TITAN
Multimodal whole-slide pathology foundation model pretrained on 335,645 WSIs with vision–language alignment.
| Category | Imaging & pathology |
|---|---|
| GitHub | mahmoodlab/TITAN |
| First public | 2024-11-29 (source) |
| Paper | https://doi.org/10.1038/s41591-025-03982-3 · Nature Medicine (2025) |
| License | CC-BY-NC-ND-4.0 (weights) |
| Pricing | Open source (non-commercial) |
| Tags | #pathology#foundation-model#vision-language |
| Last checked | 2026-10-16 |
Specs
| 2D / 3D | 2D (whole-slide images) |
|---|---|
| Modality | H&E whole-slide images + text |
| Segmentation type | N/A (slide-level embedding model) |
| GitHub stars | 373 |
| Interface | — |
Specs come from each project's README, paper or official page · TITAN README · TITAN site. “—” means we couldn't verify it.
Compare with…
Pick 1–3 other Imaging & pathology tools to compare side by side with TITAN.
Related
Generalist deep learning model for cellular segmentation.
Imaging & pathologyOpen source#segmentation
Star-convex object detection for nuclei segmentation.
Imaging & pathologyOpen source#segmentation#nuclei
Fast, interactive multi-dimensional image viewer for Python.
Imaging & pathologyOpen source#viewer#python