datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
LUAD-CT-Survival
LUAD-CT-Survival (Long and Short Survival in Adenocarcinoma Lung CTs)
40 contrast-enhanced chest CT scans of lung adenocarcinoma patients from the
H. Lee Moffitt Cancer Center, each with an expert-seeded primary-tumor
segmentation and a binary survival-outcome label (long- vs short-survivor).
This is the segmentation-ready HuggingFace mirror.
Dataset Details
Field
Value
Modality
CT (contrast-enhanced, pre-surgical)
Body part
Lung (primary… See the full description on the dataset page: https://huggingface.co/datasets/MedOtter/LUAD-CT-Survival.tcga-luad-tabular-open
TCGA-LUAD — Tabular (Open Access)
Open-access TCGA-LUAD data from the NCI Genomic Data Commons, reshaped into one table per GDC data_type. Clinical, biospecimen and every open molecular modality for this cohort, in one place, queryable without downloading a single .tar or parsing a single TSV.
GDC data release: Data Release 46.0 - August 10, 2026
Built: 2026-09-12 04:06:47 UTC
Scope: one TCGA project — see [the family][repo] for the others
from datasets import load_dataset… See the full description on the dataset page: https://huggingface.co/datasets/gabrielaltay/tcga-luad-tabular-open.tcga-luad-provgigapath-embeddings
TCGA-LUAD — Prov-GigaPath Tile Embeddings
Pre-extracted 1536-dimensional tile embeddings for TCGA-LUAD diagnostic H&E
whole-slide images, produced with the Prov-GigaPath tile encoder
(prov-gigapath/prov-gigapath). Part of a four-encoder benchmark in which every
model was run on the identical tiles for a fair comparison.
Tiling (identical across all encoders in the study)
Source: raw TCGA-LUAD .svs (GDC, open-access diagnostic slides).
20× / 0.5 microns per pixel… See the full description on the dataset page: https://huggingface.co/datasets/Eswar1885/tcga-luad-provgigapath-embeddings.luadLua_DATA