Long-MIL：扩展用于组织病理学全切片图像分析的长上下文多示例学习
Long-MIL: Scaling Long Contextual Multiple Instance Learning for Histopathology Whole Slide Image Analysis
AI总结：
提出Long-MIL方法，通过在注意力中引入线性偏置修正位置嵌入并适应二维长上下文WSI，结合Flash-Attention降低复杂度，在4个数据集上验证了对形状变化WSI分析的优越性。
摘要：
组织病理学图像分析是癌症临床诊断的金标准。在医生的日常工作和计算机辅助诊断中，使用组织病理学组织的全切片图像（WSI）进行分析。由于分辨率极其庞大，先前的方法通常将WSI划分为大量图块，然后在开发计算机辅助诊断工具时，通过多示例学习（MIL）聚合WSI内的所有图块以进行切片级预测。然而，大多数先前的WSI-MIL模型使用没有成对交互和任何位置信息的全局注意力，或者使用带有绝对位置嵌入的自注意力，无法很好地处理形状变化的大型WSI，例如，由于组织病理学WSI收集的困难，模型开发集总是有限的，模型部署后的测试WSI可能比训练WSI更大。为了解决这个问题，在本文中，我们提出通过将线性偏置引入注意力来修正形状变化的长上下文WSI的位置嵌入，并将其从一维长序列适应到二维长上下文WSI，这有助于模型将位置嵌入外推到未见或欠拟合的位置。我们进一步利用Flash-Attention模块来解决Transformer的计算复杂度问题，与先前的注意力近似工作相比，这也保持了完整的自注意力性能。我们的方法，长上下文MIL（Long-MIL）在包括WSI分类和生存预测任务的4个数据集的广泛实验中进行了评估，以验证其在形状变化的WSI上的优越性。源代码将很快开放访问。
英文摘要：
Histopathology image analysis is the golden standard of clinical diagnosis for Cancers. In doctors daily routine and computer-aided diagnosis, the Whole Slide Image (WSI) of histopathology tissue is used for analysis. Because of the extremely large scale of resolution, previous methods generally divide the WSI into a large number of patches, then aggregate all patches within a WSI by Multi-Instance Learning (MIL) to make the slide-level prediction when developing computer-aided diagnosis tools. However, most previous WSI-MIL models using global-attention without pairwise interaction and any positional information, or self-attention with absolute position embedding can not well handle shape varying large WSIs, e.g. testing WSIs after model deployment may be larger than training WSIs, since the model development set is always limited due to the difficulty of histopathology WSIs collection. To deal with the problem, in this paper, we propose to amend position embedding for shape varying long-contextual WSI by introducing Linear Bias into Attention, and adapt it from 1-d long sequence into 2-d long-contextual WSI which helps model extrapolate position embedding to unseen or under-fitted positions. We further utilize Flash-Attention module to tackle the computational complexity of Transformer, which also keep full self-attention performance compared to previous attention approximation work. Our method, Long-contextual MIL (Long-MIL) are evaluated on extensive experiments including 4 dataset including WSI classification and survival prediction tasks to validate the superiority on shape varying WSIs. The source code will be open-accessed soon.
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。
