激光与光电子学进展, 2020, 57 (20): 201008, 网络出版: 2020-10-13
基于AttentionNet和DenseUnet的脊椎CT分割 下载: 1357次
Spinal CT Segmentation Based on AttentionNet and DenseUnet
图像处理 分割 Attention图 参数量 预训练 多通道融合 image processing segmentation Attention map number of parameters pre-training multi-channel fusion
摘要
在脊椎CT图像分割问题中,由于脊椎与组织对比度过低和噪声的影响,传统分割算法存在分割精度差和自动化程度低等问题。基于此,提出一种通过AttentionNet定位脊椎,然后使用改进的DenseUnet进行脊椎CT分割的方法。首先,对所有脊椎CT样本数据进行裁剪、重采样、灰度值归一化等预处理操作;再次,对样本使用AttentionNet训练得到具有位置信息的Attention图;然后,对传统DenseUnet进行改进,在每个Dense block加入Shuffle操作来增加网络的鲁棒性,在每个Dense block后加入1×1卷积,以降低通道数,减少网络参数量;接着使用改进后的DenseUnet对训练样本进行预训练,得到具有先验信息的预测图;最后,将Attention图、预测图及原始图像融合为三通道的训练样本作为输入,采用改进的DenseUnet训练分割模型,并在测试集上进行验证,最终实现脊椎CT自动分割。实验结果表明,所提方法的分割精度优于传统DenseUnet,是一种有效的脊椎CT自动分割方法。
Abstract
In the spinal computed tomography (CT) image segmentation problem, owing to the low contrast between the spine and tissues, and the influence of noise, the traditional segmentation algorithms have problems such as poor segmentation accuracy and low degree of automation. Aiming at solving the above-mentioned problems, a method of locating the spine through AttentionNet and then using improved DenseUnet to perform spinal CT segmentation is proposed herein. First, preprocessing operations such as cropping, resampling, and normalization of gray values are performed on all spinal CT sample data; the samples are trained using AttentionNet to obtain Attention maps with position information. Second, the traditional DenseUnet is improved, and each Dense block adds the Shuffle operation to increase the network robustness. After each Dense block, a 1×1 convolution is added to reduce the number of channels and network parameters. Third, the training samples are pretrained using the improved DenseUnet to obtain the prediction maps with prior information. Finally, the Attention map, prediction map, and the original images are fused into three-channel training samples as the input, and the improved DenseUnet is used to train segmentation model and is verified against the test set. Consequently, the spinal CT automatic segmentation is realized. The experimental results show that the segmentation accuracy of the proposed method is better than that of the traditional DenseUnet, and the proposed method is an effective automatic segmentation method for spinal CT.
田丰源, 周明全, 闫峰, 范力, 耿国华. 基于AttentionNet和DenseUnet的脊椎CT分割[J]. 激光与光电子学进展, 2020, 57(20): 201008. Fengyuan Tian, Mingquan Zhou, Feng Yan, Li Fan, Guohua Geng. Spinal CT Segmentation Based on AttentionNet and DenseUnet[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201008.