mahmoodlab/TRIDENT
A Python toolkit for large-scale whole-slide histopathology image processing using deep learning foundation models.

Velocity · 7d
+1.2
★ / day
Trend
→steady
star history
Trident is a research toolkit developed by Harvard Medical School for processing pathology whole-slide images. It provides an end-to-end pipeline that performs tissue segmentation, extracts patch coordinates, and generates patch or slide embeddings using over 20 different patch encoders and multiple slide encoders. The toolkit supports multi-GPU processing and various WSI formats including OpenSlide, CuCim, OME-Zarr, and Zeiss CZI.