Department of Computer Science and Engineering, Sejong University, 209 Neungdong-ro, Gwangjin-gu, Seoul 05006, Korea.
Department of Computer Science and Engineering, Sejong University, 209 Neungdong-ro, Gwangjin-gu, Seoul 05006, Korea.
Comput Methods Programs Biomed. 2019 May;173:119-129. doi: 10.1016/j.cmpb.2019.03.007. Epub 2019 Mar 14.
Segmenting different tissue components in histopathological images is of great importance for analyzing tissues and tumor environments. In recent years, an encoder-decoder family of convolutional neural networks has increasingly adopted to develop automated segmentation tools. While an encoder has been the main focus of most investigations, the role of a decoder so far has not been well studied and understood. Herein, we proposed an improved design of a decoder for the segmentation of epithelium and stroma components in histopathology images.
The proposed decoder is built upon a multi-path layout and dense shortcut connections between layers to maximize the learning and inference capability. Equipped with the proposed decoder, neural networks are built using three types of encoders (VGG, ResNet and preactived ResNet). To assess the proposed method, breast and prostate tissue datasets are utilized, including 108 and 52 hematoxylin and eosin (H&E) breast tissues images and 224 H&E prostate tissue images.
Combining the pre-activated ResNet encoder and the proposed decoder, we achieved a pixel wise accuracy (ACC) of 0.9122, a rand index (RAND) score of 0.8398, an area under receiver operating characteristic curve (AUC) of 0.9716, Dice coefficient for stroma (DICE_STR) of 0.9092 and Dice coefficient for epithelium (DICE_EPI) of 0.9150 on the breast tissue dataset. The same network obtained 0.9074 ACC, 0.8320 Rand index, 0.9719 AUC, 0.9021 DICE_EPI and 0.9121 DICE_STR on the prostate dataset.
In general, the experimental results confirmed that the proposed network is superior to the networks combined with the conventional decoder. Therefore, the proposed decoder could aid in improving tissue analysis in histopathology images.
对组织学图像中的不同组织成分进行分割，对于分析组织和肿瘤环境非常重要。近年来，一种基于编码器-解码器的卷积神经网络家族被越来越多地用于开发自动化分割工具。尽管编码器一直是大多数研究的重点，但解码器的作用迄今为止尚未得到很好的研究和理解。在这里，我们提出了一种用于组织学图像上皮和基质成分分割的改进解码器设计。
所提出的解码器基于多路径布局和层之间的密集捷径连接构建，以最大限度地提高学习和推理能力。配备所提出的解码器，使用三种类型的编码器（VGG、ResNet 和预激活 ResNet）构建神经网络。为了评估所提出的方法，利用了乳腺和前列腺组织数据集，包括 108 张和 52 张苏木精和伊红（H&E）乳腺组织图像以及 224 张 H&E 前列腺组织图像。
将预激活 ResNet 编码器和所提出的解码器相结合，我们在乳腺组织数据集上实现了像素级准确率（ACC）为 0.9122、兰德指数（RAND）得分 0.8398、接收器操作特征曲线下面积（AUC）为 0.9716、基质 Dice 系数（DICE_STR）为 0.9092 和上皮 Dice 系数（DICE_EPI）为 0.9150。同一网络在前列腺数据集上获得了 0.9074 ACC、0.8320 Rand 指数、0.9719 AUC、0.9021 DICE_EPI 和 0.9121 DICE_STR。
总体而言，实验结果证实，所提出的网络优于与传统解码器结合的网络。因此，所提出的解码器可以帮助改进组织学图像中的组织分析。
