| 引用本文: | 陈 亮1,2,高文根1,2,张 晨1,2,陈 东1,2.新型架构下的密集网络在肺部影像的分割研究(J/M/D/N,J:杂志，M：书，D：论文，N：报纸).期刊名称,2023，40（6）：53-60 |
| CHEN X. Adap tive slidingmode contr ol for discrete2ti me multi2inputmulti2 out put systems[ J ]. Aut omatica, 2006, 42(6): 4272-435 |
|
| 摘要: |
| 在医学图像分割领域中,肺实质的分割对肺结节检测有着至关重要的作用,在考虑到模型参数量的情况下
追求更高的精度一直是研究热点之一;为此提出了新的三层密集卷积神经网络 DA-UNet,首先用密集卷积模块代
替在传统 U-Net 使用的普通 3×3 卷积,利用密集卷积特征重用特点,加强了网络的特征提取能力。 再者在没有太
过影响分割网络精确度的前提下加以修剪,减少了上下采样次数,减少不必要的算力消耗。 此外,使用了注意力门
(Attention gate),加强了跳跃连接中高底层信息融合效果,并且使用空洞空间金字塔池化( Atrous spatial pyramid
pooling),模型加入了不同尺度的特征信息,进一步加强图像中任务相关的区域特征,有效减小噪声干扰,提高网络
分割精度。 通过实验证明:三次上下采样改进模型的参数量只有传统四次上下采样的 75. 2%左右,但是分割效果
没有太大的影响,用 LUNA 竞赛肺部影像数据集进行了分割验证,实验结果在测试集上的准确率达到了 0. 991,而
IoU 则为 0. 961,比起传统 U-Net 的评价指标 IoU 提升了 2. 9%;在泛化实验的肝脏图像中,DA-UNet 的 IoU 稳定在
0. 929 左右,而 U-Net 稳定在 0. 838 左右。 这些结果证明了改进的 U-Net 有更佳的分割效果。 |
| 关键词: U-Net 密集网络 肺实质分割 空洞空间金字塔池化 注意力门 DA-UNet 评价指标 |
| DOI： |
| 分类号: |
| 基金项目: |
|
|
|
CHEN Liang1 2 GAO Wengen1 2 ZHANG Chen1 2 CHEN Dong1 2
|
|
1. School of Electrical Engineering Anhui Polytechnic University Anhui Wuhu 241000 China
2. Key Laboratory of Advanced Sensing and Intelligent Control for High-end Equipment Ministry of Education Anhui
Polytechnic University Anhui Wuhu 241000 China
|
| Abstract: |
| In the field of medical image segmentation the segmentation of lung parenchyma plays a crucial role in lung
nodule detection. Pursuing higher accuracy while considering the number of model parameters has been one of the
research hotspots. In this regard a new three-layer dense convolutional neural network DA-UNet was proposed.
Firstly a dense convolution module was used instead of the normal 3 × 3 convolution used in traditional U-Net which
enhances the feature extraction capability of the network by taking advantage of the reuse feature of dense convolution.
Furthermore the network was pruned without affecting the accuracy of the segmentation network too much reducing the
number of up and down samples and reducing unnecessary computational power consumption. In addition the Attention
Gate was used to enhance the effect of information fusion between high and low levels in the jumping connection and
atrous spatial pyramid pooling was used. The model incorporated feature information at different scales to further enhance
task-related regional features in the images effectively reducing noise interference and improving network segmentation accuracy. It was demonstrated experimentally that the number of parameters of the three-time up-and-down sampling
improved model was only about 75. 2% of those of the traditional four-time up-and-down sampling but the segmentation
effect was not much affected. The LUNA competition lung image data set was used for segmentation verification. The
experimental results showed that the accuracy reached 0. 991 and the IoU was 0. 961. Compared with the traditional UNet the evaluation index IoU was improved by 2. 9%. In the liver images of the generalization experiment the IoU of
DA-UNet was stable at about 0. 929 while that of U-Net was stable at about 0. 838. These results prove that the improved
U-Net has better segmentation results. |
| Key words: U-Net dense network lung parenchyma segmentation atrous spatial pyramid pooling attention gate DAUNet evaluation index |
