arXiv 2606.219132026-06-23cs.CVcs.AI

重新思考视觉基础模型在高效细胞分割中的适应

Rethinking the Adaptation of Vision Foundation Models for Efficient Cell Segmentation

School of Computer Science, University of Nottingham, UK（英国诺丁汉大学计算机科学学院）；School of Computer Science, University of Nottingham Ningbo China, China（中国宁波诺丁汉大学计算机科学学院）；School of Engineering and Physical Science, University of Lincoln, UK（英国林肯大学工程与物理科学学院）；Department of Computer Science, University of Rochester, USA（美国罗切斯特大学计算机科学系）

Qing Xu, Xiangjian He, Wenting Duan, Jiebo Luo, Zhen Chen

备注：: Accepted by MICCAI 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出EffiCell-Seg框架，利用冻结的视觉基础模型中的全局显著性和局部形态先验，通过细胞结构提示编码器和协同掩码解码器实现高效细胞分割，仅需约5M可训练参数。

摘要：

细胞分割对于计算病理学和生物医学发现至关重要。尽管最近的视觉基础模型（VFMs）展示了卓越的通用特征表示，但释放其在细胞成像中的全部潜力目前受到资源密集型适应范式的瓶颈。现有方法通常依赖于微调重型视觉编码器，导致大量的计算开销和对大规模标注的依赖。为了解决这个问题，我们提出了EffiCell-Seg框架，用于在不重新训练视觉编码器的情况下实现高效细胞分割。我们的核心见解是，预训练的VFMs内在地编码了互补的结构先验：用于定位潜在细胞的全局显著性和用于描绘细胞结构的局部形态模式。为了利用这些先验，我们设计了一个细胞结构提示编码器（CSP-Encoder），将从冻结的VFM表示中合成的语义感知显著性和主要形态特征转化为显式的结构先验图。此外，我们提出了一个协同掩码解码器（SM-Decoder），通过联合预测几何距离场和语义图并相互交叉引导来强制上下文一致性。大量实验表明，EffiCell-Seg在多种细胞成像模态上优于最先进的方法，同时仅需约5M可训练参数，比完全微调的VFM对应物少130倍以上。代码可在该https URL获取。

英文摘要：

Cell segmentation is critical for computational pathology and biomedical discovery. While recent Vision Foundation Models (VFMs) have demonstrated remarkable universal feature representations, unlocking their full potential for cellular imaging is currently bottlenecked by resource-intensive adaptation paradigms. Existing methods typically rely on fine-tuning heavy visual encoders, leading to extensive computational overhead and a dependency on large-scale annotations. To address this, we propose the EffiCell-Seg framework for highly efficient cell segmentation without re-training the visual encoder. Our core insight is that pretrained VFMs intrinsically encode complementary structural priors: global saliency for localizing potential cells, and local morphological patterns for delineating cellular structures. To harness these priors, we devise a Cell Structure Prompt Encoder (CSP-Encoder) that synthesizes semantic-aware saliency and principal morphological features from frozen VFM representations into explicit structural prior maps. Moreover, we propose a Synergistic Mask Decoder (SM-Decoder) that enforces contextual consistency by jointly predicting geometric distance fields and semantic maps via mutual cross-guidance. Extensive experiments demonstrate that EffiCell-Seg outperforms state-of-the-art methods across diverse cell imaging modalities while requiring only ~5M trainable parameters, over 130x fewer than fully fine-tuned VFM counterparts. The code is available at https://github.com/xq141839/EffiCell-Seg.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。