arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.01924cs.CVcs.LG
收藏

面向全玻片图像分类中位置感知多实例学习的RoFormer

RoFormer for Position Aware Multiple Instance Learning in Whole Slide Image Classification

Sanofi(赛诺菲)

Etienne Pochet, Rami Maroun, Roger Trullo

AI总结:

针对全玻片图像分类中现有多实例学习忽略块间空间关联的问题,提出基于RoFormer层的位置感知MIL方法,通过带相对位置编码的高效自注意力建模组织空间关系,在三个公开数据集上取得SOTA性能。

摘要:

全玻片图像(WSI)分类是计算病理学中的一项关键任务。然而,此类图像的十亿像素级尺寸仍是当前深度学习技术面临的一大挑战。现有方法依赖带有冻结特征提取器的多实例学习(MIL)模型。由于每张图像中的实例数量极多,MIL方法长期以来一直假设图像块(patch)具有独立性和排列不变性,忽略了组织结构以及图像块之间的关联。近期研究开始探索实例间的这种关联,但如此大量token带来的计算负载仍是一个限制因素,尤其是图像块的相对位置问题尚未得到解决。我们提出应用一种简洁的编码模块,即RoFormer层,它依托内存高效的精确自注意力机制和相对位置编码实现。该模块能够在尺寸大、形状任意的WSI的图像块上执行带相对位置编码的完整自注意力运算,满足了实例间关联建模与组织空间建模的需求。实验表明,在弱监督分类任务上,我们的方法在三个常用公开数据集(TCGA-NSCLC、BRACS和Camelyon16)上的表现优于当前最优的MIL模型。代码可在https://github.com/Sanofi-Public/DDS-RoFormerMIL 获取。

英文摘要:

Whole slide image (WSI) classification is a critical task in computational pathology. However, the gigapixel-size of such images remains a major challenge for the current state of deep-learning. Current methods rely on multiple-instance learning (MIL) models with frozen feature extractors. Given the the high number of instances in each image, MIL methods have long assumed independence and permutation-invariance of patches, disregarding the tissue structure and correlation between patches. Recent works started studying this correlation between instances but the computational workload of such a high number of tokens remained a limiting factor. In particular, relative position of patches remains unaddressed. We propose to apply a straightforward encoding module, namely a RoFormer layer , relying on memory-efficient exact self-attention and relative positional encoding. This module can perform full self-attention with relative position encoding on patches of large and arbitrary shaped WSIs, solving the need for correlation between instances and spatial modeling of tissues. We demonstrate that our method outperforms state-of-the-art MIL models on three commonly used public datasets (TCGA-NSCLC, BRACS and Camelyon16)) on weakly supervised classification tasks. Code is available at https://github.com/Sanofi-Public/DDS-RoFormerMIL

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。

↑