MambaMIL：在计算病理学中通过序列重排序增强长序列建模
MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathology
AI总结：
本文提出MambaMIL，将Mamba引入病理WSI的MIL长序列建模，并通过SR-Mamba利用实例顺序与分布信息，以线性复杂度提升特征交互并缓解过拟合和计算开销。
摘要：
多示例学习（Multiple Instance Learning，MIL）已成为计算病理学中在全切片图像（Whole Slide Images，WSIs）内提取判别性特征表示的主导范式。尽管推动了显著进展，但现有MIL方法在促进示例之间全面且高效的交互方面仍存在局限，并面临计算耗时和过拟合等挑战。本文将选择性扫描空间状态序列模型（Selective Scan Space State Sequential Model，Mamba）引入多示例学习（MIL），用于具有线性复杂度的长序列建模，称为MambaMIL。通过继承原始Mamba的能力，MambaMIL展现出全面理解和感知长示例序列的能力。此外，我们提出了感知示例顺序与分布的Sequence Reordering Mamba（SR-Mamba），以利用长序列中蕴含的固有有价值信息。以SR-Mamba为核心组件，MambaMIL能够有效捕获更具判别性的特征，并缓解与过拟合和高计算开销相关的挑战。在涵盖九个多样化数据集的两项公开且具有挑战性的任务上进行的大量实验表明，我们提出的框架性能优于最先进的MIL方法。代码已发布于https://github.com/isyangshu/MambaMIL。
英文摘要：
Multiple Instance Learning (MIL) has emerged as a dominant paradigm to extract discriminative feature representations within Whole Slide Images (WSIs) in computational pathology. Despite driving notable progress, existing MIL approaches suffer from limitations in facilitating comprehensive and efficient interactions among instances, as well as challenges related to time-consuming computations and overfitting. In this paper, we incorporate the Selective Scan Space State Sequential Model (Mamba) in Multiple Instance Learning (MIL) for long sequence modeling with linear complexity, termed as MambaMIL. By inheriting the capability of vanilla Mamba, MambaMIL demonstrates the ability to comprehensively understand and perceive long sequences of instances. Furthermore, we propose the Sequence Reordering Mamba (SR-Mamba) aware of the order and distribution of instances, which exploits the inherent valuable information embedded within the long sequences. With the SR-Mamba as the core component, MambaMIL can effectively capture more discriminative features and mitigate the challenges associated with overfitting and high computational overhead. Extensive experiments on two public challenging tasks across nine diverse datasets demonstrate that our proposed framework performs favorably against state-of-the-art MIL methods. The code is released at https://github.com/isyangshu/MambaMIL.
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。
