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.
92
datasets available to search
ShareScore release 0.9.0
Dataset results
92 results for “Histological image”
WM4237 TE histology images, H&E stain
<p>Histology images used in analysis <a href="../records/10839655">https://zenodo.org/records/10839655</a>.</p> <p>The images and metadata are viewable at <a href="https://images.jax.org/webclient/?show=image-190605">https://images.jax.org/webclient/?show=image-190605</a>.</p>
Histological images for tumor detection in gastrointestinal cancer
<p>This is a set of 11977 image patches of hematoxylin & eosin stained histological samples of human colorectal cancer. It is a subset of the data set "100,000 histological images of human colorectal cancer and healthy tissue" which is accessible at http://dx.doi.org/10.5281/zenodo.1214456. Further information on the samples is available there.</p> <p>This set contains three classes:</p> <p>ADIMUC - adipose tissue and mucus, i.e. loose non-tumor tissue</p> <p>STRMUS - stroma and muscle, i.e. dense non-tumor tissue</p> <p>TUMSTU - colorectal cancer epithelial tissue and stomach cancer epithelial tissue, i.e. tumor tissue</p> <p>All images are 512x512 px at 0.5 µm/px</p> <p>We are using this data set to train a deep neural network to detect tumor cells in histological whole slide images of colorectal and stomach cancer.</p> <p>If you use these images in your research, please consider citing our previous [1] and upcoming publication.</p> <p>For information on ethics board approval, see [1].</p> <p>-------------</p> <p>[1] http://dx.doi.org/10.1371/journal.pmed.1002730</p>
Cytological and histological images of breast cancer
<p>Data set of cytological and histological images of breast cancer.</p> <p><strong>Data set structure</strong>:</p> <ol> <li>Cytological image files (size 3264x2448 px, microscope with x40 lens used). The name of each folder contains the name of the diagnosis.</li> <li>Files of histological and corresponding immunohistochemical images of breast tissue sections (size 2048x1536 px). The name of each folder contains the name of the diagnosis. Each folder contains 1 H&E histological image and 4 folders with IHC images for 4 biomarkers: estrogen receptor (ER), progesterone receptor (PR), Ki-67 Biomarker (KI67), human epidermal growth factor receptor-2 (HER2NEU).</li> </ol>
Data-driven transcriptomics analysis identifies PCSK9 as a novel key regulator in liver aging. (Histology Images)
<p>These are the histology images on "Data-driven transcriptomics analysis identifies PCSK9 as a novel key regulator in liver aging."</p>
Animal histological images for <em>in vivo</em> maximum tolerated dose and toxicity
Open the record for dataset details and reuse information.
Nucleus feature profiles from GTEx histological images across 12 tissues
Open the record for dataset details and reuse information.
Microscopy images from: A physiological and histological atlas of reproduction in the North American deer mouse (Peromyscus maniculatus)
Open the record for dataset details and reuse information.
BACH Dataset : Grand Challenge on Breast Cancer Histology images
<p><strong>i3S Annotated Datasets on Digital Pathology</strong></p> <p> </p> <p><strong>WELCOME</strong></p> <p>In an effort to contribute and push forward the field of Digital Pathology, <a href="https://www.ipatimup.pt/">Ipatimup</a> and <a href="http://www.ineb.up.pt/">INEB</a>, two major research institutions in Portugal, have joined forces in the construction of histology datasets to support grand Challenges on automatic classification of tissue malignancy. The researchers/pathologists responsible for the datasets are:</p> <p><a href="mailto:apolonia@ipatimup.pt">António Polónia</a> (MD), Ipatimup/i3S</p> <p><a href="mailto:celoy@ipatimup.pt">Catarina Eloy</a> (MD, PhD), Ipatimup/i3S</p> <p><a href="mailto:pauloaguiar@ineb.up.pt">Paulo Aguiar</a> (PhD), INEB/i3S</p> <p> </p> <p>This specific page refers to the <a href="https://iciar2018-challenge.grand-challenge.org/home/">Grand Challenge on Breast Cancer Histology images</a>, or BACH Challenge</p> <p> </p> <p><strong>THE BACH CHALLENGE DATASET</strong></p> <p><a href="https://iciar2018-challenge.grand-challenge.org/home/">ICIAR 2018 - Grand Challenge on Breast Cancer Histology images</a> [Challenge organized by Teresa Araújo, Guilherme Aresta, António Polónia, Catarina Eloy and Paulo Aguiar]</p> <p>For detailed information visit: <a href="https://iciar2018-challenge.grand-challenge.org/home/">https://iciar2018-challenge.grand-challenge.org/home/</a></p> <p> </p> <p>THIS DATASET IS PUBLICALLY AVAILABLE UNDER A CREATIVE COMMONS CC BY-NC-ND LICENSE (<a href="https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode">ATTRIBUTION-NONCOMMERCIAL-NODERIVS</a>)<br> ESSENCIALLY, YOU ARE GRANTED ACCESS TO THE DATASET FOR USE IN YOUR RESEARCH AS LONG AS YOU CREDIT OUR WORK/PUBLICATIONS(*), BUT YOU CANNOT CHANGE THEM IN ANY WAY OR USE THEM COMMERCIALLY</p> <ul> <li>(*) Aresta, Guilherme, et al. "BACH: Grand challenge on breast cancer histology images." Medical image analysis (2019).</li> <li>(*) Araújo, Teresa, et al. "Classification of breast cancer histology images using convolutional neural networks." PloS one 12.6 (2017): e0177544.</li> <li>(*) Fondón, Irene, et al. "Automatic classification of tissue malignancy for breast carcinoma diagnosis." Computers in biology and medicine 96 (2018): 41-51.</li> </ul> <p> </p> <p> </p> <p> </p> <p> </p>
Macroscopic and histological image dataset of the European plaice (Pleuronectes platessa) ovaries
<p><strong>Macroscopic and histological image dataset of the European plaice (</strong><em><strong>Pleuronectes platessa</strong></em><strong>) ovaries </strong></p> <p> </p> <p><strong>Authors:</strong></p> <p> </p> <p>Carine Sauger<sup>1</sup>, Jérôme Quinquis<sup>1</sup>, Kristell Kellner<sup>2</sup>, Clothilde Heude-Berthelin<sup>2</sup>, Mélanie Lepoittevin<sup>2</sup>, Nicolas Elie<sup>3</sup>, Laurent Dubroca<sup>1</sup></p> <p> </p> <p><strong>Affiliations:</strong></p> <p> </p> <p>1 : Institut Français de Recherche pour l'Exploitation de la Mer (IFREMER). Laboratoire Ressources Halieutiques de Port-en-Bessin, Avenue du Général de Gaulle, 14520, Port-en-Bessin-Huppain, Calvados</p> <p>2 : Biologie des Organismes et Ecosystèmes Aquatiques (FRE 2030 BOREA). Université de Caen Normandie, Esplanade de la Paix, CS 14032, Caen, Calvados</p> <p>3 : Centre de Microscopie Appliquée à la Biologie (SF 4206 ICORE, CMABIO3). Université de Caen Normandie, Esplanade de la Paix, CS 14032, Caen, Calvados</p> <p> </p> <p><strong>Contents: </strong>This dataset was established during a 6 month long Master’s degree internship (February to July 2019), under the IFREMER (Institut Français de Recherche pour l'Exploitation de la Mer) project MATO (MATurité Objective des poissons par l’histologie quantitative), with the collaboration of two research facilities from the University of Caen-Normandie : BOREA (Biologie des Organismes et Ecosystèmes Aquatiques) and CMABIO3 (Centre de Microscopie Appliquée à la Biologie).</p> <p>This dataset contains the macroscopic and the histological images of the ovaries of 151 European plaices (female, <em>Pleuronectes platessa</em>) collected along the French Coast of the English Channel (ICES area 27.7.d) in 2017, 2018 and 2019.</p> <p><br> </p> <p><strong>Images:</strong></p> <ul> <li> <p><strong>Full_Ovaries_Data.zip: </strong>archive in zip format of 151 pictures (.JPG; 8Mo-9Mo; sRGB; 6016x4000 pixels) of both ovaries from 151 female plaice dissected during this study. Each photo was taken by the same person with a Nikon camera (D3200), in the same room with identical lightening methods (no flash). For each picture, both ovaries were set on a blue background, with a 0.50€ coin for size calibration. The upper most ovary is the dorsal gonad of the fish while the lower one is the ventral gonad. The name of the picture is the same as the fish’s ID number.</p> </li> </ul> <p><br> </p> <ul> <li> <p><strong>Stereology_Readings_Data.zip:</strong> archive in zip format of two directories containing the images</p> </li> </ul> <ul> <li> <ul> <li> <p><strong>Interagent_Calibration</strong>: the ovarian histological slides were digitized using an Aperio slide scanner (Scan Scope Console software, v.10.2.0.2352, Leica Biosystems), x20 lens. The pictures (.svs: Aperio single-file pyramidal tiled TIFF, with non-standard metadata and compression) are of the 20 histological slides used for the stereological count. 20 slides of 20 fish (with one slide per fish) were analyzed for the intercalibration analysis. The slides used were from the central position of the ventral ovary (V2).</p> </li> <li> <p><strong>Ovary_Slides</strong>: the ovarian histological slides were digitized using an Aperio slide scanner (Scan Scope Console software, v.10.2.0.2352, Leica Biosystems), x20 lens. The pictures (Aperio single-file pyramidal tiled TIFF, with non-standard metadata and compression) in this dataset are the 226 histological slides read during this study. With a total of 151 fish dissected, 151 ovarian histological slides of the median position of the ventral ovary were read. Among the remaining slides, 90 were read to analyze the homogeneous distribution of the different cell types. These 90 slides belong to 15 fish, with three histological samples taken in the anterior (1), median (2) and posterior (3) sections of the dorsal (D) and ventral (V) ovaries.</p> </li> </ul> </li> </ul> <p><strong>Data frames:</strong></p> <ul> <li> <p><strong>Intergaent_read_me.txt</strong> : a text file (.txt) listing the acronyms used in the <strong>Interagent.csv</strong> file, as well as their meaning.</p> </li> <li> <p><strong>Interagent.csv</strong>: a text data file (.csv) with the output of two stereological readings, done by three agents for 15 slides, and by two agents for 20 slides. Between the first and second reading, a reading protocol was set up to help in the determination of the different structures. This protocol allowed the three agents to calibrate themselves with a determination key. This key was necessary for the identification of specific complex structures. The information contained in this table is as follows:</p> <ul> <li> <p>agent: code id for the three agents that did the calibration exercise (A, B and C)</p> </li> <li> <p>num_fish: fish number for this study. Here we have 20 different fish</p> </li> <li> <p>fish_id: identification number of the fish. This id number is identical to the name given to the pictures of the full ovaries (<strong>Full_Ovaries_Data</strong>)</p> </li> <li> <p>scan_id: identification number of the digitized histological slide that was used for the stereological count (<strong>Stereology_Readings_Data </strong>/ <strong>Interagent_Calibration</strong>)</p> </li> <li> <p>total_points: total number of identified structures for the stereological sampling grid of a slide</p> </li> <li> <p>cell_type: abbreviation of the structure identified (reading protocol available here: https://archimer.ifremer.fr/doc/00501/61235/). In this study, we have 20 different structures</p> </li> <li> <p>hit_points: number of time a structure has been counted on a single slide</p> </li> <li> <p>Fract_estim: percentage (%) of times a structure was counted on a single slide =<em> (100 / total_point) * hit_points</em></p> </li> <li> <p>reading: reading number. In this study, we have two readings, the first (1) and the second (2)</p> </li> </ul> </li> </ul> <p><br> </p> <ul> <li> <p><strong>Macros_read_me.txt</strong> : a text file (.txt) listing the acronyms used in the <strong>Macros.csv</strong> file, as well as their meaning.</p> </li> <li> <p><strong>Macros.csv</strong>: a text data file (.csv) containing macroscopic parameters measurements for all 151 fish that have been used during this study. The information contained in this table is as follows:</p> <ul> <li> <p>num_fish: fish number for this study. Here we have 151 different female fish</p> </li> <li> <p>fish_id: identification number of the fish. This id number is identical to the name given to the pictures of the full ovaries (<strong>Full_Ovaries_Data</strong>)</p> </li> <li> <p>gon_pos: gonad position, with D being the dorsal gonad of the individual, and V being the ventral gonad.</p> </li> <li> <p>date: the date the fish was caught (dd/mm/yyyy)</p> </li> <li> <p>L_fish: total length of the fish (cm)</p> </li> <li> <p>W_fish: total weight of the fish (g)</p> </li> <li> <p>mat_estim: visually estimated maturity, after observation of the fish’s gonad with the naked eye, following the WKMATCH (ICES, 2012) scale</p> </li> <li> <p>age: estimated age (in years) of the fish, after analysis of the fish’s otolith. The IFREMER laboratory executed this analysis in Boulogne-sur-Mer (FRANCE)</p> </li> <li> <p>W_gon: gonad weight (g)</p> </li> <li> <p>Kurtosis*: kurtosis parameter</p> </li> <li> <p>Skewness*: skewness coefficient</p> </li> <li> <p>gon_area*: gonad area (mm²)</p> </li> <li> <p>L_gon*: gonad length (mm)</p> </li> <li> <p>width_gon*: maximum gonad width (mm)</p> </li> <li> <p>width_mid_L_gon*: width at mid-length of the gonad (mm)</p> </li> <li> <p>mean_col_index*: the mean color value of the different hues found on the ovary</p> </li> <li> <p>std_dev*: standard deviation of the mean_col_index</p> </li> <li> <p>modal*: modal value or the most frequently occurring color value within the selected ovary</p> </li> </ul> </li> </ul> <p>*: values determined after image analysis of the <strong>Full_Ovaries_Data</strong> with the ImageJ software (v. 1.50J)</p> <p><br> </p> <ul> <li> <p><strong>Stereology_read_me.txt</strong> : a text file (.txt) listing the acronyms used in the <strong>Stereology.csv</strong> file, as well as their meaning.</p> </li> <li> <p><strong>Stereology.csv</strong>: a text data file (.csv) of the stereology count results of 226 slides read during this study. Among these slides, 90 were read to test the homogeneity distribution of different cell types found throughout each ovary (15 fish with 6 histological sections : a median, an anterior and a posterior histological section, for both ovaries), 20 slides were read by two agents for calibration purposes, and 15 of these 20 slides were also read by a third agent for calibration purposes. Finally, 151 median histological slides of the ventral ovary were also read. The information contained in this table is as follows:</p> <ul> <li> <p>agent: code id for the 3 agents that did the calibration exercise (A, B and C)</p> </li> <li> <p>num_fish: fish number for this study. Here we have a total of 151 fish</p> </li> <li> <p>fish_id: identification number of the fish. This id number is identical to the name given to the pictures of the full ovaries (<strong>Full_Ovaries_Data</strong>)</p> </li> <li> <p>scan_id: identification number of the digitized histological slide that was used for the stereological count (<strong>Stereology_Readings_Data </strong>/ <strong>Ovary_Slides</strong>)</p> </li> <li> <p>reading: reading data to test the homogeneity of cell distributions throughout the ovaries (homogeneity), reading data of the 20 slides read for the inter-agent calibration, and reading data of all the slides (median)</p> </li> <li> <p>cell_type: abbreviation of the structure identified (reading protocol available here: https://archimer.ifremer.fr/doc/00501/61235/). In this study, we have 20 different structures</p> </li> <li> <p>point_id: identification number of the point inside the stereological sampling grid placed over the ovarian histology slide</p> </li> <li> <p>coord_x: x coordinate of the sampling point</p> </li> <li> <p>coord_y: y coordinate of the sampling point</p> </li> </ul> </li> </ul> <p><br> </p> <p><strong>Contact :</strong></p> <p>For questions, please contact: <a href="mailto:carine.sauger@gmail.com">carine.sauger@gmail.com</a> or <a href="mailto:laurent.dubroca@ifremer.fr">laurent.dubroca@ifremer.fr</a></p>
Histological image tiles for TCGA-CRC-DX, color-normalized, sorted by MSI status, train/test split
<p>These are histological images of colorectal cancer, derived from the TCGA database at https://portal.cdc.cancer.gov. Tumor tissue was outlined manually and the tumor region was cut into tiles of 256 µm edge length, saved as 512 px images (effective magnification 0.5 µm/px). All image tiles were color-normalized with the Macenko method. Patients were split into training and test set in a 2:1 ratio. For all patients, MSI status was acquired (patients with MSI-H = MSIH; patients with MSI-L and MSS = NonMSIH) and all tiles inherited the label of the parent patient. Then, tiles in the training set were randomly undersampled to equalize classes. The test set was not undersampled. Further info: www.kather.ai</p>
HAPPY: a deep learning pipeline for mapping cell-to-tissue graphs across placenta histology whole slide images
<p>These two zipped folders contain all data necessary to train, validate and reproduce results from the paper.</p> <p>Unzipping the files will create 6 folders. Data from folders with the same name across both zips should be combined into one folder. The 'annotations' folder contains all ground truth annotations for training all three deep learning models. The 'datasets' folder contains images for training the nuclei localisation and cell classification models. The 'embeddings' folder contains cell embedding vectors and nuclei coordinates from two slides used to create nodes to train the graph tissue classification model. The 'graph_splits' folder contains regions defining the validation and test splits for the graph model. The 'slides' folder contains a sample region of a whole slide image as a .tiff file for running the inference demo. The 'trained_models' folder contains trained weights for each of the three models.</p> <p>Further instructions for dataset use and creation of custom datasets are available in the GitHub readme: https://github.com/Nellaker-group/happy.</p>
Histology images from uniform tumor regions in TCGA Whole Slide Images (TCGA-UT)
<h1><strong>TCGA-UT Dataset Documentation </strong></h1> <h2>Quick Links</h2> <ul> <li><strong>Dataset on Hugging Face</strong>: For users interested in benchmarking foundation models or feature extractors, please visit <a href="https://huggingface.co/datasets/dakomura/tcga-ut">TCGA-UT on Hugging Face</a></li> <li><strong>Original Paper</strong>: <a href="https://doi.org/10.1016/j.celrep.2022.110424">Universal encoding of pan-cancer histology by deep texture representations</a></li> </ul> <p> </p> <h2>Dataset Overview</h2> <p>The TCGA-UT dataset is a large-scale collection of histopathological image patches from human cancer tissues. It contains 1,608,060 image patches extracted from hematoxylin & eosin (H&E) stained histological samples across 32 different types of solid cancers.</p> <h3>Key Features</h3> <ul> <li><strong>Size</strong>: Over 1.6 million image patches</li> <li><strong>Resolution</strong>: All patches are standardized to 256 x 256 pixels</li> <li><strong>Source</strong>: Derived from The Cancer Genome Atlas (TCGA) dataset</li> <li><strong>Quality</strong>: Curated by trained pathologists</li> <li><strong>Coverage</strong>: 32 different cancer types</li> <li><strong>Patient Base</strong>: 7,175 patients from 8,736 diagnostic slides</li> </ul> <h2>Data Collection Process</h2> <ol> <li><strong>Image Source</strong>: Whole Slide Images (WSI) were downloaded from the GDC legacy database between December 2016 and June 2017</li> <li><strong>Expert Annotation</strong>: Two trained pathologists selected at least three representative tumor regions per slide</li> <li><strong>Quality Control</strong>: 926 slides were removed due to various quality issues (poor staining, low resolution, focus problems, etc.)</li> <li><strong>Patch Extraction</strong>: 10 patches were randomly cropped at 6 different magnification levels from each annotated region</li> </ol> <h2>File Structure</h2> <p>Files are organized using the following format:</p> <div> <div> </div> <div> <div><span>Copy</span></div> </div> <div> <div><code>[cancer_type]/[resolution]/[TCGA Barcode]/[region]-[number]-[pixel resolution].jpg</code></div> </div> </div> <h3>Resolution Key</h3> <ul> <li>0: 0.5 μm/pixel</li> <li>1: 0.6 μm/pixel</li> <li>2: 0.7 μm/pixel</li> <li>3: 0.8 μm/pixel</li> <li>4: 0.9 μm/pixel</li> <li>5: 1.0 μm/pixel</li> </ul> <h2>License</h2> <ul> <li><strong>Non-Commercial Use</strong>: CC-BY-NC-SA 4.0</li> <li><strong>Commercial Use</strong>: Please contact <a href="mailto:ishum-prm@m.u-tokyo.ac.jp">ishum-prm@m.u-tokyo.ac.jp</a> for licensing</li> </ul> <h2>Citation</h2> <p>If you use this dataset in your research, please cite:</p> <div> <div> </div> <div> <div><span>Copy</span></div> </div> <div> <div><code>Komura, D., et al. (2022). Universal encoding of pan-cancer histology by deep texture representations. Cell Reports 38, 110424. https://doi.org/10.1016/j.celrep.2022.110424</code></div> </div> </div> <h2>For Model Benchmarking</h2> <p>If you're interested in using this dataset for benchmarking foundation models or feature extractors, we recommend accessing the dataset through the Hugging Face Hub at <a href="https://huggingface.co/datasets/dakomura/tcga-ut">dakomura/tcga-ut</a>. The Hugging Face version provides:</p> <ul> <li>Predefined train/validation/test splits (both internal and external facility-based splits)</li> <li>Ready-to-use benchmarking framework for foundation models</li> <li>WebDataset format support for efficient data loading</li> <li>Example implementations for state-of-the-art model evaluation</li> </ul> <p> </p>
Colorectal Cancer Histology Image Tiles for Tissue Multi-class Classification
<p><strong>Content</strong></p> <p>The present dataset is linked to a research aimed at discovering the best normalization pipeline and classification model for colorectal cancer multi-class tissue classification.<br> The 15,856 histological image tiles are completely anomized and are extracted from 10 formalin-fized paraffine-embedded samples of patients affected by colorectal cancer.</p> <p>The materials are inside the following zip file:</p> <p>“CRC_Tiles_IRCCS_ISTITUTO_TUMORI_BARI.zip”: a zipped folder containing tiles (n=15,856) annotated by a pathologist, grouped in 6 subdirectories, each of them representing a class. Tiles are of size 224 x 224 px, taken at a resolution of 0.5 μm/px.<br> <br> <strong>Ethical Statement</strong></p> <p>The study has been funded by “Tecnopolo per la Medicina di Precisione (CUP B84I18000540002)”. The institutional Ethic Committee approved the study (Prot n. 780/CE).</p> <p><br> <strong>Related Datasets and Works</strong><br> <br> For further details concerning the aforementioned dataset, refer to the papers below. <br> Please cite the following articles if you need this dataset for your research.</p> <p>Altini N. et al. (2021) Multi-class Tissue Classification in Colorectal Cancer with Handcrafted and Deep Features. In: Huang DS., Jo KH., Li J., Gribova V., Bevilacqua V. (eds) Intelligent Computing Theories and Application. ICIC 2021. Lecture Notes in Computer Science, vol 12836. Springer, Cham. <br> https://doi.org/10.1007/978-3-030-84522-3_42</p> <p>Altini, N., Marvulli, T. M., Zito, F. A., Caputo, M., Tommasi, S., Azzariti, A., ... & Bevilacqua, V. (2023). The Role of Unpaired Image-to-Image Translation for Stain Color Normalization in Colorectal Cancer Histology Classification. <em>Computer Methods and Programs in Biomedicine</em>, 107511. <br> <a href="https://doi.org/10.1016/j.cmpb.2023.107511">https://doi.org/10.1016/j.cmpb.2023.107511</a></p> <p>Please also consider the dataset offered in our previous work:</p> <p>Altini N. et al. (2021). Pathologist's Annotated Image Tiles for Multi-Class Tissue Classification in Colorectal Cancer (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.4785131</p>
Supplementary material 1 from: Jochum A, Slapnik R, Klussmann-Kolb A, Páll-Gergely B, Kampschulte M, Martels G, Vrabec M, Nesselhauf C, Weigand AM (2015) Groping through the black box of variability: An integrative taxonomic and nomenclatural re-evaluation of Zospeum isselianum Pollonera, 1887 and allied species using new imaging technology (Nano-CT, SEM), conchological, histological and molecular data (Ellobioidea, Carychiidae). Subterranean Biology 16: 123-165. https://doi.org/10.3897/subtbiol.16.5758
List of localities of Zospeum isselianum: Explanation note: List of localities of Zospeum isselianum. A − Austria, BiH − Bosnia and Herzegovina, Cro − Croatia, Slo − Slovenia, Ita − Italy, CBSS − Collection of Croatian Biospeleological Society, CSR SASA – Malacological collection of the Biological Institute of the Centre for Scientific Research of the Slovenian Academy of Sciences and Arts in Ljubljana, SMNH – Malacological collection of the Slovenian Museum of Natural History, LIT – data from literature.
The features of Tissues and Patches for "Predicting microsatellite instabilitiy from histology images with a three-level hierarchical graph fusion model"
<p>This repository contains features and corresponding coordinates of patches and tissues extracted from 430 and 326 histologic images from patients with colorectal and gastric cancers from the TCGA cohort (original whole section SVS images are freely available at https://portal.gdc.cancer.gov/). All images in this library are from formalin-fixed paraffin-embedded (FFPE) diagnostic sections (“DX” on the GDC Data Portal). This blog explains this in detail: http://www.andrewjanowczyk.com/download-tcga-digital-pathology-images-ffpe/</p> <p><strong>Preprocessing.</strong></p> <p>All SVS slices were pre-processed as follows.</p> <p>According to “Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer” these histology images were categorized into The histology images were classified as “MSS” (microsatellite stable) or “MSIMUT” (microsatellite unstable or highly mutated) according to “Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer”, which corresponds to the division of the training and test sets in the article.<br><br></p> <p>Patches were extracted at 40x objective magnification and 20x objective magnification, respectively, and the corresponding features were extracted by pre-training resnet48, respectively</p> <p>The features of Tissues are thumbnails obtained at 2.5x objective magnification and further extracted by MedSAM after extracting the masks of the tissues.</p>
Cell features for "Datasets for "Predicting microsatellite instabilitiy from histology images with a three-level hierarchical graph fusion model""
<p>This repository contains features and corresponding coordinates of cells extracted from 430 and 326 histologic images from patients with colorectal and gastric cancers from the TCGA cohort (original whole section SVS images are freely available at https://portal.gdc.cancer.gov/). All images in this library are from formalin-fixed paraffin-embedded (FFPE) diagnostic sections (“DX” on the GDC Data Portal). This blog explains this in detail: http://www.andrewjanowczyk.com/download-tcga-digital-pathology-images-ffpe/</p> <p><strong>Preprocessing.</strong></p> <p>All SVS slices were pre-processed as follows.</p> <p>According to “Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer” these histology images were categorized into “MSS” (microsatellite stable) or “MSIMUT” (microsatellite unstable or highly mutated) and corresponded to the article dividing the training and test sets.<br><br></p> <p>The features of all cells were extracted by Hovernet and Transnuseg at 40x objective magnification for extraction masking and further feature extraction</p>
Multimodal contrastive learning for spatial gene expression prediction using histology images
<p>we employed two human breast cancer datasets and one human cutaneous squamous cell carcinoma (cSCC) dataset.</p>
Histological images for MSI vs. MSS classification in gastrointestinal cancer, FFPE samples
<p>This repository contains 411,890 unique image patches derived from histological images of colorectal cancer and gastric cancer patients in the TCGA cohort (original whole slide SVS images are freely available at https://portal.gdc.cancer.gov/). All images in this repository are derived from formalin-fixed paraffin-embedded (FFPE) diagnostic slides ("DX" at the GDC data portal). This is explained well in this blog: http://www.andrewjanowczyk.com/download-tcga-digital-pathology-images-ffpe/</p> <p><strong>Preprocessing</strong></p> <p>All SVS slides were preprocessed as follows</p> <p>1. automatic detection of tumor</p> <p>2. resizing to 224 px x 224 px at a resolution of 0.5 µm/px</p> <p>4. color normalization with the Macenko method (Macenko et al., 2009, http://wwwx.cs.unc.edu/~mn/sites/default/files/macenko2009.pdf)</p> <p>5. assignment of patients to either "MSS" (microsatellite stable) or "MSIMUT" (microsatellite instable or highly mutated)</p> <p>6. randomization of patients to training and testing sets (~70% and ~30%). Randomization was done on a patient level rather than on a slide or tile level</p> <p>7. equilibration of training sets by undersampling (removing excess tiles in MSS class in a random way)</p> <p><strong>File description</strong></p> <p>1. STAD_TRAIN_MSS - training images (~70% of all patients) for gastric (stomach) cancer TCGA patients with MSS (microsatellite stable) tumors, 50285 unique image patches; FFPE samples</p> <p>2. STAD_TRAIN_MSIMUT - training images ( (~70% of all patients) for gastric (stomach) cancer TCGA patients with MSI (microsatellite instable) or highly mutated tumors, 50285 unique image patches; FFPE samples</p> <p>3. STAD_TEST_MSS - test images (~30% of all patients) for gastric (stomach) cancer TCGA patients with MSS (microsatellite stable) tumors, 90104 unique image patches; FFPE samples</p> <p>4. STAD_TEST_MSIMUT - test images ( ~30% of all patients) for gastric (stomach) cancer TCGA patients with MSI (microsatellite instable) or highly mutated tumors, 27904 unique image patches; FFPE samples</p> <p>5. CRC_DX_TEST_MSIMUT - test images (~30% of all patients) for colorectal cancer TCGA patients with MSI (microsatellite instable) or highly mutated tumors, 29335 unique image patches; FFPE samples</p> <p>6. CRC_DX_TEST_MSS - test images (~30% of all patients) for colorectal cancer TCGA patients with MSS (microsatellite stable) tumors, 70569 unique image patches; FFPE samples</p> <p>7. CRC_DX_TRAIN_MSIMUT - training images (~70% of all patients) for colorectal cancer TCGA patients with MSI (microsatellite instable) or highly mutated tumors, 46704 unique image patches; FFPE samples</p> <p>8. CRC_DX_TRAIN_MSS - training images (~70% of all patients) for colorectal cancer TCGA patients with MSS (microsatellite stable) tumors, 46704 unique image patches; FFPE samples</p>
Histological images for MSI vs. MSS classification in gastrointestinal cancer, snap-frozen samples
<p>This repository contains 218,578 unique image patches derived from histological images of colorectal cancer patients in the TCGA cohort (original whole slide SVS images are freely available at https://portal.gdc.cancer.gov/). All images in this repository are derived from snap-frozen tissue slides ("TS" or "BS" at the GDC data portal).</p> <p><strong>Preprocessing</strong></p> <p>All SVS slides were preprocessed as follows</p> <p>1. automatic detection of tumor</p> <p>2. resizing to 224 px x 224 px at a resolution of 0.5 µm/px</p> <p>4. color normalization with the Macenko method (Macenko et al., 2009, http://wwwx.cs.unc.edu/~mn/sites/default/files/macenko2009.pdf)</p> <p>5. assignment of patients to either "MSS" (microsatellite stable) or "MSIMUT" (microsatellite unstable or hypermutated)</p> <p>6. randomization of patients to training and testing sets (~70% and ~30%). Randomization was done on a patient level rather than on a slide or tile level</p> <p>7. equilibration of training sets by undersampling (removing excess tiles in MSS class in a random way)</p> <p><strong>File description</strong></p> <p>1. STAD_TRAIN_MSS - training images (~70% of all patients) for gastric (stomach) cancer TCGA patients with MSS (microsatellite stable) tumors, 50285 unique image patches; FFPE samples</p> <p>2. STAD_TRAIN_MSIMUT - training images ( (~70% of all patients) for gastric (stomach) cancer TCGA patients with MSI (microsatellite instable) or highly mutated tumors, 50285 unique image patches; FFPE samples</p> <p>3. STAD_TEST_MSS - test images (~30% of all patients) for gastric (stomach) cancer TCGA patients with MSS (microsatellite stable) tumors, 90104 unique image patches; FFPE samples</p> <p>4. STAD_TEST_MSIMUT - test images ( ~30% of all patients) for gastric (stomach) cancer TCGA patients with MSI (microsatellite instable) or highly mutated tumors, 27904 unique image patches; FFPE samples</p>
Fig. 2 Sectioned solemydid specimens and resulting binary images used for compactness analysis with Bone Profiler. a in Shell bone histology of solemydid turtles (stem Testudines): palaeoecological implications
Fig. 2 Sectioned solemydid specimens and resulting binary images used for compactness analysis with Bone Profiler. a Solemys vermiculata, costal fragment (MCNA-15047). b Solemys vermiculata, shell fragment (MCNA-15046). c Solemys sp., costal fragment (UPUAM-14001)
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.