Skip to content

Dataset · Aignostics

Tumor histology images from the TCGA atlas

Aignostics/OpenTME

Spatial annotation of tumor microenvironments on histological slides for medical computer vision.

What's inside

Inside are between 10,000 and 100,000 whole-slide tissue images (H&E staining) from The Cancer Genome Atlas (TCGA) project. The data is supplemented with spatial profiles of tumor microenvironments obtained using the HETA model from Aignostics. The dataset is open to academic researchers.

What you can do with it

  • Training and fine-tuning models for cell segmentation and detection in digital pathology
  • Feature extraction for classification of histological images
Tasks
Image classification, Image segmentation, Image feature extraction, Object detection
Size
10K–100K rows
Downloads this month
410
Likes
51
Access
on request on Hugging Face

How to load it

from datasets import load_dataset

ds = load_dataset("Aignostics/OpenTME")