VISTA-PATH: An interactive foundation model for pathology image segmentation and quantitative analysis in computational pathology
Abstract
VISTA-PATH is an interactive, class-aware pathology segmentation model that integrates visual context, semantic descriptions, and expert feedback to enable precise multi-class segmentation and clinical interpretation in digital pathology.
Accurate semantic segmentation for histopathology image is crucial for quantitative tissue analysis and downstream clinical modeling. Recent segmentation foundation models have improved generalization through large-scale pretraining, yet remain poorly aligned with pathology because they treat segmentation as a static visual prediction task. Here we present VISTA-PATH, an interactive, class-aware pathology segmentation foundation model designed to resolve heterogeneous structures, incorporate expert feedback, and produce pixel-level segmentation that are directly meaningful for clinical interpretation. VISTA-PATH jointly conditions segmentation on visual context, semantic tissue descriptions, and optional expert-provided spatial prompts, enabling precise multi-class segmentation across heterogeneous pathology images. To support this paradigm, we curate VISTA-PATH Data, a large-scale pathology segmentation corpus comprising over 1.6 million image-mask-text triplets spanning 9 organs and 93 tissue classes. Across extensive held-out and external benchmarks, VISTA-PATH consistently outperforms existing segmentation foundation models. Importantly, VISTA-PATH supports dynamic human-in-the-loop refinement by propagating sparse, patch-level bounding-box annotation feedback into whole-slide segmentation. Finally, we show that the high-fidelity, class-aware segmentation produced by VISTA-PATH is a preferred model for computational pathology. It improve tissue microenvironment analysis through proposed Tumor Interaction Score (TIS), which exhibits strong and significant associations with patient survival. Together, these results establish VISTA-PATH as a foundation model that elevates pathology image segmentation from a static prediction to an interactive and clinically grounded representation for digital pathology. Source code and demo can be found at https://github.com/zhihuanglab/VISTA-PATH.
Community
🚀 VISTA-PATH is introduced as the first interactive segmentation foundation model for pathology.
It advances computational pathology workflows by enabling more accurate, interpretable, and human-guided quantitative measurements. Key highlights include:
1️⃣ Large-scale training: Trained on over 1.6M image-mask-text pairs
2️⃣ State-of-the-art performance: Accurate segmentation across both in-distribution and out-of-distribution tissues
3️⃣ Interactive refinement: Outputs can be efficiently refined using bounding-box prompts with only a few active-learning steps
4️⃣ Deployment-ready: Fully integrated into https://tissuelab.org and available for immediate use
📄 Read the arXiv preprint: https://arxiv.org/abs/2601.16451
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation (2026)
- SwinTF3D: A Lightweight Multimodal Fusion Approach for Text-Guided 3D Medical Image Segmentation (2025)
- DualProtoSeg: Simple and Efficient Design with Text- and Image-Guided Prototype Learning for Weakly Supervised Histopathology Image Segmentation (2025)
- MedVL-SAM2: A unified 3D medical vision-language model for multimodal reasoning and prompt-driven segmentation (2026)
- TGC-Net: A Structure-Aware and Semantically-Aligned Framework for Text-Guided Medical Image Segmentation (2025)
- Boundary-Aware Test-Time Adaptation for Zero-Shot Medical Image Segmentation (2025)
- ConStruct: Structural Distillation of Foundation Models for Prototype-Based Weakly Supervised Histopathology Segmentation (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper