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.
20
datasets available to search
ShareScore release 0.9.0
Dataset results
20 results for “Digital Pathology”
Artefact segmentation in digital pathology whole-slide images
<p>Dataset with examples of Artefacts in Digital Pathology.</p> <p>The dataset contains 22 Whole-Slide Images, with H&E or IHC staining, showing various types and levels of defect to the slides. Annotations were made by a biomedical engineer based on examples given by an expert.</p> <p>The dataset is split in different folders:</p> <ul> <li>train <ul> <li>18 whole-slide images (extracted at 1.25x & 2.5x magnification)</li> <li>All from the same Block (colorectal cancer tissue)</li> <li>1/2 with H&E & 1/2 with anti-pan-cytokeratin IHC staining.</li> </ul> </li> <li>validation <ul> <li>3 whole-slide images (1.25x + 2.5x mag)</li> <li>2 from the same Block as the training set (1 IHC, 1 H&E)</li> <li>1 from another Block (IHC anti-pan-cytokerating, gastroesophageal junction lesion)</li> </ul> </li> <li>validation_tiles <ul> <li>patches of varying sizes taken from the 3 validation whole-slide images @1.25x magnification.</li> <li>7 patches from each slide.</li> </ul> </li> <li>test <ul> <li>1 whole-slide image (1.25x + 2.5x mag)</li> <li>From another block: IHC staining (anti-NR2F2), mouth cancer</li> </ul> </li> </ul> <p>For the train, validation and test whole-slide images, each slide has:<br> - The RGB images @1.25x & 2.5x mag<br> - The corresponding background/tissue masks<br> - The corresponding annotation masks containing examples of artefacts (note that a majority of artefacts are not annotated. In total, 918 artefacts are in the train set)</p> <p>For the validation tiles, the following table gives the "patch-level" supervision:</p> <p>tile# Artefact(s)<br> 00 None/Few<br> 01 Tear&Fold<br> 02 Ink<br> 03 None/Few<br> 04 None/Few<br> 05 Tear&Fold<br> 06 Tear&Fold + Blur<br> 07 Knife damage<br> 08 Knife damage<br> 09 Ink<br> 10 None/Few<br> 11 Tear&Fold<br> 12 Tear&Fold<br> 13 None/Few<br> 14 None/Few<br> 15 Knife damage<br> 16 Tear&Fold<br> 17 None/Few<br> 18 None/Few<br> 19 Blur<br> 20 Knife damage</p>
Digital Pathology Dataset for Prostate Cancer Diagnosis
<p>Links to code and <em>Patterns</em> paper:</p> <p>1. <a href="https://10.5281/zenodo.7152962">Multi-lens Neural Machine (MLNM) Code</a></p> <p>2. <a href="https://www.cell.com/patterns/fulltext/S2666-3899(22)00274-4">An AI-assisted Tool For Efficient Prostate Cancer Diagnosis in Low-grade and Low-volume Cases</a></p> <p>Digitized hematoxylin and eosin (H&E)-stained whole-slide-images (WSIs) of 40 prostatectomy and 59 core needle biopsy specimens were collected from 99 prostate cancer patients at Tan Tock Seng Hospital, Singapore. There were 99 WSIs in total such that each specimen had one WSI. H&E-stained slides were scanned at 40× magnification (specimen-level pixel size 0·25μm × 0·25μm) using Aperio AT2 Slide Scanner (Leica Biosystems). Institutional board review from the hospital were obtained for this study, and all the data were de-identified.</p> <p>Prostate glandular structures in core needle biopsy slides were manually annotated and classified using the ASAP annotation tool (<a href="https://computationalpathologygroup.github.io/ASAP/">ASAP</a>). A senior pathologist reviewed 10% of the annotations in each slide, ensuring that some reference annotations were provided to the researcher at different regions of the core. It is to be noted that partial glands appearing at the edges of the biopsy cores were not annotated.</p> <p> </p> <p><strong>Whole Slide Image Dataset </strong></p> <p>Whole Slide Image dataset containing 99 images in SVS format with corresponding annotations in XML format are provided in WSI.zip. Available patient grading for the WSIs are provided in 'gleason_score_mapped.txt'. These XML annotations can be parsed using the code in official repository.</p> <p><strong>Cropped Image Dataset </strong></p> <p>Patches of size 512 × 512 pixels were cropped from the WSI (Whole Slide Image Dataset) at resolutions 5×, 10×, 20×, and 40× with an annotated gland centered at each patch. This dataset contains these cropped images.</p> <p>This dataset is used to train the two AI models for Gland Segmentation (99 patients) and Gland Classification (46 patients). Tables 1 and 2 illustrate both gland segmentation and gland classification datasets. We have put the two corresponding sub-datasets as two zip files as follows:</p> <ol> <li>gland_segmentation_dataset.zip</li> <li>gland_classification_dataset.zip</li> </ol> <p><strong>Table 1:</strong> The number of slides and patches in training, validation, and test sets for gland segmentation task. There is one H&E stained WSI for each prostatectomy or core needle biopsy specimen.</p> <table> <tbody> <tr> <td> <p> </p> </td> <td> <p><strong>#Slides</strong></p> </td> <td> <p> </p> </td> <td> <p> </p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p> </p> </td> <td> <p>Train</p> </td> <td> <p>Valid</p> </td> <td> <p>Test</p> </td> <td> <p><strong>Total</strong></p> </td> </tr> <tr> <td> <p>Prostatectomy</p> </td> <td> <p>17</p> </td> <td> <p>8</p> </td> <td> <p>15</p> </td> <td> <p>40</p> </td> </tr> <tr> <td> <p>Biopsy</p> </td> <td> <p>26</p> </td> <td> <p>13</p> </td> <td> <p>20</p> </td> <td> <p>59</p> </td> </tr> <tr> <td> <p><strong>Total</strong></p> </td> <td> <p>43</p> </td> <td> <p>21</p> </td> <td> <p>35</p> </td> <td> <p>99</p> </td> </tr> <tr> <td> <p> </p> </td> <td> <p><strong>#Patches</strong></p> </td> <td> <p> </p> </td> <td> <p> </p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p> </p> </td> <td> <p>Train</p> </td> <td> <p>Valid</p> </td> <td> <p>Test</p> </td> <td> <p><strong>Total</strong></p> </td> </tr> <tr> <td> <p>Prostatectomy</p> </td> <td> <p>7795</p> </td> <td> <p>3753</p> </td> <td> <p>7224</p> </td> <td> <p>18772</p> </td> </tr> <tr> <td> <p>Biopsy</p> </td> <td> <p>5559</p> </td> <td> <p>4028</p> </td> <td> <p>5981</p> </td> <td> <p>15568</p> </td> </tr> <tr> <td> <p><strong>Total</strong></p> </td> <td> <p>13354</p> </td> <td> <p>7781</p> </td> <td> <p>13205</p> </td> <td> <p>34340</p> </td> </tr> </tbody> </table> <p><strong>Table 2:</strong> The number of slides and patches in training, validation, and test sets for gland classification task. There is one H&E stained WSI for each prostatectomy or core needle biopsy specimen. The gland classification datasets are the subsets of the gland segmentation datasets. <strong>GS</strong>: Gleason Score. <strong>B</strong>: Benign. <strong>M</strong>: Malignant.</p> <table> <tbody> <tr> <td> <p> </p> </td> <td> <p><strong>#Slides (GS 3+3:3+4:4+3)</strong></p> </td> <td> <p> </p> </td> <td> <p> </p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p> </p> </td> <td> <p>Train</p> </td> <td> <p>Valid</p> </td> <td> <p>Test</p> </td> <td> <p><strong>Total</strong></p> </td> </tr> <tr> <td> <p>Biopsy</p> </td> <td> <p>10:9:1</p> </td> <td> <p>3:7:0</p> </td> <td> <p>6:10:0</p> </td> <td> <p>19:26:1</p> </td> </tr> <tr> <td> <p> </p> </td> <td> <p><strong>#Patches (B:M)</strong></p> </td> <td> <p> </p> </td> <td> <p> </p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p> </p> </td> <td> <p>Train</p> </td> <td> <p>Valid</p> </td> <td> <p>Test</p> </td> <td> <p><strong>Total</strong></p> </td> </tr> <tr> <td> <p>Biopsy</p> </td> <td> <p>1557:2277</p> </td> <td> <p>1216:1341</p> </td> <td> <p>1543:2718</p> </td> <td> <p>4316:6336</p> </td> </tr> </tbody> </table> <p><strong>NB:</strong> Gland classification folder (gland_classification_dataset.zip) may contain extra patches, labels of which could not be identified from H&E slides. They were not used in the machine learning study.</p>
A formative usability study of workflow management systems in label-free digital pathology - Data and Code
<p>This repository holds the necessary data and code as well as a descriptive Readme file that was used for our publication "A formative usability study of workflow management systems in label-free digital pathology" by Markus Jelonek et al. (2022), submitted to F1000Research.</p> <p> </p> <p>Abstract:</p> <p>We present a formative usability study that investigates the usability of different<br> workflow management systems in the field of biomedical data analysis. Specifically, we study a task in the field of so-called label-free digital pathology and investigate one graphical user interface based workflow and one script-based workflow to solve the task. Our main intention is to gain first insights into the systematic study of usability in the context of biomedical image analysis, and formulate experiences and guidelines for future usability studies dealing with workflow management systems. Embedded in a specific setup dealing with label-free digital pathology, the core question behind our contribution is how usability studies for scientific workflow management can be conducted, and how they can be used systematically to improve such tools. Further, we address specific questions about the resource utilisation and management of usability studies, including the recruitment of participants as well as the design of specific workflows to be investigated.</p>
A formative usability study of workflow management systems in label-free digital pathology - Questionnaires
<p>This repository holds the necessary questionnaires, participant data, interview questions and data, as well as a descriptive Readme file that was used for our publication "A formative usability study of workflow management systems in label-free digital pathology" by Markus Jelonek et al. (2022), submitted to F1000Research.</p> <p> </p> <p>Abstract:</p> <p>We present a formative usability study that investigates the usability of different<br> workflow management systems in the field of biomedical data analysis. Specifically, we study a task in the field of so-called label-free digital pathology and investigate one graphical user interface based workflow and one script-based workflow to solve the task. Our main intention is to gain first insights into the systematic study of usability in the context of biomedical image analysis, and formulate experiences and guidelines for future usability studies dealing with workflow management systems. Embedded in a specific setup dealing with label-free digital pathology, the core question behind our contribution is how usability studies for scientific workflow management can be conducted, and how they can be used systematically to improve such tools. Further, we address specific questions about the resource utilisation and management of usability studies, including the recruitment of participants as well as the design of specific workflows to be investigated.</p>
Run of digital pathology tissue/tumor prediction workflow
<p>This dataset is an <a href="https://www.researchobject.org/ro-crate/">RO-Crate</a> representation of an execution of the tissue/tumor prediction workflow for digital pathology from <a href="https://github.com/crs4/deephealth-pipelines/tree/c54840df08742e3aa454394e0e74d15fbd640f07">crs4/deephealth-pipelines</a>. It follows the <a href="https://w3id.org/ro/wfrun/provenance/0.1">Provenance Run Crate</a> profile. The workflow has been run with <a href="https://github.com/common-workflow-language/cwltool/tree/3.1.20230213100550">cwltool</a>, using the --provenance option to generate a <a href="https://doi.org/10.1093/gigascience/giz095">CWLProv</a> RO bundle, and then converted to an RO-Crate using <a href="https://github.com/ResearchObject/runcrate/tree/755fb7f0a8ba6fc238a2cb7a3218175644eb78b5">runcrate</a>. The input dataset is <a href="https://openslide.cs.cmu.edu/download/openslide-testdata/Mirax/Mirax2-Fluorescence-2.zip">Mirax2-Fluorescence-2</a> by Yves Sucaet, from the <a href="https://openslide.cs.cmu.edu/download/openslide-testdata/Mirax/">MIRAX test data</a>.<br> </p>
StreamFlow run of digital pathology tissue/tumor prediction workflow
<p>This dataset is an <a href="https://www.researchobject.org/ro-crate/">RO-Crate</a> representation of an execution of the tissue/tumor prediction workflow for digital pathology from <a href="https://github.com/crs4/deephealth-pipelines/tree/c54840df08742e3aa454394e0e74d15fbd640f07">crs4/deephealth-pipelines</a>. It follows the <a href="https://w3id.org/ro/wfrun/provenance/0.1">Provenance Run Crate</a> profile. The workflow has been run with <a href="http://streamflow.di.unito.it">StreamFlow</a>, using the following commands to produce an RO-Crate bundle:</p> <pre><code class="language-bash"># Run the pipeline streamflow run \ --name ml-predict-pipeline-streamflow \ streamflow.yml # Generate the RO-Crate bundle streamflow prov \ --add-file src=README.md,dst=/README.md,about="{\"@id\":\"./\"}",encodingFormat=text/markdown \ --add-property \./.license=https://spdx.org/licenses/MIT \ --add-property \./.name="DeepHealth Pipeline" \ --add-property \./.description="Run of digital pathology tissue/tumor prediction workflow" \ --file streamflow.yml \ ml-predict-pipeline-streamflow</code></pre> <p>The input dataset is <a href="https://openslide.cs.cmu.edu/download/openslide-testdata/Mirax/Mirax2-Fluorescence-2.zip">Mirax2-Fluorescence-2</a> by Yves Sucaet, from the <a href="https://openslide.cs.cmu.edu/download/openslide-testdata/Mirax/">MIRAX test data</a>.</p>
Digital Pathology Dataset for Breast Cancer Diagnosis
<p>Links to code:<br><a href="https://zenodo.org/records/14294426">Tissue Region Segmentation Code</a><br>This dataset comprises high-quality <strong>immunohistochemistry (IHC)</strong> and <strong>Haematoxylin and Eosin (H&E)</strong> whole slide images (WSIs) of breast tissues, provided in <strong>.svs format</strong>.</p> <ul> <li>The <strong>IHC dataset</strong> (labeled as <em>BAU_IHC</em>) consists of <strong>55 zip files</strong>, each containing 2–3 WSIs, for a total of <strong>163 slides</strong>.</li> <li>The <strong>H&E dataset</strong> (labeled as <em>BAU_HE</em>) consists of <strong>36 zip files</strong>, each containing 2 WSIs, for a total of <strong>72 slides</strong>.</li> </ul> <p>The data were collected from <strong>Bahçeşehir University Medical School</strong> and are intended for research in <strong>histopathology </strong>and <strong>computational pathology</strong>.</p> <p>This study was approved by the <strong>Bahçeşehir University Clinical Research Institutional Review Board</strong> (Approval No: 2022-10/03).</p>
Efficacy of Digital Otoscope and Otoendoscope for Diagnosis of Middle Ear Pathology
ClinicalTrials.gov study NCT05813119. IPD Sharing: NO. Countries: 1. Publications: 5.
Digital Pathology and AI for Liver Outcomes in MASLD (DPAILO-2)
ClinicalTrials.gov study NCT06493253. IPD Sharing: NO. Countries: 1. Publications: 1.
Assessment of Dental Pathologies Using Digital Tools
ClinicalTrials.gov study NCT07205588. IPD Sharing: NO. Countries: 2. Publications: 10.
Digital Pathology and AI for Liver Outcomes in MASLD
ClinicalTrials.gov study NCT06344364. IPD Sharing: NO. Countries: 2. Publications: 2.
Task-driven framework using large models for digital pathology
<p>The dataset and code used to implement TDF are published on this page.</p>
Role of Contrast Enhanced Digital Mammography in Female Patients With Pathological Nipple Discharge
ClinicalTrials.gov study NCT04651257. IPD Sharing: Not stated. Countries: 0. Publications: 4.
Development and Prospective Validation of a Digital Pathology-based Artificial Intelligence Diagnostic Model for Pan-cancer Lymphatic Metastasis
ClinicalTrials.gov study NCT06517979. IPD Sharing: NO. Countries: 1. Publications: 0.
Rotation Equivariant CNNs for Digital Pathology
<p>The PatchCamelyon benchmark is a new and challenging image classification dataset. It consists of 327.680 color images (96 x 96px) extracted from histopathologic scans of lymph node sections. Each image is annoted with a binary label indicating presence of metastatic tissue. PCam provides a new benchmark for machine learning models: bigger than CIFAR10, smaller than imagenet, trainable on a single GPU.</p>
Personalized Digital Training Intervention to Reduce Inflammation by Correcting Pathological Movement Patterns in Pre-stage Knee Osteoarthritis After Anterior Cruciate Ligament Reconstruction
ClinicalTrials.gov study NCT06596824. IPD Sharing: NO. Countries: 1. Publications: 0.
ALK Digital Pathology Outcome Predition, Multi Institutional, Restrospective Study
ClinicalTrials.gov study NCT06846736. IPD Sharing: YES. Countries: 1. Publications: 0.
Evaluation of the Omnyx™ Integrated Digital Pathology System in the Primary Diagnosis of Surgical Pathology Specimens
ClinicalTrials.gov study NCT02470572. IPD Sharing: Not stated. Countries: 0. Publications: 0.
The Application of Rapid Fresh Digital Pathology on the Diagnosis and Biomarker Testing of Lung Cancer
ClinicalTrials.gov study NCT06497686. IPD Sharing: NO. Countries: 0. Publications: 0.
Development and Application of AI-Based Therapeutic Strategies for Esophageal Cancer Integrating Multimodal Imaging and Digital Pathology
ClinicalTrials.gov study NCT07203690. IPD Sharing: UNDECIDED. Countries: 0. Publications: 0.
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.