基于稠密金字塔特征网络的肝CT图像自动分割方法探讨

徐洪丽; 薛万国; 陈永亮; 冷建军; 钟诚; 张耀; 刘坤; 王鹏飞; 冯健; 刘添; 刘兵; 段振飞; 邱明辉

doi:10.3969/j.issn.2095-5227.2019.08.006

基于稠密金字塔特征网络的肝CT图像自动分割方法探讨

Automatic segmentation of liver CT images based on dense pyramid feature network

摘要

摘要:
目的探讨稠密金字塔特征网络在多期腹部增强CT图像上对肝全自动分割的方法与性能。
方法收集解放军总医院第一医学中心2015-2018年住院患者腹部增强CT的原始医学数字成像和通信(DICOM)图像20例，其中男性15例，女性5例，年龄均＞30岁。使用Python软件及TensorFlow开源平台进行资料分析，构建稠密金字塔特征网络进行肝自动分割，并与U型网络(U-Net)模型在性能上进行比较。
结果本文提出的肝分割方法的DICE系数在动脉期、静脉期、延迟期分别为95.97%、96.22%、96.16%，高于U-Net网络的95.59%、95.85%、95.56%。
结论稠密金字塔特征网络在不同期均明显优于U-Net分割网络。

Abstract:
Objective To discuss the performance of fully automatic liver segmentation in multi-phase abdominal enhanced CT images by dense pyramidal feature network.
Methods We collected the DICOM images of abdominal enhanced CT of 20 patients admitted to the first medical center of Chinese PLA General Hospital from 2015 to 2018. There were 15 males and 5 females aged over 30 years. The data were analyzed by Python and Tensorflow framework via constructing a dense pyramid feature network for automatic liver segmentation, and its performance was compared with the widely adopted U-Net structure.
Results In the experiment, the DICE coefficient of liver segmentation in the arterial phase, venous phase, and delay phase by dense pyramid feature network was 95.97%, 96.22%, and 96.16%, respectively, higher than 95.59%, 95.85%, and 95.56% by U-Net structure.
Conclusion The results show that dense pyramid feature network is superior to U-Net segmentation network for multi-phase liver segmentation in different phases.

HTML全文

参考文献(24)

施引文献

资源附件(0)