UN-SAM: Universal Prompt-Free Segmentation for Generalized Nuclei Images

TL;DR

This work addresses the challenge of robust nuclei segmentation in digital pathology despite tissue and imaging heterogeneity, where traditional SAM-based methods require labor-intensive prompts. It introduces UN-SAM, a prompt-free framework built from a Domain-adaptive Tuning Encoder, a Multi-scale Self-Prompt Generation module, and a Domain Query-enhanced Decoder to enable automatic, cross-domain nuclei segmentation. The approach demonstrates superior performance on both semantic and instance segmentation tasks and exhibits strong zero-shot generalization across diverse nuclei datasets, significantly reducing the need for manual annotations. By enabling automatic prompt generation and domain-aware decoding, UN-SAM promises substantial improvements in clinical throughput and consistency for nuclei analysis.

Abstract

In digital pathology, precise nuclei segmentation is pivotal yet challenged by the diversity of tissue types, staining protocols, and imaging conditions. Recently, the segment anything model (SAM) revealed overwhelming performance in natural scenarios and impressive adaptation to medical imaging. Despite these advantages, the reliance of labor-intensive manual annotation as segmentation prompts severely hinders their clinical applicability, especially for nuclei image analysis containing massive cells where dense manual prompts are impractical. To overcome the limitations of current SAM methods while retaining the advantages, we propose the Universal prompt-free SAM framework for Nuclei segmentation (UN-SAM), by providing a fully automated solution with remarkable generalization capabilities. Specifically, to eliminate the labor-intensive requirement of per-nuclei annotations for prompt, we devise a multi-scale Self-Prompt Generation (SPGen) module to revolutionize clinical workflow by automatically generating high-quality mask hints to guide the segmentation tasks. Moreover, to unleash the generalization capability of SAM across a variety of nuclei images, we devise a Domain-adaptive Tuning Encoder (DT-Encoder) to seamlessly harmonize visual features with domain-common and domain-specific knowledge, and further devise a Domain Query-enhanced Decoder (DQ-Decoder) by leveraging learnable domain queries for segmentation decoding in different nuclei domains. Extensive experiments prove that UN-SAM with exceptional performance surpasses state-of-the-arts in nuclei instance and semantic segmentation, especially the generalization capability in zero-shot scenarios. The source code is available at https://github.com/CUHK-AIM-Group/UN-SAM.

Figures (6)

• Figure 1: Performance comparison on nuclei image segmentation. The semantic segmentation is measured by Dice, and instance segmentation (marked as inst.) is measured by Aggregated Jaccard Index (AJI).
• Figure 2: The overview of the proposed UN-SAM for nuclei image segmentation, consisting of DT-Encoder, SPGen and DQ-Decoder. For ease of understanding, we elaborate on the case of UN-SAM with four nuclei image domains. Our UN-SAM can achieve superior generalization performance on these domains without the need for manual annotations.
• Figure 3: The illustration of the transformer layer with the domain bypass in the DT-Encoder. In the domain bypass, the domain-common and domain-specific embeddings process image embeddings in sequence.
• Figure 4: Visualization of generalized nuclei instance segmentation. ${+}$ indicates medical SAMs using point prompts, and $*$ indicates that classical methods are trained and tested separately for each dataset. Our UN-SAM segments more nuclei with accurate boundaries while having fewer false positives.
• Figure 5: Hyper-parameter analysis of confidence threshold on nuclei semantic segmentation of the DSB dataset.