Gigapixel Whole-Slide Images Classification using Locally Supervised Learning
Gigapixel Whole-Slide Images Classification using Locally Supervised Learning
复制标题
DOI：
10.1007/978-3-031-16434-7_19
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Jingwei Zhang;Xin Zhang;Ke Ma;Rajarsi R. Gupta;J. Saltz;M. Vakalopoulou;D. Samaras
中科院分区：
文献类型：
--
作者：
Jingwei Zhang;Xin Zhang;Ke Ma;Rajarsi R. Gupta;J. Saltz;M. Vakalopoulou;D. Samaras
组织病理学全切片图像 (WSI) 在临床研究中发挥着非常重要的作用，并成为许多癌症诊断的金标准。然而，由于 WSI 规模巨大，生成用于处理 WSI 的自动工具具有挑战性。目前，为了解决这个问题，传统方法依赖于多实例学习（MIL）策略来处理补丁级别的 WSI。虽然有效，但此类方法的计算成本很高，因为将 WSI 平铺为图块需要时间，并且不会探索这些图块之间的空间关系。为了解决这些限制，我们提出了一个本地监督学习框架，该框架通过探索其包含的整个本地和全局信息来处理整个幻灯片。该框架将预训练的网络划分为多个模块，并使用辅助模型在本地优化每个模块。我们还引入了随机特征重建单元（RFR）来在训练期间保留显着特征并提高我们方法的性能。对三个公开可用的 WSI 数据集：TCGA-NSCLC、TCGA-RCC 和 LKS 进行的广泛实验凸显了我们的方法在不同分类任务上的优越性。我们的方法在准确性方面优于最先进的 MIL 方法，同时速度提高了 7 到 10 倍。此外，当将其划分为 8 个模块时，我们的方法只需要端到端训练所需总 GPU 内存的 20%。我们的代码可在 https://github.com/cvlab-stonybrook/local_learning_wsi 获取。
Histopathology whole slide images (WSIs) play a very important role in clinical studies and serve as the gold standard for many cancer diagnoses. However, generating automatic tools for processing WSIs is challenging due to their enormous sizes. Currently, to deal with this issue, conventional methods rely on a multiple instance learning (MIL) strategy to process a WSI at patch level. Although effective, such methods are computationally expensive, because tiling a WSI into patches takes time and does not explore the spatial relations between these tiles. To tackle these limitations, we propose a locally supervised learning framework which processes the entire slide by exploring the entire local and global information that it contains. This framework divides a pre-trained network into several modules and optimizes each module locally using an auxiliary model. We also introduce a random feature reconstruction unit (RFR) to preserve distinguishing features during training and improve the performance of our method byto. Extensive experiments on three publicly available WSI datasets: TCGA-NSCLC, TCGA-RCC and LKS, highlight the superiority of our method on different classification tasks. Our method outperforms the state-of-the-art MIL methods bytoin accuracy, while being 7 to 10 times faster. Additionally, when dividing it into eight modules, our method requires as little as 20% of the total gpu memory required by end-to-end training. Our code is available at https://github.com/cvlab-stonybrook/local_learning_wsi.