Study on the improved VNet network based pulmonary nodule segmentation method

被引：0
|
作者：
Zhong S. [1 ,2 ]
Wang M. [1 ]
Guo X. [1 ]
Zhang Y. [1 ]
Zheng Y. [3 ]
机构：
[1] Chongqing Engineering Research Center for Medical Electronics Technology, College of Biological Engineering, Chongqing University, Chongqing
[2] Corporation Research Center, Shanghai United Imaging Healthcare Co., Ltd., Shanghai
[3] Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing
来源：
Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument | 2020年 / 41卷 / 09期
关键词：
Deep learning; Deep supervision; Multi-scale feature; Pulmonary nodule segmentation;
D O I：
10.19650/j.cnki.cjsi.J2006567
中图分类号：
学科分类号：
摘要：
At present, the incidence and mortality of lung cancer are the highest among cancers. Early diagnosis and treatment of lung cancer are extremely important to improve the survival rate and prognosis of patients. Pulmonary nodules are the early manifestation of lung cancer, which are clinically diagnosed as benign or malignant by observing the characteristics such as volume and morphology after segmentation. However, manual segmentation of pulmonary nodules is very inefficient. In this study, a segmentation method of pulmonary nodules based on MSVNet network is proposed, which inherits the structure of the original VNet, meanwhile a multi-scale feature structure is introduced. Through extracting the multi-scale feature of pulmonary nodule image and optimizing the feature with deep supervision strategy, the segmentation performance of the model can be effectively improved. In this study, the performance of the model is evaluated using the LIDC-IDRI pulmonary nodule public data set. The results show that the segmentation results obtained with the proposed method are similar to the gold standard. The proposed method has good pulmonary nodule segmentation performance and high segmentation robustness, and can achieve good segmentation results for the pulmonary nodules with different sizes. © 2020, Science Press. All right reserved.
引用
收藏
页码：206 / 215
页数：9
相关论文
共 25 条
  • [1] BRAY F, FERLAY J, SOERJOMATARAM I, Et al., Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries, CA: A Cancer Journal for Clinicians, 68, 6, pp. 394-424, (2018)
  • [2] ZHOU Q H, FAN Y G, WANG Y, Et al., China national guideline of classification, diagnosis and treatment for lung nodules, Chin J Lung Cancer, 19, 12, pp. 793-798, (2016)
  • [3] ZHANG X J, BAI L, JIN F G, Et al., China experts consensus on the diagnosis and treatment of lung nodules (2018 Version), Chinese Journal of Tuberculosis and Respiratory Diseases, 41, 10, pp. 763-771, (2018)
  • [4] ARMATO S G, GIGER M L, MORAN C J, Et al., Computerized detection of pulmonary nodules on CT scans, Radiographics, 19, 5, pp. 1303-1311, (1999)
  • [5] WEI Y, XU X H, JIA T, Et al., Extraction of suspected nodular lung lesions based on multi-scale morphology filtering in thoracic CT images, Journal of Northeastern University, 29, 3, pp. 312-315, (2008)
  • [6] LIU H, ZHANG C M, DENG K, Et al., Research on fast FCM pulmonary nodule segmentation algorithm using improved self-adaption, Journal of Computer-Aided Design & Computer Graphics, 26, 10, pp. 1727-1736, (2014)
  • [7] CHEN Y H, LI ZH, FENG B, Et al., Pleural contact pulmonary nodule segmentation based on improved active contour model, Chinese Journal of Scientific Instrument, 40, 11, pp. 107-116, (2019)
  • [8] ARESTA G, JACOBS C, ARAUJO T, Et al., IW-Net: an automatic and minimalistic interactive lung nodule segmentation deep network, Scientific Reports, 9, 1, pp. 1-9, (2019)
  • [9] ROY R, CHAKRABORTI T, CHOWDHURY A S., A deep learning-shape driven level set synergism for pulmonary nodule segmentation, Pattern Recognition Letters, 123, pp. 31-38, (2019)
  • [10] ZHONG S H, GUO X M, ZHENG Y N., Improved U-Net network for lung nodule segmentation, Computer Engineering and Applications, 2020, 17, pp. 203-209
123