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.
5
datasets available to search
ShareScore release 0.9.0
Dataset results
5 results for “TCGA-BRCA”
Preliminary Mitosis Detection Results for TCGA-BRCA Dataset
<p>This dataset provides mitosis detection results employing the "Mitosis Detection, Fast and Slow" (MDFS) algorithm [<a href="https://arxiv.org/abs/2208.12587">[2208.12587] Mitosis Detection, Fast and Slow: Robust and Efficient Detection of Mitotic Figures (arxiv.org)</a>] on the TCGA-BRCA dataset. </p> <p>The MDFS algorithm exemplifies a robust and efficient two-stage process for mitosis detection. Initially, potential mitotic figures are identified and later refined. The proposed model for the preliminary identification of candidates, the EUNet, stands out for its swift and accurate performance, largely due to its structural design. EUNet operates by outlining candidate areas at a lower resolution, significantly expediting the detection process. In the second phase, the initially identified candidates undergo further refinement using a more intricate classifier network, namely the EfficientNet-B7. The MDFS algorithm was originally developed for the MIDOG challenges.</p> <p> </p> <h2>Viewing in QuPath</h2> <p>The dataset at hand comprises GeoJSON files in two categories: mitosis and proxy (mimicker -- the candidates that are unlikely to be mitosis based on our algorithm). Users can open and visualize each category overlaid on the Whole Slide Image (WSI) using QuPath. Simply drag and drop the annotation file onto the opened image in the program. Additionally, users can employ the provided Python snippet to read the annotation into a Python dictionary or a Numpy array.</p> <p> </p> <h2>Loading in Python</h2> <p>To load the GeoJSON files in Python, users can use the following code:</p> <blockquote> <p>import json</p> <p>import numpy as np</p> <p>import pandas as pd</p> <p> </p> <p>def load_geojson(filename):</p> <p> # Load the GeoJSON file</p> <p> with open(filename, 'r') as f:</p> <p> data = json.load(f)</p> <p> </p> <p> # Extract the properties and store in a dictionary</p> <p> slide_properties = data["properties"]</p> <p> </p> <p> # Convert the points to a numpy array</p> <p> points_np = np.array([(feat['geometry']['coordinates'][0], feat['geometry']['coordinates'][1], feat['properties']['score']) for feat in data['features']])</p> <p> </p> <p> # Convert the points to a pandas DataFrame</p> <p> points_df = pd.DataFrame(points_np, columns=['x', 'y', 'score'])</p> <p> </p> <p> return slide_properties, points_np, points_df</p> <p> </p> <p> </p> <p># Use the function to load mitosis data</p> <p>mitosis_properties, mitosis_points_np, mitosis_points_df = load_geojson('mitosis.geojson')</p> <p> </p> <p># Use the function to load mimickers data</p> <p>mimickers_properties, mimickers_points_np, mimickers_points_df = load_geojson('mimickers.geojson')</p> </blockquote> <h2>Properties</h2> <p>Each WSI in the dataset includes the candidate's centroid, bounding box, hotspot location, hotspot mitotic count, and hotspot mitotic score. The structures of the mitosis and mimicker property dictionaries are as follows:</p> <p>Mitosis property dictionary structure:</p> <blockquote> <p>mitosis_properties = {</p> <p> 'slide_id': slide_id,</p> <p> 'slide_height': img_h,</p> <p> 'slide_width': img_w,</p> <p> 'wsi_mitosis_count': num_mitosis,</p> <p> 'mitosis_threshold': 0.5,</p> <p> 'hotspot_rect': {'x1': hotspot[0], 'y1': hotspot[1], 'x2': hotspot[2], 'y2': hotspot[3]},</p> <p> 'hotspot_mitosis_count': mitosis_count,</p> <p> 'hotspot_mitosis_score': mitosis_score,</p> <p>}</p> </blockquote> <p> </p> <p>Proxy figure (mimicker) property dictionary structure:</p> <blockquote> <p>mimicker_properties = {</p> <p> 'slide_id': slide_id,</p> <p> 'slide_height': img_h,</p> <p> 'slide_width': img_w,</p> <p> 'wsi_mimicker_count': num_mimicker,</p> <p> 'mitosis_threshold': 0.5,</p> <p>}</p> </blockquote> <h2><br>Disclaimer:</h2> <p>It should be noted that we did not conduct a comprehensive review of all mitotic figures within each WSI, and we do not purport these to be free of errors. Nonetheless, a pathologist examined the resultant hotspot regions of interest from 757 WSIs within the TCGA-BRCA Mitosis Dataset where we found strong correlations between pathologist and MDFS mitotic counts (r=0.8, p$<$0.001). Furthermore, MDFS-derived mitosis scores are shown to be as prognostic as pathologist-assigned mitosis scores [1]. This examination was also aimed at verifying the quality of the selections, ensuring excessive false detections or artifacts did not primarily drive them and were in a plausible location in the tumor landscape.</p> <p> </p> <p>[1] Ibrahim, Asmaa, et al. "Artificial Intelligence-Based Mitosis Scoring in Breast Cancer: Clinical Application." <em>Modern Pathology</em> 37.3 (2024): 100416.</p>
DICOM converted Slide Microscopy images for the TCGA-BRCA collection
<p>This dataset corresponds to a collection of images and/or image-derived data available from National Cancer Institute <a href="https://portal.imaging.datacommons.cancer.gov/">Imaging Data Commons (IDC)</a> [1]. This dataset was converted into DICOM representation and ingested by the IDC team. You can explore and visualize the corresponding images using IDC Portal here: <a href="https://portal.imaging.datacommons.cancer.gov/explore/filters/?collection_id=tcga_brca">TCGA-BRCA</a>. You can use the manifests included in this Zenodo record to download the content of the collection following the <b>Download instructions</b> below.</p> <h3>Collection description</h3> The <a href="http://imaging.cancer.gov/" target="_blank"><u>Cancer Imaging Program (CIP)</u></a> is working directly with primary investigators from institutes participating in TCGA to obtain and load images relating to the genomic, clinical, and pathological data being stored within the <a href="http://tcga-data.nci.nih.gov/" target="_blank">TCGA Data Portal</a>. Currently this MR multi-sequence image collection of breast invasive carcinoma patients can be matched by each unique case identifier with the extensive gene and expression data of the same case from The Cancer Genome Atlas Data Portal to research the link between clinical phenome and tissue genome. <br> <p>Please see the <a href="">TCGA-BRCA <i></i></a> page to learn more about the images and to obtain any supporting metadata for this collection.</p> <h3>Files included</h3> <p>A manifest file's name indicates the IDC data release in which a version of collection data was first introduced. For example, <code>collection_id-idc_v8-aws.s5cmd</code> corresponds to the contents of the <code>collection_id</code> collection introduced in IDC data release v8. If there is a subsequent version of this Zenodo page, it will indicate when a subsequent version of the corresponding collection was introduced.</p> <ol> <li><code>tcga_brca-idc_v18-aws.s5cmd</code>: manifest of files available for download from public IDC Amazon Web Services buckets</li> <li><code>tcga_brca-idc_v18-gcs.s5cmd</code>: manifest of files available for download from public IDC Google Cloud Storage buckets</li> <li><code>tcga_brca-idc_v18-dcf.dcf</code>: Gen3 manifest (for details see <a href="Gen3 manifest documentation">https://learn.canceridc.dev/data/organization-of-data/guids-and-uuids</a>)</li> </ol> <p>Note that manifest files that end in <code>-aws.s5cmd</code> reference files stored in Amazon Web Services (AWS) buckets, while <code>-gcs.s5cmd</code> reference files in Google Cloud Storage. The actual files are identical and are mirrored between AWS and GCP.</p> <h3>Download instructions</h3> <p>Each of the manifests include instructions in the header on how to download the included files.</p> <p>To download the files using <code>.s5cmd</code> manifests:</p> <ol> <li>install <a href="https://github.com/ImagingDataCommons/idc-index">idc-index</a> package: <code>pip install --upgrade idc-index</code></li> <li>download the files referenced by manifests included in this dataset by passing the <code>.s5cmd</code> manifest file: <code>idc download manifest.s5cmd</code>.</li> </ol> <p>To download the files using <code>.dcf</code> manifest, see manifest header.</p> <h3>Acknowledgments</h3> <p>Imaging Data Commons team has been funded in whole or in part with Federal funds from the National Cancer Institute, National Institutes of Health, under Task Order No. HHSN26110071 under Contract No. HHSN261201500003l.</p> <h3>References</h3> <p>[1] Fedorov, A., Longabaugh, W. J. R., Pot, D., Clunie, D. A., Pieper, S. D., Gibbs, D. L., Bridge, C., Herrmann, M. D., Homeyer, A., Lewis, R., Aerts, H. J. W., Krishnaswamy, D., Thiriveedhi, V. K., Ciausu, C., Schacherer, D. P., Bontempi, D., Pihl, T., Wagner, U., Farahani, K., Kim, E. & Kikinis, R. <i>National Cancer Institute Imaging Data Commons: Toward Transparency, Reproducibility, and Scalability in Imaging Artificial Intelligence</i>. RadioGraphics (2023). <a href="https://doi.org/10.1148/rg.230180">https://doi.org/10.1148/rg.230180</a></p>
Histopathology images for end-to-end AI, based on TCGA-BRCA
<p>These are histopathological images which are derived from the TCGA-BRCA breast cancer histology dataset at https://portal.gdc.cancer.gov/ (please check this website for the original data license). They can be used for end-to-end artificial intelligence (AI) workflows such as DeepMed (https://github.com/KatherLab/deepmed) which aim to predict high-level features directly from digital images with weakly supervised transfer learning. Here, we use two subsets of these digitized images:</p> <p>1) TCGA-BRCA-A2, these are all images from Walter Reed National Military Medical Center (tissue source site code A2, N=100 images) in the TCGA-BRCA database (tcga-brca-a2-deepmed-tiles.zip)</p> <p>2) TCGA-BRCA-E2, these are all images from Roswell Park Comprehensive Cancer Center (tissue source site code E2, N=90 images) in the TCGA-BRCA database (tcga-brca-e2-deepmed-tiles.zip)</p> <p>see also https://gdc.cancer.gov/resources-tcga-users/tcga-code-tables/tissue-source-site-codes </p> <p>The images were preprocessed according to the Aachen Protocol for Deep Learning Histopathology which is available at https://zenodo.org/record/3694994. Specifically, digital whole slide images (SVS format) of hematoxylin & eosin (H&E) stained slides were tessellated (without manual annotations) into tiles of 256x256 px edge length at 1 µm/px. Then, images were color-normalized using the Macenko method as described before (https://www.nature.com/articles/s43018-020-0087-6) and saved as JPEG files. For the A2 cohort, an additional ZIP archive is provided in which only 100 random image tiles are saved for each patient (tcga-brca-a2-deepmed-tiles_100.zip). In addition, we provide a CLINI and a SLIDE table as defined in the "Aachen Protocol". The CLINI table contains clinico-pathological data for all included patients and it is derived from clinical information on www.cbioportal.org as well as from Thorsson et al. (https://pubmed.ncbi.nlm.nih.gov/29628290/). We recommend to use the A2 dataset for training and the E2 dataset for testing. Please cite the relevant papers if you re-use this dataset, more information is available on www.kather.ai</p>
SAMPLER representations of TCGA-BRCA DX WSIs using an InceptionV3 backbone pretrained on imagenet
Open the record for dataset details and reuse information.
SAMPLER representations of TCGA-BRCA frozen WSIs using an InceptionV3 backbone pretrained on imagenet
Open the record for dataset details and reuse information.
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.