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.
282
datasets available to search
ShareScore release 0.7.1
Dataset results
282 results for “image segments”
Code and example images from: recolorize: An R package for flexible color segmentation of biological images
<p>Color pattern variation provides biological information in fields ranging from disease ecology to speciation dynamics. Comparing color pattern geometries across images requires color segmentation, where pixels in an image are assigned to one of a set of color classes shared by all images. Manual methods for color segmentation are slow and subjective, while automated methods can struggle with high technical variation in aggregate image sets. We present recolorize, an R package toolbox for human-subjective color segmentation with functions for batch-processing low-variation image sets and additional tools for handling images from diverse (high variation) sources. The package also includes export options for a variety of formats and color analysis packages. This paper illustrates recolorize for three example datasets, including high variation, batch processing, and combining with reflectance spectra, and demonstrates the downstream use of methods that rely on this output.</p>
Images supporting: Nondestructive, quantitative viability analysis of 3D tissue cultures using machine learning image segmentation
<p>Two image datasets (as zip files) including all images analyzed in the manuscript Nondestructive, quantitative viability analysis of 3D tissue cultures using machine learning image segmentation. Images are of pancreatic adenocarcinoma (PDAC) cystic spheroid samples grown in either BME or Matrigel. Some images have background noise in the form of iron oxide nanoparticles introduced to them.</p>
MatSeg DataSet and Benchmark For Zero-Shot Material States Segmentation From images
<h2>This is an old version for the new version see <a href="../records/11331618">https://zenodo.org/records/11331618</a></h2> <p> </p> <p>A Dataset and Benchmark for zero-shot segmentation of materials states described in: “Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic Data” Described in <strong><a href="https://arxiv.org/pdf/2403.03309.pdf">https://arxiv.org/pdf/2403.03309.pdf</a> </strong></p> <p>See ReadMe in the zip file for technical details.</p> <p> </p> <h2><strong>MatSeg Benchmark </strong></h2> <p>A benchmark for zero-shot material state segmentation. The benchmark contains 820 real-world images with a wide range of material states and settings. For example: food states (cooked/burned..), plants (infected/dry.), to rocks/soil (minerals/sediment), construction/metals (rusted, worn), liquids (foam/sediment), and many other states in a class-agnostic manner. The goal is to evaluate the segmentation of material materials without knowledge or pretraining on the material or setting. The focus is on materials with complex scattered boundaries, and gradual transition (like the level of wetness of the surface). The annotation of the benchmark is point-based and similarity-based. Hence, for each image, we select several points and regions (Figure 4). We group the points of the same materials into the same label, we also define a group of points that have partial similarity. For example points in group A are more similar to points in group B than to points in group C (In case materials A and B are similar to each other but not identical). This approach allows us to capture the complexity of gradual transition and partial similarities in the world. While also enabling dealing with complex scattered and blurry shapes without needing to annotate the full shape which in many cases is unclear or very hard.</p> <p>Files <a href="../api/records/10801191/draft/files/MatSegBenchmarkPart1of3.zip/content" target="_blank" rel="noopener noreferrer">MatSegBenchmark</a>*.zip</p> <h2><strong>MatSeg synthetic Dataset Samples </strong></h2> <p>Synthethic dataset of images of materials spread on object surfaces and their segmentation map.</p> <p>The synthetic dataset is a very big, sample of the dataset as been uploaded.</p> <p>Files: MatSegSynthehticDataSample*.zip</p> <p>The full dataset can be found in this URLS:</p> <p><a href="https://e.pcloud.link/publink/show?code=kZHCcnZOfzqInb3anSl7xzFBoqCDmkr2JKV">https://e.pcloud.link/publink/show?code=kZHCcnZOfzqInb3anSl7xzFBoqCDmkr2JKV</a></p> <p><a href="https://icedrive.net/s/SBb3g9WzQ5wZuxX9892Z3R4bW8jw">https://icedrive.net/s/SBb3g9WzQ5wZuxX9892Z3R4bW8jw</a></p> <p> </p> <p>Generation Script for the synthetic data:</p> <p><a href="https://github.com/sagieppel/MatSeg-Synthethic-Dataset-Generation-Script">https://github.com/sagieppel/MatSeg-Synthethic-Dataset-Generation-Script</a></p> <p><a href="../records/10822596/files/sagieppel/MatSeg-Synthethic-Dataset-Generation-Script-3.zip?download=1">https://zenodo.org/records/10822596</a></p> <p> </p> <p> </p> <p> </p>
Data from: Coronary artery segmentation in non-contrast calcium scoring CT images using deep learning
<p><strong>Abstract</strong></p> <p>Precise segmentation of coronary arteries in non-contrast Computed Tomography (CT) scans plays an important role in the assessment of the coronary artery disease, where it is the key component for evaluating the Calcium Score (Agatston et al. 1990). In the paper by Bujny et al. (2024), a deep-learning approach for high-precision segmentation of coronary arteries in non-contrast CT was proposed along with a novel method for generating Ground Truth (GT) test data (<em>test-GT</em>) via manual registration of high-resolution coronary tree models obtained based on contrast CT with the non-contrast CT scans. In this dataset, we present the inferences of the neural network model together with the corresponding <em>test-GT</em> samples, based on 6 CT scans from the openly available OrCaScore dataset (Wolterink et al. 2016). The geometrical models included in the dataset can be used both for inspection of the proposed deep learning model and for testing of new non-contrast coronary vessel segmentation approaches, which is a unique opportunity since, to the best of our knowledge, manual generation of GT for non-contrast coronary artery segmentation was not addressed so far due to very challenging character of this particular segmentation task.</p> <p> </p> <p><strong>Methods</strong></p> <p><strong><em>Manual Generation of test-GT</em></strong></p> <p>The geometric models of coronary arteries used for the evaluation of the proposed neural network model were generated according to the manual mesh-to-image registration process as described by Bujny et al. (2024). In this approach, the high-resolution coronary artery masks obtained based on contrast CT scans are manually aligned with the corresponding non-contrast CT images using tools available in the open-source 3D computer graphics software, Blender (<a href="https://www.blender.org/">https://www.blender.org/</a>). To ease the manual alignment process, specialized add-ons for medical image processing such as Cardiac add-on for Blender of Graylight Imaging (<a href="https://graylight-imaging.com/3d-modelling/">https://graylight-imaging.com/3d-modelling/</a>) can be used, as well. The STL models in this dataset were manually generated by a medical expert with 4 years of experience.</p> <p><strong><em>Segmentation of Coronary Arteries using a Deep Learning Model</em></strong></p> <p>For each of the cases presented in this dataset, we run an inference of an nnU-Net (Isensee et al. 2021) model trained according to the process described in our paper (Bujny et al. 2024). Since we use a standard nnU-Net, which utilizes a sliding window approach for processing of the CT scan, the context information within a patch is limited, which can lead to some false-positive detections. To mitigate this problem, we additionally post-process the inferences by eliminating small vessel fragments of less than 50 [mm^3] volume and structures outside of pericardium, which we segment using another nnU-Net model, SegTHOR (Lambert et al. 2020). The resulting geometric models are stored using the STL format and presented as green masks in the HTML reports with an embedded viewer based on the K3D-jupyter library (<a href="https://k3d-jupyter.org/">https://k3d-jupyter.org/</a>).</p> <p> </p> <p><strong>Dataset organization</strong></p> <p>The root folder contains 6 folders whose names correspond to the CT scans from the OrCaScore dataset (Wolterink et al. 2016). In each of the folders, there are the following 4 files available:</p> <ul> <li><span>‘manualGT_rater1.stl’ – high-resolution STL model of coronary arteries obtained via manual alignment of the geometric model segmented in contrast CT with the corresponding non-contrast CT scan by the first rater.</span> A sample belonging to the <em>test-GT</em> set (Bujny et al. 2024).</li> <li>‘manualGT_rater2.stl’ – corresponding <em>test-GT</em> sample by the second rater.</li> <li>‘ML.stl’ – post-processed inference of the nnU-Net ML model in the STL format.</li> <li>‘report.html’ – interactive HTML report consisting of a manually-aligned <em>test-GT</em> sample (red mask), the ML segmentation based on the non-contrast CT scan (green mask), and selected slices of the non-contrast CT scan. The reports contain the relevant information related to the scanning device and present the main segmentation quality metrics for the ML model inference.</li> </ul>
An Image Dataset for Training Deep Learning Segmentation Models to Identify Karst Sinkholes
<p>The image dataset was prepared for training deep learning image segmentation models to identify karst sinkholes. Information about the work can be found at (https://github.com/mvrl/sink-seg/). The dataset consists of a DEM image, an aerial image, and a binary sinkhole label image in an area in central Kentucky, USA. It also includes four images derived from the DEM image. The image dataset is sourced from publicly available data from Kentucky's Elevation Data & Aerial Photography Program (https://kyfromabove.ky.gov/) and Kentucky LiDAR-derived sinkholes (https://kgs.uky.edu/geomap).</p> <p> </p>
Diffraction images of a crystal of the F-BAR domain of PSTPIP1 (Proline-serine-threonine phosphatase-interacting protein 1) bound to the C-terminal homology (CTH) segment of the phosphatase LYP (PTPN22) (PDB entry 7AAM)
<p>Diffraction images of a crystal of the F-BAR domain of human PSTPIP1 (residues 1-289, Uniprot reference O43586-1) in complex with the CTH of LYP (residues 787-807, Uniprot Q9Y2R2-1).</p> <p>Data were collected on a single crystal at the beamline i03 of the Diamond Light Source synchrotron (Didcot, UK) using radiation of 0.99987 Å wavelength and a PILATUS3 6M detector. The dataset consists of 3 groups, each containing of 1800 images (0.1 degree oscillation per image), collected at three different positions of the same crystal. Crystal belongs to the space group P2(1)2(1)2(1) with unit cell dimensions a=48.0 Å, b=72.0 Å, c=205.0 Å. The asymmetric unit contains an homodimer of the F-BAR domain bound to a LYP-CTH (~53% solvent content), which is the biological complex.</p> <p>Diffraction data was notably anisotropic. The lowest resolution limit was 4.05 Å in the direction b* and the highest limits were 2.11 Å and 2.10 in the directions a* and c*, respectively.</p> <p> </p> <p>The structure derived form these data is published in:</p> <p>Manso, J.A., Marcos, T., Ruiz-Martín, V. Casas J, Alcón P, Sánchez Crespo M, Bayón Y, de Pereda JM, Alonso A <em>PSTPIP1-LYP phosphatase interaction: structural basis and implications for autoinflammatory disorders</em>. <strong>Cell. Mol. Life Sci</strong>. 79, 131 (2022). <a href="https://doi.org/10.1007/s00018-022-04173-w">https://doi.org/10.1007/s00018-022-04173-w</a></p> <p>The structure is available at the PDB under the code <strong>7AAM</strong>:</p> <p><a href="https://www.ebi.ac.uk/pdbe/entry/pdb/7aam">https://www.ebi.ac.uk/pdbe/entry/pdb/7aam</a></p>
A novel strategy for fully automated segmentation of supratentorial meningiomas: Use of pre-trained models and inclusion of normal brain images
<p>This repository is accompanying MRI datasets under the journal, titled: <strong>A novel strategy for fully automated segmentation of supratentorial meningiomas: Use of pre-trained models and inclusion of normal brain images</strong>. </p> <p>Nii_data.tar.gz (zipped) file includes MRI images of all patients described in the paper that are formatted as .nii.</p>
Supplementary Material of : Large-Scale 3D Image Segmentation Using Scattering Networks
<p>The reader will find here the supplementary material associated with the manuscript "Large-Scale 3D Image Segmentation Using<br> Scattering Networks" submitted to IEEE Transaction of Pattern Analysis and Machine Intelligence (TPAMI), 2022.</p>
Dataset of very-high-resolution satellite RGB images to train deep learning models to detect and segment high-mountain juniper shrubs in Sierra Nevada (Spain)
<p>This dataset provides annotated very-high-resolution satellite RGB images extracted from Google Earth to train deep learning models to perform instance segmentation of Juniperus communis L. and Juniperus sabina L. shrubs. All images are from the high mountain of Sierra Nevada in Spain. The dataset contains 810 images (.jpg) of size 224x224 pixels. We also provide partitioning of the data into Train (567 images), Test (162 images), and Validation (81 images) subsets. Their annotations are provided in three different .json files following the COCO annotation format.</p>
A Dataset of Synthetic Images of Outdoor Scenes Taken from Sidewalks, for Temporal Semantic Segmentation Applications
<p>This dataset has been generated using the CARLA simulator (release 0.9.11), an open-source 3D simulator for experiments in autonomous vehicle, based on the Unreal Engine game engine. It comes with pre-made city environment maps. CARLA is distributed with several integrated maps as well as parameters to increase the variety in the dataset. In the release that we have used, there are 13 semantic segmentation classes: None, Building, Fence, Other, Pedestrian, Pole, Lane-marking, Road, Sidewalk, Vegetation, Vehicle, Wall, and Traffic sign. The "None" category corresponds to textures that are not part of an object, such as lawns which are not part of "Vegetation", or sky. In the “Other” category are found objects that are not included in the other classes like plant and flower pots. For smart mobility applications, the “Sidewalks” and “Road” classes are of particular importance to find the way forward, as well as “Buildings” and “Poles” for obstacle avoidance. Sequences are made of 4 images. The dataset is composed of 46436 frames (11609 sequences) partitioned in 41024 frames (10256 sequences) for train, 2696 frames (674 sequences) for validation, and 2716 for test (679 sequences). The size of the images is 800 x 600 (resp. width x height).</p> <p>Additionaly, we have generated another smaller dataset with images taken from 2 different viewpoints: one located on the road and the other located on the sidewalk. The number of frames for train/validation/test is respectively 7288 (1822 sequences) partitioned in 6344 (1687 sequences) for train, 416 frames (104 sequences) for validation, and 424 for test (106 sequences). This smaller dataset is aimed at showing the importance of the viewpoint in the result of semantic segmentation. This can be done by cross-validation: learning on images taken from a viewpoint located on the road and test on images with a viewpoint located on the sidewalk, and vice versa.</p>
Data from: imageseg: An R package for deep learning-based image segmentation
<p>1. Convolutional neural networks (CNNs) and deep learning are powerful and robust tools for ecological applications, and are particularly suited for image data. Image segmentation (the classification of all pixels in images) is one such application and can for example be used to assess forest structural metrics. While CNN-based image segmentation methods for such applications have been suggested, widespread adoption in ecological research has been slow, likely due to technical difficulties in implementation of CNNs and lack of toolboxes for ecologists.</p> <p>2. Here, we present R package imageseg which implements a CNN-based workflow for general-purpose image segmentation using the U-Net and U-Net++ architectures in R. The workflow covers data (pre)processing, model training, and predictions. We illustrate the utility of the package with image recognition models for two forest structural metrics: tree canopy density and understory vegetation density. We trained the models using large and diverse training data sets from a variety of forest types and biomes, consisting of 2877 canopy images (both canopy cover and hemispherical canopy closure photographs) and 1285 understory vegetation images.</p> <p>3. Overall segmentation accuracy of the models was high with a Dice score of 0.91 for the canopy model and 0.89 for the understory vegetation model (assessed with 821 and 367 images, respectively). The image segmentation models performed significantly better than commonly used thresholding methods, and generalized well to data from study areas not included in training. This indicates robustness to variation in input images and good generalization strength across forest types and biomes.</p> <p>4. The package and its workflow allow simple yet powerful assessments of forest structural metrics using pre-trained models. Furthermore, the package facilitates custom image segmentation with single or multiple classes and based on color or grayscale images, e.g. for applications in cell biology or for medical images. Our package is free, open source, and available from CRAN. It will enable easier and faster implementation of deep learning-based image segmentation within R for ecological applications and beyond.</p>
Micro-CT Imaging Dataset on ex-vivo Ovine Functional Spinal Segments as Healthy, Injured and Treated with Cement Discoplasty
<p>General information:</p> <p>- This dataset contains micro-CT images and mechanical test data from ovine functional spinal units (FSU). <br> - The micro-CT data was produced using a Bruker SkyScan 1172. The settings for the scans are given in the '.log' files in each folder. <br> - The compression testing was conducted on an MTS 858 Mini Bionix T/II. The settings for each test can be found in test '.txt' files.<br> - In short, every FSU was mechanically tested in compression under different conditions. Before and after every test, the FSUs were scanned to ensure there was no damage<br> to the sample. More information can be found in the related publication: <br> - The mechanical testing data is arranged in folders with consecutive cycles. It is highly recommended to use the last three cycles for analysis. </p> <p>Data set notation:</p> <p>- All the datasets are noted by Sheep number. Sh7 = Sheep 7; Sh8 = Sheep 8; Sh9 = Sheep 9. In the publication, the numbers were switched to 1,2,3 respectively.<br> - files denoted with '_rec' contain the reconstruction of the projection images. <br> - 'Tested' or 'After test' files refers to the scan after mechanical testing. </p>
Segmentation masks of ZooScan images focusing on images with several objects separated by a human operator
<p>All information is available from the original publication page: https://doi.org/10.17882/99663</p>
Automated Segmentation of Large Image Datasets using Artificial Intelligence for Microstructure Characterisation and Damage Analysis
<p>Many properties of commonly used materials are driven by their microstructure, which can be influenced<br>by the composition and manufacturing processes. To optimise future materials, understanding the<br>microstructure is critically important. Here, we present two novel approaches based on artificial intelligence<br>that allow the segmentation of the phases of a microstructure for which simple numerical approaches, such<br>as thresholding, are not applicable: One is based on the nnU-Net neural network, and the other on generative<br>adversarial networks (GAN).<br>Using scanning electron microscopy images collected from large areas (~1 mm²) of dual-phase steels as a<br>case study, we demonstrate how both methods effectively segment intricate microstructural details,<br>including martensite, ferrite, and damage sites, for subsequent analysis.<br>Either method shows substantial generalizability across a range of image sizes and conditions, including<br>heat-treated microstructures with different phase configurations. The nnU-Net excels in mapping large<br>image areas. Conversely, the GAN-based method performs reliably on smaller images, providing greater<br>step-by-step control and flexibility over the segmentation process.<br>This study highlights the benefits of segmented microstructural data for various purposes, such as<br>calculating phase fractions, modelling material behaviour through finite element simulation, and<br>conducting geometrical analyses of damage sites and the local properties of their surrounding<br>microstructure.</p> <p>https://doi.org/10.1016/j.matdes.2024.113031</p>
Train and Evaluation Code, Road Classification Models and Test set of the paper "Insights into the Effects of Image Overlap and Image Size on Semantic Segmentation Models Trained for Road Surface Area Extraction from Aerial Orthophotography"
<p>This repository contains the Python scripts built for training and evaluation of the implementation, together with the test data and the resulting road segmentation models corresponding to the paper "Insights into the Effects of Image Overlap and Image Size on Semantic Segmentation Models Trained for Road Surface Area Extraction from Aerial Orthophotography". The scripts make use of the Tensorflow with Keras framework and their additional required dependencies.</p> <p>The training and validation set is based on the binary SROADEX dataset (<a href="../records/6482346">https://zenodo.org/records/6482346</a>) that was re-split into tiles that feature the image resolutions (256 x 256, 512 x 512, and 1024 x 1024 pixels) and image overlaps (0% and 12.5%) considered in this study. The data have been generated using scripts developed in Python using Open Source libraries (GDAL/OGR and MapScript) for rasterization of vector cartography that represents the axes of the different types of roads (urban, interurban and rural). This binary road data contains information from 16 full orthoimages (28.5 km * 18.5 km) with spatial resolution of 0.5 m/pixel from the insular and peninsular Spanish territory. Due to the size on disk of approximately 492 gigabytes, this training and validation data is only available upon request from the corresponding author. The test set has been generated from a novel area from Palencia (Spain) and features 18 million pixels labelled with the positive "Road" class. The test sets are provided in the repository for each resolution (with no overlap), so that additional DL models can be evaluated on the same data and compared with the results achieved in this study.</p> <p>The structure of the information shared in this repository is as follows:<br>The scripts have been grouped by tile resolution (256, 512 and 1024). First, the test set and the evaluation script can be found. For each tile resolution, there are two subfolders (corresponding to the "no overlap" and "12.5% overlap"). In each case, the Python scripts for training the models in the three repetitions are shared, and the trained models (H5 format) are shared in compressed form. Finally, for each resolution we also share the testing dataset which consists of two folders.</p> <p>The material is distributed under a CC-BY 4.0 license.</p>
UAV Railroad Images for Segmentation and Obstacle Detection
<p><span>UAV-RSOD dataset contains five different types of obstacles including </span><span>person, boulder, barrel, branch, jerry can, and iron rod. This dataset supports the development and evaluation of computer vision models for railroad-related applications, such as autonomous train navigation, obstacle detection in railroad, railroad extraction and safety monitoring. </span><span> </span><span>The DJI Phantom 4 PRO UAV </span><span>Drone was used to take all the videos and images in the Indian Railways, Tiruchirapalli city of Tamilnadu, India.</span></p> <p><span>Version 1: 315 Images with Labelling, Masking for Segmentation Process and without any Data Augmentation techniques applied</span></p> <p><span>Version 2: 2002 Annotated Images with Data Augmentation techniques applied (Rotate, Flip, etc) for Obstacle Detection</span></p>
BRAIN Journal-Performance Analysis of Unsupervised Clustering Methods for Brain Tumor Segmentation-Figure 3:(a) Input MR Image (b) Enhanced Image (c) Segmented Tumor (d) Located brain tumor
<p>Figure 3 shows three different original brain MR images, contrast enhancement of the<br> images, segmented images using K-means algorithm and finally located tumor. Fig 1.4 shows the<br> performance of the unsupervised clustering methods with the no. of tumor pixels and execution<br> time to locate the brain tumor.</p>
BRAIN Journal-Automatic Anthropometric System Development Using Machine Learning-Figure 3. (3.a) – The flowchart of Graph cuts method; (3.b)- the result of Graph cuts image segmentation.
<p>Figure 3 describes the steps implemented Graph cuts algorithm for the segmentation of human body parts. The results obtained are 5 main sections that include the hands, the legs, the center of the body (chest, waist, hips), and the head. The result of the display image is taken from the human image database, which was collected by us (Нгуен, 2016). </p>
Segmentation of Nuclei in Histopathology Images by deep regression of the distance map
<p>This dataset has been annonced in our accepted paper "Segmentation of Nuclei in Histopathology Images by deep regression of the distance map" in Transcation on Medical Imaging on the 13th of August.<br> This dataset consists of 50 annotated images, divided into 11 patients.</p> <p> </p> <p>v1.1 (27/02/19): Small corrections to a few pixel that were labelled nuclei but weren't.</p>
Image segmentation masks for curved arrows on molecular images from chemical reaction mechanism images
<p>The dataset presented herein is designed as a ground truth for image segmentation tasks focused on noise extraction in Optical Chemical Structure Recognition (OCSR) processes. It comprises 73 manually extracted and annotated images from real reaction mechanism images, along with 5320 synthetic molecular images generated using RDKit, each featuring computer-drawn curved arrows on random locations on the molecular image pertinent to their respective tasks. Curved arrows are prevalent in chemical reaction mechanism images and significantly impact the accuracy of molecular identity recognition. This dataset aims to enhance OCSR tasks by enabling the pretreatment of molecular images to remove noise, thereby improving molecular recognition accuracy.</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.