论文标题
学习二进制和稀疏置换不变的表示形式
Learning Binary and Sparse Permutation-Invariant Representations for Fast and Memory Efficient Whole Slide Image Search
论文作者
论文摘要
学习合适的全幻灯片图像（WSIS）表示有效检索系统是一项非平凡的任务。从当前方法中获得的WSI嵌入在欧几里得空间中并不理想有效的WSI检索。此外，由于多组补丁集的同时处理，当前大多数当前方法都需要高GPU存储器。为了应对这些挑战，我们提出了一个新颖的框架，用于利用深厚的生成建模和Fisher向量学习二进制和稀疏的WSI表示。我们介绍了新的损失功能，以学习稀疏和二进制置换不变的WSI表示，这些表征采用基于实例的培训来提高记忆效率。在癌症基因组地图集（TCGA）和肝脏-Kidney-Stomach（LKS）数据集上验证了学习的WSI表示。在检索准确性和速度方面，提出的方法优于Yottixel（最新的组织病理学图像搜索引擎）。此外，我们在公共基准LKS数据集上对SOTA实现竞争性能进行WSI分类。
Learning suitable Whole slide images (WSIs) representations for efficient retrieval systems is a non-trivial task. The WSI embeddings obtained from current methods are in Euclidean space not ideal for efficient WSI retrieval. Furthermore, most of the current methods require high GPU memory due to the simultaneous processing of multiple sets of patches. To address these challenges, we propose a novel framework for learning binary and sparse WSI representations utilizing a deep generative modelling and the Fisher Vector. We introduce new loss functions for learning sparse and binary permutation-invariant WSI representations that employ instance-based training achieving better memory efficiency. The learned WSI representations are validated on The Cancer Genomic Atlas (TCGA) and Liver-Kidney-Stomach (LKS) datasets. The proposed method outperforms Yottixel (a recent search engine for histopathology images) both in terms of retrieval accuracy and speed. Further, we achieve competitive performance against SOTA on the public benchmark LKS dataset for WSI classification.
