| 摘要: |
| 计算机断层成像(computed tomography, CT)中, 胰腺分割作为医学图像分析中最具挑战的任务之一, 由于其体积小、形状多变的特点, 导致传统的自动分割方法无法达到理想的分割精度. 利用高级语义特征指导低级特征的思想, 提出一种基于双解码U型卷积神经网络的单阶段胰腺分割模型. 模型由一个编码器和两个解码器构成, 两个解码器利用不同编码深度的特征将低级空间信息与高级语义信息有效结合, 加强分割网络对特征信息的高效利用, 能够对未裁剪、未降低分辨率的CT切片实现高精确度的分割. 实验结果表明, 方法能够在全尺寸的输入下实现较好的分割性能, 在公开胰腺数据集上的分割效果优于现有单阶段胰腺分割方法. |
| 关键词: 医学图像 胰腺分割 卷积神经网络 单阶段分割模型 双解码U-Net |
| DOI：10.13328/j.cnki.jos.006198 |
| 分类号:TP391 |
| 基金项目:国家自然科学基金(61806032, 61976031); 国家重点研发计划(2016YFC1000307-3); 重庆市基础与前沿项目(cstc2018jcyjAX0117); 重庆市教委科学技术研究计划(KJZD-K201800601, KJQN201800611) |
|
| Pancreas Segmentation Based on Dual-decoding U-Net |
|
BI Xiu-Li, LU Meng, XIAO Bin, LI Wei-Sheng
|
|
Chongqing Key Laboratory of Image Cognition, Chongqing 400065, China
|
| Abstract: |
| Pancreas segmentation in computed tomography (CT) is one of the most challenging tasks in medical image analysis. Due to small size and changeable shape, the traditional automatic segmentation methods can not achieve the acceptable segmentation accuracy. By using the idea of high-level semantic features to guide low-level features, this study proposes a single-stage pancreas segmentation model based on dual-decoding U-net. The proposed architecture consists of one encoder and two decoders, which can effectively combine low-level spatial information with high-level semantic information using the features of different coding depths to improve the segmentation accuracy of CT slices without clipping and resolution reduction. The experimental results show that this method can achieve better segmentation performance under full-size input. Moreover, the segmentation result by the proposed method is superior to the single-stage methods on the open dataset for pancreas segementation tasks. |
| Key words: medical image pancreas segmentation convolutional neural networks (CNN) single-stage model dual-decoding U-Net (DDU-Net) |
