超图Mamba用于高效全切片图像理解
Hypergraph Mamba for Efficient Whole Slide Image Understanding
AI总结：
针对全切片图像分析中现有方法计算成本高的问题，提出WSI-HGMamba框架，融合超图神经网络与状态空间模型，实现高效且准确的高阶关系建模，计算量降低达7倍。
摘要：
组织病理学中的全切片图像（WSIs）因其超高分辨率、巨大规模及复杂的空间关系，对广泛的医学图像分析构成了重大挑战。尽管现有的多实例学习（MIL）方法，如图神经网络（GNNs）和Transformer，展现出强大的实例级建模能力，但它们在可扩展性和计算成本方面面临限制。为克服这些局限，我们提出了WSI-HGMamba，一个新颖的框架，将超图神经网络（HGNNs）的高阶关系建模能力与状态空间模型的线性时间序列建模效率统一起来。我们设计的核心是HGMamba块，它整合了消息传递、超图扫描与展平以及双向状态空间建模（Bi-SSM），使模型在保持计算高效的同时，能够保留关系性和上下文线索。与Transformer和图Transformer对应方法相比，WSI-HGMamba在FLOPs上实现了高达7倍的减少，同时取得了更优越的性能。在多个公开和私有WSI基准上的大量实验表明，我们的方法为切片级理解提供了一种可扩展、准确且高效的解决方案，使其成为下一代病理学AI系统的有前景的基础架构。
英文摘要：
Whole Slide Images (WSIs) in histopathology pose a significant challenge for extensive medical image analysis due to their ultra-high resolution, massive scale, and intricate spatial relationships. Although existing Multiple Instance Learning (MIL) approaches like Graph Neural Networks (GNNs) and Transformers demonstrate strong instance-level modeling capabilities, they encounter constraints regarding scalability and computational expenses. To overcome these limitations, we introduce the WSI-HGMamba, a novel framework that unifies the high-order relational modeling capabilities of the Hypergraph Neural Networks (HGNNs) with the linear-time sequential modeling efficiency of the State Space Models. At the core of our design is the HGMamba block, which integrates message passing, hypergraph scanning & flattening, and bidirectional state space modeling (Bi-SSM), enabling the model to retain both relational and contextual cues while remaining computationally efficient. Compared to Transformer and Graph Transformer counterparts, WSI-HGMamba achieves superior performance with up to 7* reduction in FLOPs. Extensive experiments on multiple public and private WSI benchmarks demonstrate that our method provides a scalable, accurate, and efficient solution for slide-level understanding, making it a promising backbone for next-generation pathology AI systems.
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。
