首页 > 论文 > 光学学报 > 38卷 > 8期(pp:815023--1)

基于形状特征的肺裂检测算法

Pulmonary Fissure Detection Based on Shape Features

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

了解肺裂解剖结构特征在定位和评估肺部疾病方面具有非常重要的作用。在计算机断层扫描图像中肺裂经常会受到形变、体素效应和噪声等影响,使得肺裂检测难度很大。为了解决此问题,提出一种基于形状特征的肺裂检测算法。首先融合肺裂幅度信息和方向信息在增强肺裂的同时高效率的抑制噪声;然后利用区域属性分析算法去除气管、血管等噪声来识别肺裂;最后采用表面曲率算法去除黏连噪声,达到分割肺裂的目的。该算法在公开数据集LOLA11上进行了验证。与人工参考对比,本文算法分割的肺裂的F1-score中值为0.8451。实验结果表明,本文算法能够高效率的分割肺裂。

Abstract

Knowledge of pulmonary fissure anatomy plays an important role in localization of lesions and evaluation of lung disease. In computed tomography images, pulmonary fissure detection is an intricate task due to factors such as pathological deformation, partial volume effect and noise. To solve the problem, a novel method based on shape features is proposed for pulmonary fissure detection. Firstly, the orientation information and magnitude information of pulmonary fissures are fused to enhance pulmonary fissures and suppress interferences. Then region property analysis algorithm is used to remove interferences like airways and vessels for pulmonary fissure identification. Finally, surface curvature approach is utilized to remove adhering interferences for pulmonary fissure segmentation. The performance of the proposed method is validated in experiments with a publicly available LOLA11 dataset. Compared with manual references, the proposed method acquired a high median F1-score of 0.8451. Experimental results show that the proposed method has a good performance in pulmonary fissure segmentation.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.41

DOI:10.3788/aos201838.0815023

所属栏目:“机器视觉检测与应用”专题

基金项目:国家自然科学基金(61172160,61571184,U1613209)、长沙市科技计划项目(kq1706016)、湖南省重点研发计划项目(2016GK2056)

收稿日期:2018-03-19

修改稿日期:2018-05-17

网络出版日期:2018-05-29

作者单位    点击查看

彭圆圆:湖南大学电气与信息工程学院, 湖南 长沙 410000
肖昌炎:湖南大学电气与信息工程学院, 湖南 长沙 410000

联系人作者:彭圆圆(pengmi467347713@126.com)

【1】van Rikxoort E M, van Ginneken B. Automated segmentation of pulmonary structures in thoracic computed tomography scans: a review[J]. Physics in Medicine and Biology, 2013, 58(17): 187-220.

【2】Doel T, Gavaghan D J, Grau V. Review of automatic pulmonary lobe segmentation methods from CT[J]. Computerized Medical Imaging and Graphics, 2015, 40: 13-29.

【3】Li S, Zhou K, Wang M, et al. Degree of pulmonary fissure completeness can predict postoperative cardiopulmonary complications and length of hospital stay in patients undergoing video-assisted thoracoscopic lobectomy for early-stage lung cancer[J]. Interactive Cardiovascular and Thoracic Surgery, 2018, 26(1): 25-33.

【4】Zhang L, Hoffman E A, Reinhardt J M. Atlas-driven lung lobe segmentation in volumetric X-ray CT images[J]. IEEE Transactions on Medical Imaging, 2006, 25(1): 1-16.

【5】Wang J, Betke M, Ko J P. Pulmonary fissure segmentation on CT[J]. Medical Image Analysis, 2006, 10(4): 530-547.

【6】Wei Q, Hu Y, Gelfand G, et al. Segmentation of lung lobes in high-resolution isotropic CT images[J]. IEEE Transactions on Biomedical Engineering, 2009, 56(5): 1383-1393.

【7】Klinder T, Wendland H, Wiemker R. Lobar fissure detection using line enhancing filters[C]. SPIE, 2013, 8669: 86693C.

【8】Wiemker R, Bülow T, Blaffert T. Unsupervised extraction of the pulmonary interlobar fissures from high resolution thoracic CT data[C]. International Congress Series, 2005, 1281: 1121-1126.

【9】Doel T, Matin T N, Gleeson F V, et al. Pulmonary lobe segmentation from CT images using Fissureness, airways, vessels and multilevel B-splines[C]. IEEE International Symposium on Biomedical Imaging, 2012: 1491-1494.

引用该论文

Peng Yuanyuan,Xiao Changyan. Pulmonary Fissure Detection Based on Shape Features[J]. Acta Optica Sinica, 2018, 38(8): 0815023

彭圆圆,肖昌炎. 基于形状特征的肺裂检测算法[J]. 光学学报, 2018, 38(8): 0815023

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF