浏览全部资源
扫码关注微信
收稿：2021-08-20，
修回：2021-12-16，
录用：2021-12-23，
纸质出版：2022-03-16
移动端阅览
目的
2
肺内血管形态结构的改变是慢性阻塞性肺疾病（慢阻肺）的一种重要病理改变。针对慢阻肺中肺血管疾病的定量评估问题，提出一种基于各向异性连续最大流的肺内血管自动分割方法，并定量分析不同半径的肺内血管体积分布，以研究慢阻肺病程中肺血管重塑规律。
方法
2
使用U-Net分割肺体，获取肺脏区域，减少后续血管增强与分割的运算量；借助基于多尺度Hessian矩阵的血管增强方法，获得血管的似然增强结果和轴向方向；将血管似然结果和轴向信息以数据保真项和各向异性正则项的形式融入到连续最大流分割框架，实现肺血管的自动分割。
结果
2
在公开数据集ArteryVein和仿真数据集VascuSynth上对肺内血管分割方法的有效性进行测试；在从4家医院收集的614例临床影像数据上分析小半径血管体积占比情况，对比慢阻肺组与非慢阻肺组之间肺血管重塑差异。肺血管分割方面，对于增加不同程度的高斯噪声（
σ
=5，10，15，20，25，30，35）的VascuSynth仿真数据，本文方法获得的Dice值分别为0.87，0.80，0.77，0.75，0.73，0.71，0.69；对于低剂量数据集ArteryVein，Dice值为0.79。肺血管定量分析方面，非慢阻肺组和慢阻肺组的小血管体积平均占比值为0.656±0.067，0.589±0.074。不同慢阻肺分级GOLD1—4组小血管占比为0.612±0.051、0.600±0.078、0.565±0.067、0.528±0.053。
结论
2
本文提出的肺内血管算法可以用于肺血管重塑研究，通过实验分析验证了非慢阻肺组与慢阻肺组小血管体积占比存在显著差异；基于慢阻肺分级指数（global initiative for chronic obstructive pulmonary disease，GOLD）的不同慢阻肺病人之间，小血管体积占比在轻症和重症之间也存在显著差异。
Objective
2
Chronic obstructive pulmonary disease (COPD) is a worldwide prevalent pulmonary disease. In China
COPD is the third leading cause of death. Pulmonary function tests (PFTs) are widely used to assess COPD severity
but they cannot evaluate the contribution of each disease compartment. Pulmonary vascular remodeling is a remarkable characteristic of COPD. In the past
pulmonary vascular remodeling was regarded as an end-stage feature of COPD. However
more recent studies have found that vascular disease is present in patients with early COPD stage. Pulmonary vascular remodeling has been described as dilation of proximal vessels and pruning or narrowing of distal vessels
thereby increasing vascular resistance. The available tools for the assessment of pulmonary vascular disease remain limited. Computed tomography (CT) is the most widely used imaging modality in COPD patients; it may be utilized to assess the severity of pulmonary vascular diseases. This study aims to develop and validate an automatic method for extracting pulmonary vessels and quantifying pulmonary vascular morphology in CT images.
Method
2
The extraction of pulmonary vessels is important for automated quantitative analysis of pulmonary vascular morphology. We present an anisotropic variational approach
which incorporates appearance and orientation of pulmonary vessels as prior knowledge for extracting pulmonary vessels. The pipeline of segmentation procedure includes three stages as follows. First
because the lung segmentation can reduce the running time of subsequent stages
we apply a U-Net model
which is a convolution neural network (CNN) trained with high diversity clinical CT images to obtain the left and right lungs. Second
the response of conventional Hessian-based vesselness filters is low at the vessels' edges and bifurcations. To overcome this problem
motivated by the measurement of anisotropy of diffusion tensor
a multiscale Hessian-based vesselness filter is used to highlight pulmonary vessels and generate the axial orientation of tubular structures. This vesselness filter may mitigate the low response of branch points and maintain robust contrast of various images. Third
considering the long and thin characteristic of pulmonary vessels
we incorporate an anisotropic variational regularizer into a continuous maximal flow framework to improve the segmentation performance. This anisotropic regularizer was constructed from the orientation of pulmonary vessels in the form of matrix generated by Eigen vectors of Hessian matrix. The proposed segmentation framework was implemented with parallel computing library. For quantifying the extracted pulmonary vessels
a public clinical data set from the ArteryVein challenge and a simulated data set from the VascuSynth were used to evaluate the performance of pulmonary vessel segmentation. To verify the association between the small vessel volume and COPD
614 patients with COPD and other pulmonary diseases were investigated with the proposed approach.
Result
2
For evaluating the pulmonary vessel segmentation method
we tested our segmentation method on simulated vessels with seven levels of Gaussian noise (
σ
=5
10
15
20
25
30
35) and 10 CT scans from a public clinical data set. The average dice coefficient for the simulated data set is 0.87 (
σ
=5)
0.80 (
σ
=10)
0.77 (
σ
=15)
0.75 (
σ
=20)
0.73 (
σ
=25)
0.71 (
σ
=30)
and 0.69 (
σ
=35). The average dice coefficient for the clinical data set is 0.79. For investigating the pulmonary vessel remodeling in COPD patients
614 CT scans from 352 patients with COPD and 262 patients with other diseases were used for quantitative analysis
where 281 cases in the COPD group contain GOLD classification information (GOLD 1:16 cases
GOLD 2:108 cases
GOLD 3:108 cases
and GOLD 4:49 cases). The average proportion of small pulmonary vessels (cross section areas
<
10 mm
2
) in the non-COPD and the COPD group was 0.656±0.067 and 0.589±0.074
respectively. The proportions of small vessels in the GOLD1-4 group were 0.612±0.051
0.600±0.078
0.565±0.067
and 0.528±0.053.
Conclusion
2
We proposed a pulmonary vessel segmentation method that incorporates the vessels' directions. It can be used in the study of pulmonary vascular remodeling. Experimental results have verified the difference in the proportion of small pulmonary vessel volume between the non-COPD and the COPD group
and the differences also exist in GOLD 1-4 groups.
Bülow T, Wiemker R, Blaffert T, Lorenz C and Renisch S. 2005. Automatic extraction of the pulmonary artery tree from multi-slice CT data//Proceedings Volume 5746, Medical Imaging 2005: Physiology, Function, and Structure from Medical Images. San Diego, USA: SPIE: 730-740[ DOI: 10.1117/12.595286 http://dx.doi.org/10.1117/12.595286 ]
Bian Z J, Qin W J, Liu JR and Zhao D Z. 2018. Review of anatomic segmentation methods in thoracic CT images. Journal of Image and Graphics, 23(10): 1450-1471
边子健, 覃文军, 刘积仁, 赵大哲. 2018. 肺部CT图像中的解剖结构分割方法综述. 中国图象图形学报, 23(10): 1450-1471[DOI:10.11834/jig.180067]
Charbonnier J P, Brink M, Ciompi F, Scholten E T, Schaefer-Prokop C M and van Rikxoort E M. 2016. Automatic pulmonary artery-vein separation and classification in computed tomography using tree partitioning and peripheral vessel matching. IEEE Transactions on Medical Imaging, 35(3): 882-892[DOI:10.1109/TMI.2015.2500279]
Estépar R S J, Kinney G L, Black-Shinn J L, Bowler R P, Kindlmann G L, Ross J C, Kikinis R, Han M K, Come C E, Diaz A A, Cho M H, Hersh C P, Schroeder J D, Reilly J J, Lynch D A, Crapo J D, Wells J M, Dransfield M T, Hokanson J E, Washko G R and COPDGene Study. 2013. Computed tomographic measures of pulmonary vascular morphology in smokers and their clinical implications. American Journal of Respiratory and Critical Care Medicine, 188(2): 231-239[DOI:10.1164/rccm.201301-0162OC]
Frangi A F, Niessen W J, Hoogeveen R M, van Walsum T and Viergever M A. 1999. Model-based quantitation of 3-D magnetic resonance angiographic images. IEEE Transactions on Medical Imaging, 18(10): 946-956[DOI:10.1109/42.811279]
Haft-Javaherian M, Villiger M, Schaffer C B, Nishimura N, Golland P and Bouma B E. 2020. A topological encoding convolutional neural network for segmentation of 3D multiphoton images of brain vasculature using persistent homology//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle, USA: IEEE: 4262-4271[ DOI: 10.1109/CVPRW50498.2020.00503 http://dx.doi.org/10.1109/CVPRW50498.2020.00503 ]
Hamarneh G and Jassi P. 2010. VascuSynth: simulating vascular trees for generating volumetric image data with ground-truth segmentation and tree analysis. Computerized Medical Imaging and Graphics, 34(8): 605-616[DOI:10.1016/j.compmedimag.2010.06.002]
Hofmanninger J, Prayer F, Pan J, Röhrich S, Prosch H and Langs G. 2020. Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem. European Radiology Experimental, 4(1): #50[DOI:10.1186/s41747-020-00173-2]
Jerman T, Pernuš F, Likar B and Špiclin Ž. 2016. Enhancement of vascular structures in 3D and 2D angiographic images. IEEE Transactions on Medical Imaging, 35(9): 2107-2118[DOI:10.1109/TMI.2016.2550102]
Jiang Y F, Ye J D, Ding X Y, Chen Q H and Ye Y G. 2010. Image noise and artifact in chest low-dose CT. Chinese Journal of Radiology, 44(1): 37-40
江一峰, 叶剑定, 丁晓毅, 陈群慧, 叶贻刚. 2010. 胸部低剂量CT图像噪声和伪影分析. 中华放射学杂志, 44(1): 37-40[DOI:10.3760/cma.j.issn.1005-1201.2010.01.010]
Kiros R, Popuri K, Cobzas D and Jagersand M. 2014. Stacked multiscale feature learning for domain independent medical image segmentation//Proceedings of the 5th International Workshop on Machine Learning in Medical Imaging. Boston, USA: Springer: 25-32[ DOI: 10.1007/978-3-319-10581-9_4 http://dx.doi.org/10.1007/978-3-319-10581-9_4 ]
Law M W K and Chung A C S. 2008. Three dimensional curvilinear structure detection using optimally oriented flux//Proceedings of the 10th European Conference on Computer Vision. Marseille, France: Springer: 368-382[ DOI: 10.1007/978-3-540-88693-8_27 http://dx.doi.org/10.1007/978-3-540-88693-8_27 ]
Lindeberg T. 1998. Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2): 79-116[DOI:10.1023/A:1008045108935]
Lo P, Sporring J, Ashraf H, Pedersen J J H and De Bruijne M. 2010. Vessel-guided airway tree segmentation: a voxel classification approach. Medical Image Analysis, 14(4): 527-538[DOI:10.1016/j.media.2010.03.004]
Maher G, Parker D, Wilson N and Marsden A. 2020. Neural network vessel lumen regression for automated lumen cross-section segmentation in cardiovascular image-based modeling. Cardiovascular Engineering and Technology, 11(6): 621-635[DOI:10.1007/s13239-020-00497-5]
Manniesing R and Niessen W. 2005. Multiscale vessel enhancing diffusion in CT angiography noise filtering//Proceedings of the 19th International Conference on Information Processing in Medical Imaging. Glenwood Springs, USA: Springer: 138-149[ DOI: 10.1007/11505730_12 http://dx.doi.org/10.1007/11505730_12 ]
Matsuoka S, Washko G R, Dransfield M T, Yamashiro T, Estepar R S J, Diaz A, Silverman E K, Patz S and Hatabu H. 2010. Quantitative CT measurement of cross-sectional area of small pulmonary vessel in COPD: correlations with emphysema and airflow limitation. Academic Radiology, 17(1): 93-99[DOI:10.1016/j.acra.2009.07.022]
Moccia S, De Momi E, El Hadji S and Mattos L S. 2018. Blood vessel segmentation algorithms-review of methods, datasets and evaluation metrics. Computer Methods and Programs in Biomedicine, 158: 71-91[DOI:10.1016/j.cmpb.2018.02.001]
Nadeem S A, Hoffman E A, Sieren J C, Comellas A P, Bhatt S P, Barjaktarevic I Z, Abtin F and Saha P K. 2021. A CT-based automated algorithm for airway segmentation using freeze-and-grow propagation and deep learning. IEEE Transactions on Medical Imaging, 40(1): 405-418[DOI:10.1109/TMI.2020.3029013]
Nardelli P, Jimenez-Carretero D, Bermejo-Pelaez D, Washko G R, Rahaghi F N, Ledesma-Carbayo M J and Estépar R S J. 2018. Pulmonary artery-vein classification in CT images using deep learning. IEEE Transactions on Medical Imaging, 37(11): 2428-2440[DOI:10.1109/TMI.2018.2833385]
Ochs R A, Goldin J G, Abtin F, Kim H J, Brown K, Batra P, Roback D, Mcnittgray M F and Brown M S. 2007. Automated classification of lung bronchovascular anatomy in CT using AdaBoost. Medical Image Analysis, 11(3): 315-324[DOI:10.1016/j.media.2007.03.004]
Perona P and Malik J. 1990. Scale-space and edge detection using anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(7): 629-639[DOI:10.1109/34.56205]
Pezold S, Horváth A, Fundana K, Tsagkas C, AndělováM, Weier K, Amann M and Cattin P C. 2016. Automatic, robust, and globally optimal segmentation of tubular structures//Proceedings of the 19th International Conference on Medical Image Computing and Computer-Assisted Intervention. Athens, Greece: Springer: 362-370[ DOI: 10.1007/978-3-319-46726-9_42 http://dx.doi.org/10.1007/978-3-319-46726-9_42 ]
Qin Y L, Zheng H, Gu Y, Huang X L, Yang J, Wang L H, Yao F, Zhu Y M and Yang G Z. 2021. Learning tubule-sensitive CNNs for pulmonary airway and artery-vein segmentation in CT. IEEE Transactions on Medical Imaging, 40(6): 1603-1617[DOI:10.1109/TMI.2021.3062280]
Rahaghi F N, Argemí G, Nardelli P, Domínguez-Fandos D, Arguis P, Peinado V I, Ross J C, Ash S Y, de la Bruere I, Come C E, Diaz A A, Sánchez M, Washko G R, Barberà J A and Estépar R S J. 2019. Pulmonary vascular density: comparison of findings on computed tomography imaging with histology. European Respiratory Journal, 54(2): #1900370[DOI:10.1183/13993003.00370-2019]
Selle D, Preim B, Schenk A and Peitgen H O. 2002. Analysis of vasculature for liver surgical planning. IEEE Transactions on Medical Imaging, 21(11): 1344-1357[DOI:10.1109/TMI.2002.801166]
Sethian J A. 2001. Evolution, implementation, and application of level set and fast marching methods for advancing fronts. Journal of Computational Physics, 169(2): 503-555[DOI:10.1006/jcph.2000.6657]
Shen D G, Wu G R and Suk H I. 2017. Deep learning in medical image analysis. Annual Review of Biomedical Engineering, 19(1): 221-248[DOI:10.1146/annurev-bioeng-071516-044442]
Xiao C Y, Staring M, Wang Y N, Shamonin D P and Stoel B C. 2013. Multiscale bi-Gaussian filter for adjacent curvilinear structures detection with application to vasculature images. IEEE Transactions on Image Processing, 22(1): 174-188[DOI:10.1109/TIP.2012.2216277]
Yuan J, Bae E and Tai X C. 2010. A study on continuous max-flow and min-cut approaches//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, USA: IEEE: 2217-2224[ DOI: 10.1109/CVPR.2010.5539903 http://dx.doi.org/10.1109/CVPR.2010.5539903 ]
Zhao B W, Cao Z L and Wang S C. 2017. Lung vessel segmentation based on random forests. Electronics Letters, 53(4): 220-222[DOI:10.1049/el.2016.4438]
Zhou C, Chan H P, Kuriakose J W, Chughtai A, Wei J, Hadjiiski L M, Guo Y H, Patel S and Kazerooni E A. 2012. Pulmonary vessel segmentation utilizing curved planar reformation and optimal path finding (CROP) in computed tomographic pulmonary angiography (CTPA) for CAD applications//Proceedings Volume 8315, Medical Imaging 2012: Computer-Aided Diagnosis. San Diego, USA: SPIE: 83150 N[ DOI: 10.1117/12.912446 http://dx.doi.org/10.1117/12.912446 ]
相关作者
相关机构
京公网安备11010802024621
