Is SAM3 ready for pathology segmentation?

2026-04-20 · Qiuyu Kong, Shakiba Sharifi, Yiming Wang, Marco Cristani, Zanxi Ruan arxiv

Is Segment Anything Model 3 (SAM3) capable in segmenting Any Pathology Images? Digital pathology segmentation spans tissue-level and nuclei-level scales, where traditional methods often suffer from high annotation costs and poor generalization. SAM3 introduces Promptable Concept Segmentation, offering a potential automated interface via text prompts. With this work, we propose a systematic evaluation protocol to explore the capability space of SAM3 in a structured manner. Specifically, we evaluate SAM3 under different supervision settings including zero-shot, few-shot, and supervised with varying prompting strategies. Our extensive evaluation on pathological datasets including NuInsSeg, PanNuke and GlaS, reveals that: (1) text-only prompts poorly activate nuclear concepts; (2) performance is highly sensitive to visual prompt types and budgets; (3) few-shot learning offers gains, but SAM3 lacks robustness against visual prompt noise; and (4) a significant gap persists between prompt-based usage and task-trained adapter-based reference. Our study delineates SAM3's boundaries in pathology image segmentation and provides practical guidance on the necessity of pathology domain adaptation.

📄 PDF Abstract BibTeX arXiv:2604.18225

Code (0)

등록된 구현이 없습니다.

Tasks

Image Segmentation Few-Shot Learning Domain Adaptation

Pathology Segmentation using Distributional Differences to Images of Healthy Origin

2018-05-25 · Simon Andermatt, Antal Horváth, Simon Pezold, Philippe Cattin

Fully supervised segmentation methods require a large training cohort of already segmented images, providing information at the pixel level of each image. We present a method to automatically segment and model pathologie…

Image-to-Image Translation Segmentation Translation Weakly supervised segmentation

Transplant-Ready? Evaluating AI Lung Segmentation Models in Candidates with Severe Lung Disease

2025-09-18 · Jisoo Lee, Michael R. Harowicz, Yuwen Chen, Hanxue Gu 외 arxiv

This study evaluates publicly available deep-learning based lung segmentation models in transplant-eligible patients to determine their performance across disease severity levels, pathology categories, and lung sides, an…

Multi-Layer Pseudo-Supervision for Histopathology Tissue Semantic Segmentation using Patch-level Classification Labels

2021-10-14 · Chu Han, Jiatai Lin, Jinhai Mai, Yi Wang 외

Tissue-level semantic segmentation is a vital step in computational pathology. Fully-supervised models have already achieved outstanding performance with dense pixel-level annotations. However, drawing such labels on the…

Segmentation Semantic Segmentation Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation+1

VISTA-PATH: An interactive foundation model for pathology image segmentation and quantitative analysis in computational pathology

2026-01-23 · Peixian Liang, Songhao Li, Shunsuke Koga, Yutong Li 외 arxiv

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…

Semantic Segmentation Image Segmentation

SAM-Path: A Segment Anything Model for Semantic Segmentation in Digital Pathology

2023-07-12 · Jingwei Zhang, Ke Ma, Saarthak Kapse, Joel Saltz 외

Semantic segmentations of pathological entities have crucial clinical value in computational pathology workflows. Foundation models, such as the Segment Anything Model (SAM), have been recently proposed for universal use…

Instance Segmentation Segmentation Semantic Segmentation