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.
26
datasets available to search
ShareScore release 0.9.0
Dataset results
26 results for “stardist”
3D Nuclei annotations and StarDist 3D model(s) (rat brain)
<p><strong>Name</strong>: 3D Nuclei annotations and StarDist3D model(s) (rat brain)</p> <p><strong><em>Images: </em></strong>From a large tiling acquisition ( https://doi.org/10.5281/zenodo.6646128 ) individual Tile (xyz : 1024x1024x62) were downsampled and cropped (128x128x62). Four crops, from different tiles (./annotations_BIOP/images/) were manually annotated with ITK-SNAP (./annotations_BIOP/masks/)</p> <p>These four images, and their corresponding masks, were cropped into four quadrants (./crops_BIOP_v1/) in order to get 16 different images (64x64x62).</p> <p><strong><em>Conda environment</em></strong><em>: </em>A conda environment was created using the yml file <em>stardist0.8_TF1.15.yml</em></p> <p><strong><em>Training : </em></strong>Training was performed using the jupyter notebook <em>1-Training_notebook.ipynb</em>.<br> Three different trainings (with the same random seed, same anisotropy, patch size and grid) were performed and produced three different models (./models/)</p> <p>Validation images (from the random seed used) were exported to ease the visual inspection of the results(./val_rdm42/).</p> <p><strong><em>Validation: </em></strong>To save metrics in a csv file and compare predictions to the annotations the jupyter notebook <em>2-QC_notebook.ipynb </em>can be used on the validation folder.</p> <p><strong>Large images</strong>: To test the model on larger images one can use Whole_ds441.tif (or Crop_ds441.tif )<br> These images were obtained using the plugin <a href="https://imagej.net/plugins/bigstitcher/">BigSticher </a>on the raw data ( https://doi.org/10.5281/zenodo.6646128 ), resaved as h5 and exported the downsample by 4 version.</p> <p> </p> <p> </p>
StarDist Adipocyte Segmentation Training data, Training Notebook and Model
<p>Data from H&E human bone marrow whole slide scanner images used in the paper: "MarrowQuant 2.0: a digital pathology workflow assisting bone marrow evaluation in clinical and experimental hematology" (https://doi.org/10.21203/rs.3.rs-1860140/v1)</p> <p> </p> <p>292 image patches</p> <p>Ground truth were manually annotated using QuPath and split into 263 images for training and 29 for validation.</p> <p>Training in StarDist was done on a Windows 10 PC with an RTX 2080 GPU. The requirements file for installing a Python 3.7 environment to run the attached notebooks is provided (<strong>stardist-val.txt</strong>).</p> <p>The StarDist model configuration can be found in the Jupyter Notebook :</p> <pre><code>Adipocyte Training.ipynb</code></pre> <p>Model validation and metrics can be performed by running the notebook after finishing the <strong>Adipocyte Training</strong> notebook.</p> <pre><code>Quality Control.ipynb</code></pre> <p> </p>
Stardist model for Ascaidan embryo
<p>Stardist trained model for doing object detection of membrane labelled Ascadian mouse embryo cells.</p>
DeepBacs – Escherichia coli release from stationary phase - Bright field segmentation dataset and StarDist model
<p>Training and test images of live <em>E. coli</em> cells imaged under bright field 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 a bright field image of live <em>E. coli </em>cells of an overnight culture and the manually annotated segmentation mask.</p> <p> </p> <p><strong>Data type</strong>: Paired bright field and segmented mask images </p> <p><strong>Microscopy data type</strong>: 2D bright field images recorded at 2 min interval</p> <p><strong>Microscope</strong>: Nikon Eclipse Ti-E equipped with an Apo TIRF 1.49NA 100x oil immersion objective</p> <p><strong>Cell type</strong>: <em>E. coli</em> MG1655 wild type strain (CGSC #6300).</p> <p><strong>File format</strong>: .tif (8-bit)</p> <p><strong>Image size</strong>: 512 x 512 px² (106 nm / pixel), 19/15 individual frames (training/test dataset)</p> <p>512 x 512 px² (106 nm / pixel), 7 regions of interest with 20 frames @ 2 min time interval (live-cell time series)</p> <p><strong>Data annotation</strong>: Images were annotated using the Fiji freehand selection tool.</p> <p><strong>Image preprocessing</strong>: Time series were stabilized using the Fiji plugin StackReg and the 480 x 480 px center region was cropped</p> <p><strong>StarDist model</strong></p> <p>The StarDist 2D model was trained from scratch for 200 epochs on 33 paired image patches (image dimensions: (512, 512 px²), patch size: (512 x 512 px²)) with a batch size of 2, 80 rays, grid size 1, 4-fold data augmentation and a mae loss function, using the StarDist 2D ZeroCostDL4Mic notebook (v 1.13) (von Chamier & Laine et al., 2020). Key python packages used include tensorflow (v 0.1.12), Keras (v2.3.1), csbdeep (v 0.6.3), numpy (v 1.21.5), cuda (v 11.1.105). The training was accelerated using a Tesla K80 GPU.</p> <p>Model weights can be used with the ZeroCostDL4Mic StarDist 2D notebook or the Fiji StarDist plugin.</p> <p><br> <strong>Author(s)</strong>: Christoph Spahn<sup>1,2</sup>, Mike Heilemann<sup>1,3</sup></p> <p><strong>Contact email</strong>: christoph.spahn@mpi-marburg.mpg.de</p> <p><strong>Affiliation(s)</strong>: </p> <p>1) Institute of Physical and Theoretical Chemistry, Max-von-Laue Str. 7, Goethe-University Frankfurt, 60439 Frankfurt, Germany</p> <p>2) ORCID: 0000-0001-9886-2263 </p> <p>3) ORCID: 0000-0002-9821-3578 </p>
ProdgerLab-StarDist-HIV Target Cell Training Set
<p>40 annotated immunofluorescence microscopy images (600 microns x 600 microns) of foreskin tissue stained for CD3/CD4/CCR5/Nuclei. These images were used to train StarDist models used for the identification of HIV Target Cells in foreskin tissue section scans. </p>
Combining StarDist and TrackMate example 3 - Flow chamber dataset
<p><strong>Description</strong>: Contains a StarDist example training dataset, a test dataset, and the StarDist model generated using ZeroCostDL4Mic (see https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki/Stardist)</p> <p><strong>Training dataset</strong>: Paired microscopy images (brightfield) and corresponding masks</p> <p><strong>Microscopy data type</strong>: brightfield microscopy and masks obtained via manual segmentation (see <a href="https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki/Stardist">https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki/Stardist</a> for details about the segmentation)</p> <p><strong>Microscope</strong>: Images were acquired with a brightfield microscope (Zeiss Laser-TIRF 3 Imaging System, Carl Zeiss) and a 10X objective.</p> <p><strong>File format</strong>: .tif (8-bit for brightfield images and 8 and 16-bit for the masks)</p> <p><strong>Image size</strong>: 1024x1024 (Pixel size: 650 nm)</p>
A StarDist Journey (dataset and exercises)
<p>A dataset (with images of nuclear stainings) with some step-by-step exercises to discover <a href="https://github.com/stardist/stardist">StarDist</a>, the usefulness of the tool and its limitations.</p>
DeepBacs – Mixed segmentation dataset and StarDist model
<p>Mixed training and test images of <em>S. aureus</em>, <em>E. coli</em> and <em>B. subtilis </em>for cell segmentation using StarDist, as well as the trained StarDist model.</p> <p>Additional information can be found on this <a href="https://github.com/HenriquesLab/DeepBacs/wiki">github wiki</a>.</p> <p> </p> <p><strong>Data type</strong>: Paired bright field / fluorescence and segmented mask images</p> <p><strong>Microscopy data type</strong>: 2D widefield images; DIC and fluorescence for <em>S. aureus</em>, bright field images for <em>E. coli</em>, and fluorescence images for <em>B. subtilis</em></p> <p><strong>Microscopes</strong>: </p> <p><em>S. aureus</em>: </p> <p>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><em>E.coli</em>:</p> <p>Nikon Eclipse Ti-E equipped with an Apo TIRF 1.49NA 100x oil immersion objective</p> <p><em>B. subtilis</em>:</p> <p>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> </p> <p><strong>Cell types</strong>: <em>S. aureus</em> strain JE2, <em>E. coli </em>MG1655 (CGSC #6300) and <em>B. subtilis</em> strain SH130; all grown under agarose pads</p> <p><strong>File format</strong>: .tif (8-bit and 16-bit)</p> <p><strong>Image size</strong>: 512 x 512 px² @ 80 nm pixel size (S. aureus); 1024 x 1024 px² @ 79 nm pixel size (E. coli); 1024 x 1024 px² @ 65 nm pixel size (B. subtilis)</p> <p><strong>Image preprocessing</strong>: </p> <p><em>S. aureus:</em></p> <p>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><em>E. coli:</em></p> <p>Raw images were recorded in 16-bit mode (image size 512x512 px² @ 158 nm/px). Images were upscaled with a factor of 2 (no interpolation) to enable generation of higher-quality segmentation masks.</p> <p><em>B. subtilis</em>:</p> <p>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>StarDist model:</strong></p> <p>The StarDist 2D model was generated using the ZeroCostDL4Mic platform (Chamier et al., 2021). It was trained from scratch for 200 epochs (120 steps/epoch) on 155 paired image patches (image dimensions: (1024, 1024), patch size: (256,256)) with a batch size of 4, 10% validation data, 64 rays on grid 2, a learning rate of 0.0003 and a mae loss function, using the StarDist 2D ZeroCostDL4Mic notebook (v 1.12.2). Key python packages used include tensorflow (v 0.1.12), Keras (v 2.3.1), csbdeep (v 0.6.1), numpy (v 1.19.5), cuda (v 11.0.221). The training was accelerated using a Tesla P100GPU. The dataset was augmented by a factor of 3.</p> <p> </p> <p>The model weights can be used in the ZeroCostDL4Mic StarDist 2D notebook, the StarDist Fiji plugin or the TrackMate Fiji plugin (v7+).</p> <p> </p> <p><strong>Author(s)</strong>: Christoph Spahn<sup>1,2</sup>, Mike Heilemann<sup>1,3</sup>, Mia Conduit<sup>4</sup>, Séamus Holden<sup>4,5</sup>, Pedro Matos Pereira<sup>6,7</sup>, Mariana Pinho<sup>6,8</sup></p> <p><strong>Contact email</strong>: <a href="mailto:christoph.spahn@mpi-marburg.mpg.de">christoph.spahn@mpi-marburg.mpg.de</a>, <a href="mailto:Seamus.Holden@newcastle.ac.uk">Seamus.Holden@newcastle.ac.uk</a>, <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(s)</strong>: </p> <p>1) Institute of Physical and Theoretical Chemistry, Max-von-Laue Str. 7, Goethe-University Frankfurt, 60439 Frankfurt, Germany</p> <p>2) ORCID: 0000-0001-9886-2263 </p> <p>3) ORCID: 0000-0002-9821-3578</p> <p>4) Centre for Bacterial Cell Biology, Biosciences Institute, Newcastle University, NE2 4AX UK</p> <p>5) ORCID: 0000-0002-7169-907X</p> <p>6) Bacterial Cell Biology, Instituto de Tecnologia Química e Biológica António Xavier, Universidade Nova de Lisboa, Oeiras, Portugal</p> <p>7) ORCID: 0000-0002-1426-9540</p> <p>8) ORCID: 0000-0002-7132-8842</p>
Breast Cancer Nuclei images for DL Training + ZeroCostDL4Mic StarDist Model
<div> <p><strong>Training dataset:</strong><br>Paired microscopy images (fluorescence) and corresponding masks</p> <p>Microscopy data type: Fluorescence microscopy and masks obtained via manual correction of automatic segmentation with pre-trained StarDist model (see https://github.com/qupath/models/tree/main/stardist) </p> <p>Cells were imaged using a 20x objective with a 1x camera adapter was used in conjunction with a pco.edge 4.2 4MP camera on Pannoramic SCAN 150 scanner.</p> <p>Cell type: FFPE tissue sections were sliced from all cancer-containing paraffin blocks</p> <p>File format: .tif (8-bit for fluorescence and 16-bit for the masks)</p> <p> </p> <p><strong>StarDist Model:</strong><br>The StarDist model was generated using the ZeroCostDL4Mic platform (Chamier et al., 2021). This custom StarDist model was trained for 100 epochs using 80 manually annotated paired images (image dimensions: (257, 257)) with a batch size of 2, an augmentation factor of 10 and a mae loss function. The StarDist “Versatile fluorescent nuclei” model was used as a training starting point. Key python packages used include TensorFlow (v 2.2.0), Keras (v 1.1.2), CSBdeep (v 0.7.2), NumPy (v 1.21.6), Cuda (v 11..1.105). The training was accelerated using a Tesla P100GPU.<br>The model weights can be used in the ZeroCostDL4Mic StarDist 2D notebook or in the StarDist Fiji plugin. a QuPath-compatible model is also provided.</p> <p> </p> <p> </p> </div>
Segmenting cells in a spheroid in 3D using 2D StarDist within TrackMate
<p>3D image of cells in a spheroid, imaged on a confocal microscope, used in a tutorial to demonstrate how to hack TrackMate to segment cells in 3D using the 2D segmentation algorithms it ships.</p> <p>Image by Guillaume Jacquemet.</p> <p>For more details see https://imagej.net/plugins/trackmate/trackmate-stardist#generation-of-3d-labels-by-tracking-2d-labels-using-trackmate</p> <p> </p>
StarDist model for Arabidopsis using Resnet backbone
<p>Stardist model for Arabidopsis using Resnet backbone to be used in conjugation with U-Net model in vollseg setting</p>
ZeroCostDL4Mic - Stardist example training and test dataset
<p><strong>Name</strong>: ZeroCostDL4Mic - Stardist example training and test dataset</p> <p>(see <a href="http://https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki">our Wiki</a> for details)</p> <p> </p> <p><strong>Data type</strong>: Paired microscopy images (fluorescence) and corresponding masks</p> <p><strong>Microscopy data type</strong>: Fluorescence microscopy (SiR-DNA) and masks obtained via manual segmentation (see <a href="https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki/Stardist">https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki/Stardist</a> for details about the segmentation)</p> <p><strong>Microscope</strong>: Spinning disk confocal microscope with a 20x 0.8 NA objective</p> <p><strong>Cell type</strong>: DCIS.COM LifeAct-RFP cells</p> <p><strong>File format</strong>: .tif (16-bit for fluorescence and 8 and 16-bit for the masks)</p> <p><strong>Image size</strong>: 1024x1024 (Pixel size: 634 nm)</p> <p> </p> <p><strong>Author(s)</strong>: Johanna Jukkala<sup>1,2</sup> and Guillaume Jacquemet<sup>1,2</sup></p> <p><strong>Contact email</strong>: guillaume.jacquemet@abo.fi</p> <p><strong>Affiliation</strong> : </p> <p>1) Faculty of Science and Engineering, Cell Biology, Åbo Akademi University, 20520 Turku, Finland</p> <p>2) Turku Bioscience Centre, University of Turku and Åbo Akademi University, FI-20520 Turku, Finland</p> <p> </p> <p><strong>Associated publications</strong>: Unpublished</p> <p><strong>Funding bodies</strong>: G.J. was supported by grants awarded by the Academy of Finland, the Sigrid Juselius Foundation and Åbo Akademi University Research Foundation (CoE CellMech) and by Drug Discovery and Diagnostics strategic funding to Åbo Akademi University.</p>
StarDist_BF_cancer_cell_dataset_20x
<p>This repository contains a StarDist deep learning model and its training and validation datasets designed for segmenting cancer cells perfused over an endothelial cell monolayer captured at 20x magnification. Using computational methods, the initial dataset of 20 manually annotated images was augmented to 160 paired images. The model was trained over 400 epochs and achieved an average F1 Score of 0.921, demonstrating high accuracy in cell segmentation tasks.</p> <h3>Specifications</h3> <ul> <li> <p>Model: StarDist for cancer cell segmentation on endothelial cells (20x magnification)</p> </li> <li> <p>Training Dataset:</p> </li> <ul> <li> <p>Number of Original Images: 20 paired brightfield microscopy images and label masks</p> </li> <li> <p>Microscope: Nikon Eclipse Ti2-E, 20x objective</p> </li> <li> <p>Data Type: Brightfield microscopy images with manually segmented masks</p> </li> <li> <p>File Format: TIFF (.tif)</p> </li> <ul> <li> <p>Brightfield Images: 16-bit</p> </li> <li> <p>Masks: 8-bit</p> </li> </ul> <li> <p>Image Size: 1024 x 1022 pixels (Pixel size: 650 nm)</p> </li> </ul> <li> <p>Training Parameters:</p> </li> <ul> <li> <p>Epochs: 400</p> </li> <li> <p>Patch Size: 992 x 992 pixels</p> </li> <li> <p>Batch Size: 2</p> </li> </ul> <li> <p>Performance:</p> </li> <ul> <li> <p>Average F1 Score: 0.921</p> </li> <li> <p>Average IoU: 0.793</p> </li> </ul> <li> <p>Model Training: Conducted using ZeroCostDL4Mic (<a href="https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki/Stardist">https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki</a>)</p> </li> </ul> <p> </p> <div> <h3>Reference</h3> <div><strong>Fast label-free live imaging reveals key roles of flow dynamics and CD44-HA interaction in cancer cell arrest on endothelial monolayers</strong></div> </div> <div>Gautier Follain, Sujan Ghimire, Joanna W. Pylvänäinen, Monika Vaitkevičiūtė, Diana Wurzinger, Camilo Guzmán, James RW Conway, Michal Dibus, Sanna Oikari, Kirsi Rilla, Marko Salmi, Johanna Ivaska, Guillaume Jacquemet</div> <div>bioRxiv 2024.09.30.615654; doi: <a href="https://www.biorxiv.org/content/10.1101/2024.09.30.615654v1">https://doi.org/10.1101/2024.09.30.615654</a></div>
StarDist_AsPC1_Lifeact
<p>This repository includes a StarDist deep learning model designed for segmenting AsPC1 cells labeled with Lifeact from fluorescence microscopy images. The model distinguishes individual AsPC1 cells within clusters and separates them from the background. The model was trained on a small dataset and achieved an Intersection over Union (IoU) score of 0.884 and an F1 Score of 0.967, indicating high accuracy in cell segmentation.</p> <h3>Specifications</h3> <ul> <li> <p>Model: StarDist for segmenting AsPC1 cells in fluorescence microscopy images</p> </li> <li> <p>Training Dataset:</p> </li> <ul> <li> <p>Number of Images: 10 paired fluorescence microscopy images and label masks</p> </li> <li> <p>Microscope: Spinning disk confocal microscope (3i CSU-W1) with a 20x objective, NA 0.8</p> </li> <li> <p>Data Type: Fluorescence microscopy images of the AsPC1 Lifeact channel with manually segmented masks</p> </li> <li> <p>File Format: TIFF (.tif)</p> </li> <ul> <li> <p>Fluorescence Images: 16-bit</p> </li> <li> <p>Masks: 8-bit</p> </li> </ul> <li> <p>Image Size: 1024 x 1024 pixels (Pixel size: 0.6337 x 0.6337 µm²)</p> </li> </ul> <li> <p>Model Capabilities:</p> </li> <ul> <li> <p>Segment AsPC1 Cells: Detects individual AsPC1 cells from a cluster and separates them from the background</p> </li> <li> <p>Measure Intensity: Enables measurement of CD44, ICAM1, ICAM2, or Fibronectin intensity under individual cells in respective channels</p> </li> </ul> <li> <p>Performance:</p> </li> <ul> <li> <p>Average IoU: 0.884</p> </li> <li> <p>Average F1 Score: 0.967</p> </li> </ul> <li> <p>Model Training: Conducted using ZeroCostDL4Mic (<a href="https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki/Stardist">https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki</a>)</p> </li> </ul> <div> <h3>Reference</h3> <div><strong>Fast label-free live imaging reveals key roles of flow dynamics and CD44-HA interaction in cancer cell arrest on endothelial monolayers</strong></div> </div> <div>Gautier Follain, Sujan Ghimire, Joanna W. Pylvänäinen, Monika Vaitkevičiūtė, Diana Wurzinger, Camilo Guzmán, James RW Conway, Michal Dibus, Sanna Oikari, Kirsi Rilla, Marko Salmi, Johanna Ivaska, Guillaume Jacquemet</div> <div>bioRxiv 2024.09.30.615654; doi: <a href="https://www.biorxiv.org/content/10.1101/2024.09.30.615654v1">https://doi.org/10.1101/2024.09.30.615654</a></div> <p> </p>
StarDist_Fluorescent_cells
<p>This repository includes a StarDist deep learning model and its training and validation datasets for detecting fluorescently labeled cancer cells perfused over an endothelial cell monolayer. The model was trained on 66 images labeled with CellTrace and demonstrated high accuracy, achieving an average F1 Score of 0.877. The dataset and the trained model can be used for biomedical image analysis, particularly in cancer research.</p> <h3>Specifications</h3> <ul> <li> <p>Model: StarDist for cancer cell detection</p> </li> <li> <p>Training Dataset:</p> </li> <ul> <li> <p>Number of Images: 66 paired fluorescent microscopy images and label masks</p> </li> <li> <p>Microscope: Nikon Eclipse Ti2-E, 10x objective</p> </li> <li> <p>Data Type: Fluorescent microscopy images with manually segmented masks</p> </li> <li> <p>File Format: TIFF (.tif)</p> </li> <ul> <li> <p>Brightfield Images: 16-bit</p> </li> <li> <p>Masks: 8-bit</p> </li> </ul> <li> <p>Image Size: 1024 x 1024 pixels (Pixel size: 1.3205 μm)</p> </li> </ul> <li> <p>Training Parameters:</p> </li> <ul> <li> <p>Epochs: 200</p> </li> <li> <p>Patch Size: 1024 x 1024 pixels</p> </li> <li> <p>Batch Size: 2</p> </li> </ul> <li> <p>Performance:</p> </li> <ul> <li> <p>Average F1 Score: 0.877</p> </li> <li> <p>Average IoU: 0.646</p> </li> </ul> <li> <p>Model Training: Conducted using ZeroCostDL4Mic (<a href="https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki/Stardist">https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki</a>)</p> </li> </ul> <div> <h3>Reference</h3> <div><strong>Fast label-free live imaging reveals key roles of flow dynamics and CD44-HA interaction in cancer cell arrest on endothelial monolayers</strong></div> </div> <div>Gautier Follain, Sujan Ghimire, Joanna W. Pylvänäinen, Monika Vaitkevičiūtė, Diana Wurzinger, Camilo Guzmán, James RW Conway, Michal Dibus, Sanna Oikari, Kirsi Rilla, Marko Salmi, Johanna Ivaska, Guillaume Jacquemet</div> <div>bioRxiv 2024.09.30.615654; doi: <a href="https://www.biorxiv.org/content/10.1101/2024.09.30.615654v1">https://doi.org/10.1101/2024.09.30.615654</a></div>
StarDist_BF_Neutrophil_dataset
<p>This repository includes a StarDist deep learning model and its training and validation datasets for detecting neutrophils perfused over an endothelial cell monolayer. The model was trained on 36 manually annotated images, achieving an average F1 Score of 0.969. The dataset and model are intended for use in biomedical research, particularly for analyzing interactions between neutrophils and endothelial cells.</p> <h3>Specifications</h3> <ul> <li> <p>Model: StarDist for neutrophil detection on endothelial cells</p> </li> <li> <p>Training Dataset:</p> </li> <ul> <li> <p>Number of Images: 36 paired brightfield microscopy images and label masks</p> </li> <li> <p>Microscope: Nikon Eclipse Ti2-E, 20x objective</p> </li> <li> <p>Data Type: Brightfield microscopy images with manually segmented masks</p> </li> <li> <p>File Format: TIFF (.tif)</p> </li> <ul> <li> <p>Brightfield Images: 16-bit</p> </li> <li> <p>Masks: 8-bit</p> </li> </ul> <li> <p>Image Size: 1024 x 1022 pixels (Pixel size: 650 nm)</p> </li> </ul> <li> <p>Training Parameters:</p> </li> <ul> <li> <p>Epochs: 400</p> </li> <li> <p>Patch Size: 992 x 992 pixels</p> </li> <li> <p>Batch Size: 2</p> </li> </ul> <li> <p>Performance:</p> </li> <ul> <li> <p>Average F1 Score: 0.969</p> </li> <li> <p>Average IoU: 0.914</p> </li> </ul> <li> <p>Model Training: Conducted using ZeroCostDL4Mic (<a href="https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki/Stardist">https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki</a>)</p> </li> </ul> <div> <h3>Reference</h3> <div><strong>Fast label-free live imaging reveals key roles of flow dynamics and CD44-HA interaction in cancer cell arrest on endothelial monolayers</strong></div> </div> <div>Gautier Follain, Sujan Ghimire, Joanna W. Pylvänäinen, Monika Vaitkevičiūtė, Diana Wurzinger, Camilo Guzmán, James RW Conway, Michal Dibus, Sanna Oikari, Kirsi Rilla, Marko Salmi, Johanna Ivaska, Guillaume Jacquemet</div> <div>bioRxiv 2024.09.30.615654; doi: <a href="https://www.biorxiv.org/content/10.1101/2024.09.30.615654v1">https://doi.org/10.1101/2024.09.30.615654</a></div>
Stardist_MiaPaCa2_from_CD44
<p>This repository contains a StarDist deep learning model designed for segmenting MiaPaCa2 cells from the CD44 channel in fluorescence microscopy images. The model is capable of accurately segmenting individual MiaPaCa2 cells while excluding HUVECs. Trained on a small dataset, the model achieved an Intersection over Union (IoU) score of 0.884 and an F1 Score of 0.950, indicating high precision in cell segmentation.</p> <h3>Specifications</h3> <ul> <li> <p>Model: StarDist for segmenting MiaPaCa2 cells from the CD44 fluorescence channel</p> </li> <li> <p>Training Dataset:</p> </li> <ul> <li> <p>Number of Images: 8 paired fluorescence microscopy images and label masks</p> </li> <li> <p>Microscope: Spinning disk confocal microscope (3i CSU-W1) with a 20x objective, NA 0.8</p> </li> <li> <p>Data Type: Fluorescence microscopy images of the CD44 channel, obtained after immunofluorescence staining with primary and secondary antibodies and manually segmented masks</p> </li> <li> <p>File Format: TIFF (.tif)</p> </li> <ul> <li> <p>Fluorescence Images: 16-bit</p> </li> <li> <p>Masks: 8-bit</p> </li> </ul> <li> <p>Image Size: 920 x 920 pixels (Pixel size: 0.6337 x 0.6337 µm²)</p> </li> </ul> <li> <p>Model Capabilities:</p> </li> <ul> <li> <p>Segment MiaPaCa2 Cells: Accurately detects individual MiaPaCa2 cells while ignoring HUVECs</p> </li> <li> <p>Measure CD44 Intensity: Allows for the measurement of CD44 intensity around MiaPaCa2 cells, specifically from the CD44 channel</p> </li> </ul> <li> <p>Performance:</p> </li> <ul> <li> <p>Average IoU: 0.884</p> </li> <li> <p>Average F1 Score: 0.950</p> </li> </ul> <li> <p>Model Training: Conducted using ZeroCostDL4Mic (<a href="https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki/Stardist">https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki</a>)</p> </li> </ul> <div> <h3>Reference</h3> <div><strong>Fast label-free live imaging reveals key roles of flow dynamics and CD44-HA interaction in cancer cell arrest on endothelial monolayers</strong></div> </div> <div>Gautier Follain, Sujan Ghimire, Joanna W. Pylvänäinen, Monika Vaitkevičiūtė, Diana Wurzinger, Camilo Guzmán, James RW Conway, Michal Dibus, Sanna Oikari, Kirsi Rilla, Marko Salmi, Johanna Ivaska, Guillaume Jacquemet</div> <div>bioRxiv 2024.09.30.615654; doi: <a href="https://www.biorxiv.org/content/10.1101/2024.09.30.615654v1">https://doi.org/10.1101/2024.09.30.615654</a></div>
StarDist_HUVEC_nuclei_dataset
<p>This repository contains a StarDist deep learning model and its training and validation datasets for segmenting endothelial nuclei while ignoring cancer cells. The cancer cells were perfused over an endothelial cell monolayer. The initial dataset consisted of 17 images, where cancer cell nuclei were manually removed after segmentation with the StarDist Versatile Nuclei model. This dataset was augmented to 68 paired images using computational techniques like rotation and flipping. The model was trained for 200 epochs, achieving an average F1 Score of 0.976, demonstrating high accuracy in segmenting endothelial nuclei while excluding cancer cells.</p> <h3>Specifications</h3> <ul> <li> <p>Model: StarDist for segmenting endothelial nuclei while ignoring cancer cells</p> </li> <li> <p>Training Dataset:</p> </li> <ul> <li> <p>Number of Original Images: 17 paired predictions of nuclei and label images</p> </li> <li> <p>Augmented Dataset: Expanded to 68 paired images using rotation and flipping</p> </li> <li> <p>Source Image Generation: Generated using a pix2pix model trained to predict nuclei from brightfield images of cancer cells on top of an endothelium (DOI: 10.5281/zenodo.10617532)</p> </li> <li> <p>Target Image Generation: Masks obtained via manual segmentation</p> </li> <li> <p>File Format: TIFF (.tif)</p> </li> <ul> <li> <p>Brightfield Images: 8-bit</p> </li> <li> <p>Masks: 8-bit</p> </li> </ul> <li> <p>Image Size: 1024 x 1022 pixels (uncalibrated)</p> </li> </ul> <li> <p>Training Parameters:</p> </li> <ul> <li> <p>Epochs: 200</p> </li> <li> <p>Patch Size: 1024 x 1024 pixels</p> </li> <li> <p>Batch Size: 2</p> </li> </ul> <li> <p>Performance:</p> </li> <ul> <li> <p>Average F1 Score: 0.976</p> </li> <li> <p>Average IoU: 0.927</p> </li> </ul> <li> <p>Model Training: Conducted using ZeroCostDL4Mic (<a href="https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki/Stardist">https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki</a>)</p> </li> </ul> <div> <h3><strong>Reference</strong></h3> <div><strong>Fast label-free live imaging reveals key roles of flow dynamics and CD44-HA interaction in cancer cell arrest on endothelial monolayers</strong></div> </div> <div>Gautier Follain, Sujan Ghimire, Joanna W. Pylvänäinen, Monika Vaitkevičiūtė, Diana Wurzinger, Camilo Guzmán, James RW Conway, Michal Dibus, Sanna Oikari, Kirsi Rilla, Marko Salmi, Johanna Ivaska, Guillaume Jacquemet</div> <div>bioRxiv 2024.09.30.615654; doi: <a href="https://www.biorxiv.org/content/10.1101/2024.09.30.615654v1">https://doi.org/10.1101/2024.09.30.615654</a></div>
StarDist_BF_Monocytes_dataset
<p>This repository includes a StarDist deep learning model and its training and validation datasets for detecting mononucleated cells perfused over an endothelial cell monolayer. The model was trained on 27 manually annotated images and achieved an average F1 Score of 0.941. The dataset and model are helpful for biomedical research, especially in studying interactions between mononucleated and endothelial cells.</p> <h3>Specifications</h3> <ul> <li> <p>Model: StarDist for mononucleated cell detection on endothelial cells</p> </li> <li> <p>Training Dataset:</p> </li> <ul> <li> <p>Number of Images: 27 paired brightfield microscopy images and label masks</p> </li> <li> <p>Microscope: Nikon Eclipse Ti2-E, 20x objective</p> </li> <li> <p>Data Type: Brightfield microscopy images with manually segmented masks</p> </li> <li> <p>File Format: TIFF (.tif)</p> </li> <ul> <li> <p>Brightfield Images: 16-bit</p> </li> <li> <p>Masks: 8-bit</p> </li> </ul> <li> <p>Image Size: 1024 x 1022 pixels (Pixel size: 650 nm)</p> </li> </ul> <li> <p>Training Parameters:</p> </li> <ul> <li> <p>Epochs: 400</p> </li> <li> <p>Patch Size: 992 x 992 pixels</p> </li> <li> <p>Batch Size: 2</p> </li> </ul> <li> <p>Performance:</p> </li> <ul> <li> <p>Average F1 Score: 0.941</p> </li> <li> <p>Average IoU: 0.831</p> </li> </ul> <li> <p>Model Training: Conducted using ZeroCostDL4Mic (<a href="https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki/Stardist">https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki</a>)</p> </li> </ul> <h3>Reference</h3> <div><strong>Fast label-free live imaging reveals key roles of flow dynamics and CD44-HA interaction in cancer cell arrest on endothelial monolayers</strong></div> <div>Gautier Follain, Sujan Ghimire, Joanna W. Pylvänäinen, Monika Vaitkevičiūtė, Diana Wurzinger, Camilo Guzmán, James RW Conway, Michal Dibus, Sanna Oikari, Kirsi Rilla, Marko Salmi, Johanna Ivaska, Guillaume Jacquemet</div> <div>bioRxiv 2024.09.30.615654; doi: <a href="https://www.biorxiv.org/content/10.1101/2024.09.30.615654v1">https://doi.org/10.1101/2024.09.30.615654</a></div>
StarDist_BF_cancer_cell_dataset_10x
<p>This repository includes a StarDist deep learning model and its training dataset designed for segmenting cancer cells perfused over an endothelial cell monolayer captured at 10x magnification. The model was trained on 77 manually annotated images, with the dataset being computationally augmented during training by a factor of 8. The model was trained for 500 epochs and achieved an average F1 Score of 0.968, indicating high accuracy in segmenting cancer cells on endothelial cells.</p> <h3>Specifications</h3> <ul> <li> <p>Model: StarDist for cancer cell segmentation on endothelial cells (10x magnification)</p> </li> <li> <p>Training Dataset:</p> </li> <ul> <li> <p>Number of Images: 77 paired brightfield microscopy images and label masks</p> </li> <li> <p>Augmented Dataset: Computational augmentation by a factor of 8 during training</p> </li> <li> <p>Microscope: Nikon Eclipse Ti2-E, 10x objective</p> </li> <li> <p>Data Type: Brightfield microscopy images with manually segmented masks</p> </li> <li> <p>File Format: TIFF (.tif)</p> </li> <ul> <li> <p>Brightfield Images: 16-bit</p> </li> <li> <p>Masks: 8-bit or 16-bit</p> </li> </ul> <li> <p>Image Size: 1024 x 1022 pixels (pixel size: 1.3148 μm)</p> </li> </ul> <li> <p>Training Parameters:</p> </li> <ul> <li> <p>Epochs: 500</p> </li> <li> <p>Patch Size: 992 x 992 pixels</p> </li> <li> <p>Batch Size: 2</p> </li> </ul> <li> <p>Performance:</p> </li> <ul> <li> <p>Average F1 Score: 0.968</p> </li> <li> <p>Average IoU: 0.882</p> </li> </ul> <li> <p>Model Training: Conducted using ZeroCostDL4Mic (<a href="https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki/Stardist">https://github.com/HenriquesLab/ZeroCostDL4Mic/wiki</a>)</p> </li> </ul> <div> <h3>Reference</h3> <div><strong>Fast label-free live imaging reveals key roles of flow dynamics and CD44-HA interaction in cancer cell arrest on endothelial monolayers</strong></div> </div> <div>Gautier Follain, Sujan Ghimire, Joanna W. Pylvänäinen, Monika Vaitkevičiūtė, Diana Wurzinger, Camilo Guzmán, James RW Conway, Michal Dibus, Sanna Oikari, Kirsi Rilla, Marko Salmi, Johanna Ivaska, Guillaume Jacquemet</div> <div>bioRxiv 2024.09.30.615654; doi: <a href="https://www.biorxiv.org/content/10.1101/2024.09.30.615654v1">https://doi.org/10.1101/2024.09.30.615654</a></div>
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.