从像素到千兆像素：使用 Pixel-Mamba 桥接局部归纳偏置与长距离依赖
From Pixels to Gigapixels: Bridging Local Inductive Bias and Long-Range Dependencies with Pixel-Mamba
AI总结：
针对全切片图像分析的计算与表示学习挑战，提出 Pixel-Mamba 架构，结合 Mamba 模块与局部归纳偏置，无需病理学预训练即超越 SOTA 基础模型性能。
摘要：
组织病理学在医学诊断中发挥着关键作用，全切片图像（WSIs）提供的宝贵见解直接影响临床决策。然而，WSIs 的大尺寸和复杂性在计算效率和有效表示学习方面给深度学习模型带来了重大挑战。在本研究中，我们提出了 Pixel-Mamba，一种旨在高效处理千兆像素 WSIs 的新型深度学习架构。Pixel-Mamba 利用 Mamba 模块（一种具有线性内存复杂度的状态空间模型（SSM）），并通过逐渐扩展 token（类似于卷积神经网络）引入局部归纳偏置。这使得 Pixel-Mamba 能够分层结合局部和全局信息，同时高效应对计算挑战。值得注意的是，在一系列肿瘤分期和生存分析任务中，Pixel-Mamba 达到甚至超越了在数百万 WSIs 或 WSI-文本对上预训练的最先进（SOTA）基础模型的定量性能，{\bf 甚至无需任何病理学特定的预训练}。大量实验证明 Pixel-Mamba 是用于端到端 WSI 分析的强大且高效的框架。
英文摘要：
Histopathology plays a critical role in medical diagnostics, with whole slide images (WSIs) offering valuable insights that directly influence clinical decision-making. However, the large size and complexity of WSIs may pose significant challenges for deep learning models, in both computational efficiency and effective representation learning. In this work, we introduce Pixel-Mamba, a novel deep learning architecture designed to efficiently handle gigapixel WSIs. Pixel-Mamba leverages the Mamba module, a state-space model (SSM) with linear memory complexity, and incorporates local inductive biases through progressively expanding tokens, akin to convolutional neural networks. This enables Pixel-Mamba to hierarchically combine both local and global information while efficiently addressing computational challenges. Remarkably, Pixel-Mamba achieves or even surpasses the quantitative performance of state-of-the-art (SOTA) foundation models that were pretrained on millions of WSIs or WSI-text pairs, in a range of tumor staging and survival analysis tasks, {\bf even without requiring any pathology-specific pretraining}. Extensive experiments demonstrate the efficacy of Pixel-Mamba as a powerful and efficient framework for end-to-end WSI analysis.
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。
