RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification
RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification
复制标题
DOI：
10.1016/j.media.2019.101549
复制
发表时间：
2019-12-01
影响因子：
10.9
通讯作者：
Heng, Pheng-Ann
中科院分区：
文献类型：
--
作者：
Wang, Shujun;Zhu, Yaxi;Heng, Pheng-Ann
全切片组织病理学图像（WSIs）在胃癌诊断中具有重要作用。然而，由于wsi的规模大，异常区域的大小不一，在自动诊断过程中，如何选择信息区域并对其进行分析是一个很大的挑战。基于最具判别性实例的多实例学习对整个胃切片图像的诊断有很大的帮助。在本文中，我们设计了一个重新校准的多实例深度学习方法（RMDL）来解决这个具有挑战性的问题。我们首先选择有区别的实例，然后利用这些实例基于所提出的RMDL方法进行疾病诊断。所设计的RMDL网络能够捕获实例依赖关系，并根据从融合特征中学习到的重要系数重新校准实例特征。此外，我们建立了一个具有详细像素级注释的大型整张胃组织病理学图像数据集。在构建的胃数据集上的实验结果表明，与其他最先进的多实例学习方法相比，我们提出的框架的准确性有了显着提高。此外，我们的方法具有通用性，可以扩展到基于wsi的其他不同癌症类型的诊断任务。(C) 2019 Elsevier B.V.版权所有
The whole slide histopathology images (WSIs) play a critical role in gastric cancer diagnosis. However, due to the large scale of WSIs and various sizes of the abnormal area, how to select informative regions and analyze them are quite challenging during the automatic diagnosis process. The multi-instance learning based on the most discriminative instances can be of great benefit for whole slide gastric image diagnosis. In this paper, we design a recalibrated multi-instance deep learning method (RMDL) to address this challenging problem. We first select the discriminative instances, and then utilize these instances to diagnose diseases based on the proposed RMDL approach. The designed RMDL network is capable of capturing instance-wise dependencies and recalibrating instance features according to the importance coefficient learned from the fused features. Furthermore, we build a large whole-slide gastric histopathology image dataset with detailed pixel-level annotations. Experimental results on the constructed gastric dataset demonstrate the significant improvement on the accuracy of our proposed framework compared with other state-of-the-art multi-instance learning methods. Moreover, our method is general and can be extended to other diagnosis tasks of different cancer types based on WSIs. (C) 2019 Elsevier B.V. All rights reserved.