NuSegDG: Integration of Heterogeneous Space and Gaussian Kernel for Domain-Generalized Nuclei Segmentation

TL;DR

NuSegDG is a novel framework that enhances nuclei segmentation across diverse domains by integrating heterogeneous space adaptation and Gaussian kernel prompts, reducing manual effort and improving generalization.

Contribution

It introduces a Heterogeneous Space Adapter, Gaussian-Kernel Prompt Encoder, and Two-Stage Mask Decoder to improve domain-generalized nuclei segmentation with minimal manual prompts.

Findings

Achieves state-of-the-art domain generalization in nuclei segmentation.

Demonstrates superior performance over existing methods.

Reduces manual prompt requirements significantly.

Abstract

Domain-generalized nuclei segmentation refers to the generalizability of models to unseen domains based on knowledge learned from source domains and is challenged by various image conditions, cell types, and stain strategies. Recently, the Segment Anything Model (SAM) has made great success in universal image segmentation by interactive prompt modes (e.g., point and box). Despite its strengths, the original SAM presents limited adaptation to medical images. Moreover, SAM requires providing manual bounding box prompts for each object to produce satisfactory segmentation masks, so it is laborious in nuclei segmentation scenarios. To address these limitations, we propose a domain-generalizable framework for nuclei image segmentation, abbreviated to NuSegDG. Specifically, we first devise a Heterogeneous Space Adapter (HS-Adapter) to learn multi-dimensional feature representations of different nuclei domains by injecting a small number of trainable parameters into the image encoder of SAM. To alleviate the labor-intensive requirement of manual prompts, we introduce a Gaussian-Kernel Prompt Encoder (GKP-Encoder) to generate density maps driven by a single point, which guides segmentation predictions by mixing position prompts and semantic prompts. Furthermore, we present a Two-Stage Mask Decoder (TSM-Decoder) to effectively convert semantic masks to instance maps without the manual demand for morphological shape refinement. Based on our experimental evaluations, the proposed NuSegDG demonstrates state-of-the-art performance in nuclei instance segmentation, exhibiting superior domain generalization capabilities. The source code is available at https://github.com/xq141839/NuSegDG.