A multi-scale recurrent fully convolution neural network for laryngeal leukoplakia segmentation
A multi-scale recurrent fully convolution neural network for laryngeal leukoplakia segmentation
复制标题
喉白斑分割的多尺度循环全卷积神经网络
DOI：
10.1016/j.bspc.2020.101913
复制
发表时间：
2020-05-01
影响因子：
5.1
通讯作者：
Liu, Kai
中科院分区：
文献类型：
--
作者：
Ji, Bin;Ren, Jianjun;Liu, Kai
喉白斑是喉癌前病变的一种。喉镜图像中白斑的准确检测和分割对喉部疾病的诊断和治疗具有重要意义。本文提出了一种多尺度循环全卷积神经网络——bold - m - net (BM-Net)，用于喉白斑病变的识别和分割。该网络由多尺度输入层、双u型卷积网络和侧输出层组成。首先，我们对图像进行扩充以产生6个通道，然后为多尺度输入层构建图像金字塔。对于u型卷积网络，我们使用多尺度卷积构建了一个新的u型网络，并使用循环卷积层（RCL）代替原有的卷积层。然后我们使用跳跃连接连接双u形卷积网络，其中一个有三个2 x 2 max池化层，另一个有四个，从而形成了BM-Net的主要结构。我们将三层U-Net的输出添加到侧输出层，为每个尺度层生成伴随的局部预测图。图像金字塔和多尺度卷积可以产生多个水平接受域，而RCL允许随着参数t的增加而对上下文有更大的感知。最后，我们将所提出的BM-Net与流行的网络（包括FCN-8s、Seg-Net、U-Net、M-Net和其他三种用于分割喉镜图像中喉白斑的改进网络）的性能进行了比较。实验结果表明，BM-Net继承了U-Net、M-Net和RCL的优点，在喉白斑分割方面总体表现优于其他网络。(C) 2020由Elsevier Ltd.出版。
Laryngeal leukoplakia is one kind of precancerous lesions in the larynx. Precise detection and segmentation of leukoplakia in laryngoscopic images is important for laryngeal disease diagnosis and treatment. In this paper, we proposed a multi-scale recurrent fully convolution neural network named boldface-M-Net (BM-Net) to identify and segment laryngeal leukoplakia lesions. The proposed BM-Net was composed of a multi-scale input layer, a double U-shaped convolution network, and a side-output layer. First, we augmented the image to produce six channels and then constructed image pyramids for the multi-scale input layer. For the U-shaped convolution network, we constructed a new U-Net using multi-scale convolution and a recurrent convolution layer (RCL) instead of the original convolution layer. We then employed skip connections to connect the double U-shaped convolution network, one with three 2 x 2 max pooling layers and the other with four, thus forming the main structure of BM-Net. We added the output for the three-layered U-Net to the side-output layer to produce a companion local prediction map for each scale layer. Image pyramids and multi-scale convolution can generate multiple level-receptive fields, while the RCL allows for the greater perception of context with parameter t increases. Finally, we compared the performance of the proposed BM-Net with the popular networks, including FCN-8s, Seg-Net, U-Net, M-Net, and three other modified networks for segmenting laryngeal leukoplakia in laryngoscopic images. According to the experimental results, BM-Net, which inherited the advantages of U-Net, M-Net, and RCL, exhibited overall better performance in laryngeal leukoplakia segmentation than the other networks. (C) 2020 Published by Elsevier Ltd.