the data construction are discussed.</p> <p>All parts of the whole dataset can be found at:</p> <p>Part 1: <a href="https://zenodo.org/record/7294916">https://zenodo.org/record/7294916</a></p> <p>Part 2: <a href="https://zenodo.org/record/7389550">https://zenodo.org/record/7389550</a></p> <p>Part 3: <a href="https://zenodo.org/record/7390382">https://zenodo.org/record/7390382</a></p> <p>Part 4: <a href="https://zenodo.org/record/7390741">https://zenodo.org/record/7390741</a></p> <p>Part 5: <a href="https://zenodo.org/record/7391205">https://zenodo.org/record/7391205</a></p> <p>Part 6: <a href="https://zenodo.org/record/7393060">https://zenodo.org/record/7393060</a></p> <p>Part 7: <a href="https://zenodo.org/record/7393174">https://zenodo.org/record/7393174</a></p> <p>Part 8: <a href="https://zenodo.org/record/7393347">https://zenodo.org/record/7393347</a></p> <p>Part 9: <a href="https://zenodo.org/record/7394250">https://zenodo.org/record/7394250</a></p> <p>Part 10: <a href="https://zenodo.org/record/7394667">https://zenodo.org/record/7394667</a></p> <p>Part 11: <a href="https://zenodo.org/record/7394939">https://zenodo.org/record/7394939</a></p> <p>Part 12: <a href="https://zenodo.org/record/7395031">https://zenodo.org/record/7395031</a></p> <p>Part 13: <a href="https://zenodo.org/record/7395620">https://zenodo.org/record/7395620</a></p> <p>Part 14: <a href="https://zenodo.org/record/7395622">https://zenodo.org/record/7395622</a></p> <p> </p>
HaN-Seg: The head and neck organ-at-risk CT & MR segmentation dataset
<p><strong>The HaN-Seg: Head and Neck Organ-at-Risk CT & MR Segmentation Dataset</strong> is a publicly available dataset of anonymized head and neck (HaN) images of 42 patients that underwent both CT and T1-weighted MR imaging for the purpose of image-guided radiotherapy planning. In addition, the dataset also contains reference segmentations of 30 organs-at-risk (OARs) for CT images in the form of binary segmentation masks, which were obtained by curating manual pixel-wise expert image annotations. A full description of the HaN-Seg dataset can be found in:</p> <p>G. Podobnik, P. Strojan, P. Peterlin, B. Ibragimov, T. Vrtovec, "HaN-Seg: The head and neck organ-at-risk CT & MR segmentation dataset", Medical Physics, 2023. <a href="https://doi.org/10.1002/mp.16197" target="_blank" rel="noopener">10.1002/mp.16197</a>,</p> <p>and any research originating from its usage is required to cite this paper.</p> <p>In parallel with the release of the dataset, the <strong><a href="https://han-seg2023.grand-challenge.org">HaN-Seg: The Head and Neck Organ-at-Risk CT & MR Segmentation Challenge</a></strong> is launched to promote the development of new and application of existing state-of-the-art fully automated techniques for OAR segmentation in the HaN region from CT images that exploit the information of multiple imaging modalities, in this case from CT and MR images. The task of the HaN-Seg challenge is to automatically segment up to 30 OARs in the HaN region from CT images in the devised test set, consisting of 14 CT and MR images of the same patients, given the availability of the training set (i.e. the herein publicly available HaN-Seg dataset), consisting of 42 CT and MR images of the same patients with reference 3D OAR binary segmentation masks for CT images.<br><br>Please find below a list of relevant publications that address: (1) the assessment of inter-observer and inter-modality variability in OAR contouring, (2) results of the HaN-Seg challenge, (3) development of our multimodal segmentation model, and (4) development of MR-to-CT image-to-image translation using diffusion models:</p> <ol> <li>G. Podobnik, B. Ibragimov, P. Strojan, P. Peterlin, T. Vrtovec, "vOARiability: Interobserver and intermodality variability analysis in OAR contouring from head and neck CT and MR images", Medical Physics, 2024. <a href="https://doi.org/10.1002/mp.16924" target="_blank" rel="noopener">10.1002/mp.16924</a>,</li> <li>G. Podobnik, B. Ibragimov, E. Tappeiner, et al., "HaN-Seg: The head and neck organ-at-risk CT and MR segmentation challenge", Radiotherapy and Oncology, 2024. <a href="https://doi.org/10.1016/j.radonc.2024.110410" target="_blank" rel="noopener">10.1016/j.radonc.2024.110410</a>,</li> <li>G. Podobnik, P. Strojan, P. Peterlin, B. Ibragimov, T. Vrtovec, "Multimodal CT and MR Segmentation of Head and Neck Organs-at-Risk", MICCAI 2023, 2023. <a href="https://doi.org/10.1007/978-3-031-43901-8_71" target="_blank" rel="noopener">10.1007/978-3-031-43901-8_71</a>,</li> <li>R. M. Šter, G. Podobnik, T. Vrtovec, "Diffusion-based MR-to-CT translation of head and neck images", SPIE Medical Imaging 2025, 2025. <a href="https://doi.org/10.1117/12.3047458" target="_blank" rel="noopener">10.1117/12.3047458</a>.</li> </ol>
Annotated dataset for the semantic segmentation of radishes
<p>This folder contains pictures of radishes collected on the PMF experimental field during Spring 2017. There are two kinds of labeled images in the following folders:</p> <p><br> - human annotations: human annotators draw polygons around each plant and those were then refined using an active contours algorithm.<br> - machine annotations: An SVM trained on the human annotations was used to produce labeled images. Images with bad segmentation were manually discarded.</p> <p>Each of these folder contains an images folder containing original pictures and a labels folder containing binary segmentation masks.</p>
Manual segmentation and classification dataset
<p>The archive contains 2 datasets for the Special issue "Neuroinformatics and Signal Processing" </p> <p>https://www.mdpi.com/journal/brainsci/special_issues/Neuroinformatics_Signal</p> <p>A segmentation dataset demonstrating Active Segmentation. The image is taken from the ISIBI 2012 dataset.</p> <p>A classification dataset - HeLa cells</p>
ReSyRIS: Real-Synthetic Rock Instance Segmentation dataset
<pre># ReSyRIS The Real-Synthetic Rock Instance Segmentation dataset (ReSyRIS) is created for training and evaluation of rock segmentation, detection and instance segmentation in (quasi-)extra-terrestrial environments. It consists of a set of annotated, real images of rocks on a lunar-like surface, a precisely mimicked synthetic version thereof, and respective synthetic assets for training data generation. In the folders, you find the following structure: - `stone_models`: all 36 .obj files of the 3d reconstructed stones - `test_data_realworld`: the real world recordings with accompanying ground truth - `test_data_synthetic`: the synthetic renderings matching approximately the real world recordings, with accompanying ground truth - `oaisys`: config files for rendering synthetic training data with oaisys If you find this dataset useful for your work please consider citing our paper: https://elib.dlr.de/194113/. </pre>
Line Segment in Document Images Datasets
<p>Those datasets are related to the accepted article to ICDAR 2023: "Linear Object Detection in Document Images<br> using Multiple Object Tracking" by Bernet et al.</p> <p>The official github repository is : https://github.com/EPITAResearchLab/bernet.23.icdar</p> <p>.png ground truth are labelled images where white pixels correspond to the background.</p> <p>.csv ground truth are using the following format:<br> ```<br> x,y,w,h # First line is the size of the interest area in the image<br> x1,y1,x2,y2 # Following lines are the coordinates of the extremities of the line<br> ...<br> xn,yn,xn+1,yn+1<br> ```</p>
2DeteCT - A large 2D expandable, trainable, experimental Computed Tomography dataset for machine learning: Slices 3,001-4,000 (reference reconstructions and segmentations)
<p>This upload contains the reference reconstructions and segmentation of slices 3,001 – 4,000 from the data collection described in</p> <p>Maximilian B. Kiss, Sophia B. Coban, K. Joost Batenburg, Tristan van Leeuwen, and Felix Lucka “"2DeteCT - A large 2D expandable, trainable, experimental Computed Tomography dataset for machine learning", <a href="https://doi.org/10.1038/s41597-023-02484-6"><em>Sci Data</em> <strong>10</strong>, 576 (2023)</a> or <a href="https://arxiv.org/abs/2306.05907">arXiv:2306.05907 (2023)</a></p> <p>Abstract:<br> "Recent research in computational imaging largely focuses on developing machine learning (ML) techniques for image reconstruction, which requires large-scale training datasets consisting of measurement data and ground-truth images. However, suitable experimental datasets for X-ray Computed Tomography (CT) are scarce, and methods are often developed and evaluated only on simulated data. We fill this gap by providing the community with a versatile, open 2D fan-beam CT dataset suitable for developing ML techniques for a range of image reconstruction tasks. To acquire it, we designed a sophisticated, semi-automatic scan procedure that utilizes a highly-flexible laboratory X-ray CT setup. A diverse mix of samples with high natural variability in shape and density was scanned slice-by-slice (5000 slices in total) with high angular and spatial resolution and three different beam characteristics: A high-fidelity, a low-dose and a beam-hardening-inflicted mode. In addition, 750 out-of-distribution slices were scanned with sample and beam variations to accommodate robustness and segmentation tasks. We provide raw projection data, reference reconstructions and segmentations based on an open-source data processing pipeline."</p> <p>The data collection has been acquired using a highly flexible, programmable and custom-built X-ray CT scanner, the FleX-ray scanner, developed by <a href="https://info.tescan.com/micro-ct">TESCAN-XRE NV,</a> located in the FleX-ray Lab at the <a href="https://www.cwi.nl/en/">Centrum Wiskunde & Informatica (CWI)</a> in Amsterdam, Netherlands. It consists of a cone-beam microfocus X-ray point source (limited to 90 kV and 90 W) that projects polychromatic X-rays onto a 14-bit CMOS (complementary metal-oxide semiconductor) flat panel detector with CsI(Tl) scintillator (Dexella 1512NDT) and 1536-by-1944 pixels, <span class="math-tex">\(74.8\mu m^2\)</span> each. To create a 2D dataset, a fan-beam geometry was mimicked by only reading out the central row of the detector. Between source and detector there is a rotation stage, upon which samples can be mounted. The machine components (i.e., the source, the detector panel, and the rotation stage) are mounted on translation belts that allow the moving of the components independently from one another.</p> <p>Please refer to the paper for all further technical details.</p> <p>The complete dataset can be found via the following links: <a href="https://doi.org/10.5281/zenodo.8014758">1-1000</a>, <a href="https://doi.org/10.5281/zenodo.8014766">1001-2000</a>, <a href="https://doi.org/10.5281/zenodo.8014787">2001-3000</a>, <a href="https://doi.org/10.5281/zenodo.8014829">3001-4000</a>, <a href="https://doi.org/10.5281/zenodo.8014874">4001-5000</a>, <a href="https://doi.org/10.5281/zenodo.8014907">OOD</a>.<br> The reference reconstructions and segmentations can be found via the following links: <a href="https://doi.org/10.5281/zenodo.8017583">1-1000</a>, <a href="https://doi.org/10.5281/zenodo.8017604">1001-2000</a>, <a href="https://doi.org/10.5281/zenodo.8017612">2001-3000</a>, <a href="https://doi.org/10.5281/zenodo.8017618">3001-4000</a>, <a href="https://doi.org/10.5281/zenodo.8017624">4001-5000</a>, <a href="https://doi.org/10.5281/zenodo.8017653">OOD</a>.</p> <p>The corresponding Python scripts for loading, pre-processing, reconstructing and segmenting the projection data in the way described in the paper can be found on <a href="https://github.com/mbkiss/2DeteCTcodes">github</a>. A machine-readable file with the used scanning parameters and instrument data for each acquisition mode as well as a script loading it can be found on the GitHub repository as well.</p> <p>Note: It is advisable to use the graphical user interface when decompressing the .zip archives. If you experience a zipbomb error when unzipping the file on a Linux system rerun the command with the UNZIP_DISABLE_ZIPBOMB_DETECTION=TRUE environment variable by setting in your .bashrc “export UNZIP_DISABLE_ZIPBOMB_DETECTION=TRUE”.</p> <p>For more information or guidance in using the data collection, please get in touch with</p> <p> Maximilian.Kiss [at] cwi.nl</p> <p> Felix.Lucka [at] cwi.nl</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.