Multiple Instance Learning (MIL) is a widely employed framework for learning on gigapixel whole-slide images (WSIs) from WSI-level annotations. In most MIL based analytical pipelines for WSI-level analysis, the WSIs are often divided into patches and deep features for patches (i.e., patch embeddings) are extracted prior to training to reduce the overall computational cost and cope with the GPUs' limited RAM. To overcome this limitation, we present EmbAugmenter, a data augmentation generative adversarial network (DA-GAN) that can synthesize data augmentations in the embedding space rather than in the pixel space, thereby significantly reducing the computational requirements. Experiments on the SICAPv2 dataset show that our approach outperforms MIL without augmentation and is on par with traditional patch-level augmentation for MIL training while being substantially faster.
翻译:多实例学习(MIL)是一个广泛应用的框架,用于学习来自WSI级注解的千象整流图像(WSIs),在大多数基于MIL的用于WSI级分析的分析管道中,WSI常常被分为补丁和补丁(即补丁嵌入器)的深层特征,在培训前进行提取,以减少总体计算成本,并应对GPU的有限内存。为了克服这一限制,我们介绍了EmbAugment,这是一个数据增强基因对抗网络(DA-GAN),它可以综合嵌入空间而不是像素空间的数据增强,从而大大减少计算要求。关于SICAPv2数据集的实验表明,我们的方法在不增强的情况下比MIL更符合传统的补丁级增强功能,同时大大加快了MIL培训。