STHELAR 20X: Multi-Tissue Histology and Spatial Transcriptomics for Cell Type Prediction

STHELAR is a multi-tissue dataset integrating high-resolution spatial transcriptomics data with Hematoxylin & Eosin (H&E) whole slide images to provide detailed segmentation masks and cell-type annotations. The dataset was created by FelicieGS and last updated on Hugging Face in January 2026. It is designed for developing models capable of predicting cell types directly from histological images.

Use Cases

• Train cell type prediction models based on integrated H&E whole slide images and spatial transcriptomics data.
• Develop image segmentation algorithms based on the provided detailed segmentation masks.
• Benchmark multimodal models for cancer research based on the combined image and spatial transcriptomic data.

Strengths

• Integrates two high-resolution data modalities: spatial transcriptomics and H&E histology.
• Provides detailed segmentation masks and cell-type annotations for model development.
• Last updated on 2026-01-22, indicating recent maintenance.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and dataset size are unknown, which may limit suitability assessment.

Provenance

Source

Hugging Face, uploaded by author FelicieGS.

Collection Method

Integrates high-resolution spatial transcriptomics data with histology whole slide images.

Time Range

null

Freshness

Last updated 2026-01-22 14:22:48; freshness should be verified.

Geography

null