datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
tcga-wsi-uni2h-features
TCGA WSI UNI2H Features
Dataset Summary
This dataset provides tile-level UNI2-h embeddings extracted from TCGA whole-slide images (WSIs) using a reproducible, auditable pipeline designed for computational pathology research.
Data is organized by project (for example TCGA-HNSC) and currently exposes:
features/ containing H5 feature files with tile-level embeddings
vis/ containing overlay images for quality inspection and pipeline verification
[!IMPORTANT]
Unlike the… See the full description on the dataset page: https://huggingface.co/datasets/W8Yi/tcga-wsi-uni2h-features.tcga-brca-titan-idc-ilc
tcga-brca-titan-idc-ilc
1. Tổng quan
[CẦN ĐIỀN THỦ CÔNG: mục đích, ngữ cảnh tạo dataset]
Tổng số bản ghi (cộng tất cả manifest phát hiện được): 4228
Số manifest phát hiện được trong bộ nhớ: 3 (df, brca_df, full_df)
Repo HuggingFace: okbro1234/tcga-brca-titan-idc-ilc
2. Cấu trúc lưu trữ tại đích
/ # suy từ hàm `HfApi`
file.txt # suy từ hàm `HfApi`
lfs.bin # suy từ hàm `HfApi`
shard_{i}_of_5.bin # suy từ hàm `HfApi`
remote/file/path.h5 #… See the full description on the dataset page: https://huggingface.co/datasets/okbro1234/tcga-brca-titan-idc-ilc.TCGA_OncoTree_pt2
TCGA_OncoTree_pt2
1. Tổng quan
[CẦN ĐIỀN THỦ CÔNG: mục đích, ngữ cảnh tạo dataset]
Tổng số bản ghi (cộng tất cả manifest phát hiện được): 23984
Số manifest phát hiện được trong bộ nhớ: 3 (df, labels_df, progress)
Repo HuggingFace chính: ento3686/TCGA_OncoTree_pt2
⚠️ Dataset được lưu trên 2 repo/tài khoản HuggingFace khác nhau:
ento3686/TCGA_OncoTree_pt2 (biến: REPO_ID_2, UPLOAD_REPO_ID, CENTRAL_PROGRESS_REPO_ID, _repo_id_var)
tuna2004/TCGA_OncoTree (biến:… See the full description on the dataset page: https://huggingface.co/datasets/ento3686/TCGA_OncoTree_pt2.tcga-ut
Histology images from uniform tumor regions in TCGA Whole Slide Images (TCGA-UT-Internal, TCGA-UT-External)
This repository provides a benchmarking framework for the TCGA histology image dataset originally published on Zenodo. It includes predefined train/validation/test splits and example code for foundation model evaluation.
Task
Classification of 31 different cancer types from tumor histopathological images.
Original Dataset Description… See the full description on the dataset page: https://huggingface.co/datasets/dakomura/tcga-ut.BraTS-TCGA
BraTS-TCGA (BraTS-TCGA-GBM + BraTS-TCGA-LGG)
Expert segmentation labels for the pre-operative TCGA glioma MRI cohorts
(Bakas et al. 2017), combining the two TCIA analysis-result collections
BraTS-TCGA-GBM (102 glioblastoma patients) and BraTS-TCGA-LGG
(65 lower-grade glioma patients) = 167 cases.
What this is (faithful-naming note): the publicly released training
half of the pre-operative subset of TCGA-GBM / TCGA-LGG, already
co-registered to a T1 template, resampled to 1 mm³… See the full description on the dataset page: https://huggingface.co/datasets/MedOtter/BraTS-TCGA.tcga-tissue-segmentation
Overview
This dataset consists of 242 images from The Cancer Genome Atlas (TCGA) pathology dataset manually annotated for segmentation of tissue (i.e. pixel-level annotation of presence or absence of tissue).
Each image is a full TCGA slide (mostly H&E) downsampled to 10 microns per pixel (MPP) and saved as a PNG.
Each image has a corresponding mask, which is also saved as a PNG where each pixel corresponds to the pixel at the same position in the 10 MPP image.
The pixel values of… See the full description on the dataset page: https://huggingface.co/datasets/conflux-xyz/tcga-tissue-segmentation.TCGA-LGG-Mask
TCGA-LGG-Mask — LGG Segmentation Dataset (Brain MRI)
Mirror of the LGG Segmentation Dataset ("Brain MRI segmentation"), the
canonical release by Mateusz Buda on Kaggle
(mateuszbuda/lgg-mri-segmentation), associated with:
Buda M., Saha A., Mazurowski M.A. Association of genomic subtypes of
lower-grade gliomas with shape features automatically extracted by a deep
learning algorithm. Computers in Biology and Medicine 109:218-225, 2019.
Brain MRI of 110 patients from the TCIA… See the full description on the dataset page: https://huggingface.co/datasets/MedOtter/TCGA-LGG-Mask.tcga_clamtcga-ov-multiomics-network-derived-results
TCGA-OV Multiomics Network Derived Results
This dataset contains derived, publication-ready outputs from a reproducible TCGA-OV multi-omics network analysis pipeline.
Current status
Primary manuscript target: Journal of Biomedical Informatics
Preferred bundle: manuscript/journal_of_biomedical_informatics/
Current JBI main manuscript status:
required statement-of-significance table included
main-paper combined tables/figures reduced to a compliant <=8
sequential in-text… See the full description on the dataset page: https://huggingface.co/datasets/hssling/tcga-ov-multiomics-network-derived-results.TCGA-Breast-Radiogenomics
TCGA-Breast-Radiogenomics
Whole-lesion breast tumour segmentation on dynamic contrast-enhanced (DCE)
MRI. 91 patients from the TCGA-BRCA cohort, each with one binary mask of the
primary invasive carcinoma, paired with its post-contrast source volume.
The upstream TCIA product is an analysis result: a 105 KB archive of masks in an
undocumented .les format with no image reference of any kind, plus a set of
spreadsheets. This mirror decodes those masks, resolves each one to its… See the full description on the dataset page: https://huggingface.co/datasets/MedOtter/TCGA-Breast-Radiogenomics.tcga
TCGA
A multi-omics subset of the TCGA PanCancer Atlas (RNA, methylation, mutation, clinical),
for use with AUTOENCODIX tutorials.
Base set (for Vanillix and other Tutorials)
Covers 8 cancer types: BRCA, OV, LUAD, UCEC, LUSC, COAD, READ, UCS.
rna.parquet — 3552 samples × 17448 genes (RNA expression)
methylation.parquet — 3875 samples × 9829 genes (per-gene methylation)
mutation.parquet — 3461 samples × 20304 genes (combined mutation/CNA score per gene;
restricted… See the full description on the dataset page: https://huggingface.co/datasets/autoencodix/tcga.TCGA_Brain
TCGA_Brain
1. Tổng quan
[CẦN ĐIỀN THỦ CÔNG: mục đích, ngữ cảnh tạo dataset]
Tổng số bản ghi: 1704
Repo HuggingFace: okbro1234/TCGA_Brain
2. Cấu trúc lưu trữ tại đích
/
(Suy tự động từ hàm HfApi trong notebook gốc; PATH_PREFIX hiện tại = ``)
3. Manifest và các cột dữ liệu
Cột
Dtype
Số giá trị thiếu (NaN)
file_id
object
0
file_name
object
0
slide_id
object
0
data_format
object
0
experimental_strategy
object
0… See the full description on the dataset page: https://huggingface.co/datasets/okbro1234/TCGA_Brain.sample-tcga-brcatcga-ut
Histology images from uniform tumor regions in TCGA Whole Slide Images (TCGA-UT-Internal, TCGA-UT-External)
This repository provides a benchmarking framework for the TCGA histology image dataset originally published on Zenodo. It includes predefined train/validation/test splits and example code for foundation model evaluation.
Task
Classification of 31 different cancer types from tumor histopathological images.
Original Dataset Description
This… See the full description on the dataset page: https://huggingface.co/datasets/qwertyuiop456556/tcga-ut.tcga-ucec-embedding
TCGA-UCEC endometrial pathology: page images + ColPali embeddings
Read-only serving assets for an endometrial pathology report review tool,
derived from the public TCGA / GDC endometrial (UCEC) corpus. All source
data is public and de-identified; embeddings come from the open-weight ColPali
model.
Contents
<patient_filename>/page_NNN.png -- rendered report page images at 200 DPI
(545 cases, 1921 pages), one folder per case.
<patient_filename>.npz -- ColPali page… See the full description on the dataset page: https://huggingface.co/datasets/reversely/tcga-ucec-embedding.SVS-TCGA-2048viral_cancer_tcga
TCGA Viral Etiology in Hepatocellular Carcinoma
Overview
Comprehensive transcriptomic analysis comparing viral (HBV/HCV) versus non-viral hepatocellular carcinoma (HCC) using The Cancer Genome Atlas (TCGA-LIHC) dataset.
Analysis Pipeline
Data Loading & QC - Patient ID standardization, viral status classification
Differential Expression - DESeq2 negative binomial modeling
Pathway Enrichment - KEGG & GO gene set enrichment analysis
Survival… See the full description on the dataset page: https://huggingface.co/datasets/QasimHussain/viral_cancer_tcga.Synthetic-TCGA-10M
PixCell: A generative foundation model for digital histopathology images
[📄 arXiv][🔬 PixCell-1024] [🔬 PixCell-256] [🔬 Pixcell-256-Cell-ControlNet] [💾 Synthetic-TCGA-10M]
Load dataset
import numpy as np
from datasets import load_dataset
dataset = load_dataset("StonyBrook-CVLab/Synthetic-TCGA-10M")
print("Total # of images:", len(dataset['train']))
idx = np.random.randint(0, len(dataset['train']))
image = dataset['train'][idx]['image']
TCGA-BRCA-30-samplesSVS-TCGA-BRtcga-ut
Histology images from uniform tumor regions in TCGA Whole Slide Images (TCGA-UT-Internal, TCGA-UT-External)
This repository provides a benchmarking framework for the TCGA histology image dataset originally published on Zenodo. It includes predefined train/validation/test splits and example code for foundation model evaluation.
Task
Classification of 31 different cancer types from tumor histopathological images.
Original Dataset Description… See the full description on the dataset page: https://huggingface.co/datasets/Sai452/tcga-ut.eval-tcga-mix-chr123-bs_512-32xl40s-aws-eval_on_tcga_chr123eval-tcga_mix_chr1-bs_512-c2b2This repository contains the eval results of "MethylProphet: A Generalized Gene-Contextual Model for Inferring Whole-Genome DNA Methylation Landscape".
Detailed instructions can be found at https://github.com/xk-huang/methylprophet/blob/main/docs/EXPERIMENTS.md.
eval-250116-train-tcga_chr1-base-wd_1e_5-half_data-16xl40seval-250116-train-tcga_chr1-base-b12_wi1024_mlp-wd_1e_5-half_data-16xl40seval-wo_tissue_embedder-tcga_mix_chr1-32xl40s-awseval-w_tissue_embedder-tcga_mix_chr1-32xl40s-c2b2eval-tcga_array_chr1-32xl40s-c2b2eval-tcga_array_epic_chr1-32xl40s-c2b2eval-tcga_array_wgbs_chr1-32xl40s-c2b2