Abstract
Carotid atherosclerosis is one of the leading causes of cardiovascular disease with high mortality. Multi-contrast MRI can identify atherosclerotic plaque components with high sensitivity and specificity. Accurate segmentation of the diseased carotid artery from MR images is very essential to quantitatively evaluate the state of atherosclerosis. However, due to the complex morphology of atherosclerosis plaques and the lack of well-annotated data, the segmentation of lumen and wall is very challenging. Different from popular deep learning methods, in this paper, we propose an integration segmentation framework by introducing a lightweight prediction model and improved optimal surface graph cuts (OSG), which adopts a simplified flow line sampling and post-reconstructing method to reduce the cost of graph construction. Moreover, a flexibly adaptive smoothing penalty is presented for maintaining the shape of diseased carotid surface. For the experiments, we have collected an MR image dataset from patients with carotid atherosclerosis and evaluated our method by cross-validation. It can reach 89.68%/80.29% of dice coefficients and 0.2480 mm/0.3396 mm of average surface distances on the lumen/wall segmentation, respectively. The experimental results show that our method can generate precise and reliable segmentation of both lumen and wall of diseased carotid artery with a quite small training cost.
Graphical abstract
Similar content being viewed by others
References
Teng Z, Peng W, Zhan Q, et al. (2016) An assessment on the incremental value of high-resolution magnetic resonance imaging to identify culprit plaques in atherosclerotic disease of the middle cerebral artery. Eur Radiol 26(7):2206–2214. https://doi.org/10.1007/s00330-015-4008-5
Teng Z, Brown AJ, Gillard JH (2016) From ultrasonography to high resolution magnetic resonance imaging: Towards an optimal management strategy for vulnerable carotid atherosclerotic plaques. EBioMedicine 3:2–3. https://doi.org/10.1016/j.ebiom.2016.01.001
Mingminglu YF, Zhang L et al (2020) Segment-specific progression of carotid artery atherosclerosis: a magnetic resonance vessel wall imaging study. Neuroradiology 62(2):211–220
Pereira T, Betriu A, Alves R (2019) Non-invasive imaging techniques and assessment of carotid vasa vasorum neovascularization: Promises and pitfalls. Trends in Cardiovascular Medicine 29(2):71–80. https://doi.org/10.1016/j.tcm.2018.06.007
Oshida S, Mori F, Sasaki M et al (2018) Wall shear stress and t1 contrast ratio are associated with embolic signals during carotid exposure in endarterectomy. Stroke 49(9):2061–2066. https://doi.org/10.1161/STROKEAHA.118.022322
Chen Y, Canton G, Kerwin WS, et al. (2016) Modeling hemodynamic forces in carotid artery based on local geometric features. Medical & Biological Engineering & Computing 54(9):1437–1452. https://doi.org/10.1007/s11517-015-1417-1
Kobayashi M, Hoshina K, Nemoto Y, et al. (2020) A penalized spline fitting method to optimize geometric parameters of arterial centerlines extracted from medical images. Computerized Medical Imaging and Graphics 84:101,746. https://doi.org/10.1016/j.compmedimag.2020.101746
Nieuwstadt HA, Speelman L, Breeuwer M et al (2014) The influence of inaccuracies in carotid mri segmentation on atherosclerotic plaque stress computations. Journal of Biomechanical Engineering 136 (2):021,015. https://doi.org/10.1115/1.4026178
Brown AJ, Teng Z, Calvert PA et al (2016) Plaque structural stress estimations improve prediction of future major adverse cardiovascular events after intracoronary imaging. Circulation: Cardiovascular Imaging 9(6):e004,172. https://doi.org/10.1161/circimaging.115.004172
Yuan C, Lin E, Millard J et al (1999) Closed contour edge detection of blood vessel lumen and outer wall boundaries in black-blood mr images. Magn Reson Imaging 17(2):257–266. https://doi.org/10.1016/s0730-725x(98)00162-3
Ladak HM, Milner J, Steinman DA (2000) Rapid three-dimensional segmentation of the carotid bifurcation from serial mr images. J Biomech Eng 122(1):96–99. https://doi.org/10.1115/1.429646
Jin Y, Ladak HM (2004) Software for interactive segmentation of the carotid artery from 3d black blood magnetic resonance images. Comput Methods Prog Biomed 75(1):31–43. https://doi.org/10.1016/j.cmpb.2003.10.003
Van’t Klooster R, de Koning PJ, Dehnavi RA et al (2012) Automatic lumen and outer wall segmentation of the carotid artery using deformable three-dimensional models in mr angiography and vessel wall images. J Magn Reson Imaging 35(1):156–165. https://doi.org/10.1002/jmri.22809
Hameeteman K, Van’t Klooster R, Selwaness M et al (2013) Carotid wall volume quantification from magnetic resonance images using deformable model fitting and learning-based correction of systematic errors. Physics in Medicine & Biology 58(5):1605. https://doi.org/10.1088/0031-9155/58/5/1605
Wang F, Guan Q, Chen S et al (2010) Multi-scale segmentation of carotid artery wall in mri images. In: The 2nd international conference on information science and engineering, IEEE, pp 1–4. https://doi.org/10.1109/ICISE.2010.5688938
Tang H, Van Walsum T, Van Onkelen RS et al (2012) Semiautomatic carotid lumen segmentation for quantification of lumen geometry in multispectral mri. Med Image Anal 16 (6):1202–1215. https://doi.org/10.1007/978-3-642-15711-0∖_13
Ukwatta E, Yuan J, Rajchl M et al (2013) 3-d carotid multi-region mri segmentation by globally optimal evolution of coupled surfaces. IEEE Trans Med Imag 32(4):770–785. https://doi.org/10.1109/tmi.2013.2237784
Arias Lorza AM, Petersen J, Van Engelen A et al (2015) Carotid artery wall segmentation in multispectral mri by coupled optimal surface graph cuts. IEEE Transactions on Medical Imaging 35(3):901–911. https://doi.org/10.1109/tmi.2015.2501751
Arias Lorza AM, Van Engelen A, Petersen J et al (2018) Maximization of regional probabilities using optimal surface graphs: Application to carotid artery segmentation in mri. Med Phys 45(3):1159–1169. https://doi.org/10.1002/mp.12771
Lu F, Wu F, Hu P, et al. (2017) Automatic 3d liver location and segmentation via convolutional neural network and graph cut. Int J CARS 12(2):171–182. https://doi.org/10.1007/s11548-016-1467-3
Li L, Yang G, Wu F et al (2019) Atrial scar segmentation via potential learning in the graph-cut framework. In: Statistical atlases and computational models of the heart. Atrial Segmentation and LV Quantification Challenges. Springer International Publishing, pp 152–160. https://doi.org/10.1007/978-3-030-12029-0∖_17
Liu Z, Song YQ, Sheng VS et al (2019) Liver ct sequence segmentation based with improved u-net and graph cut. Expert Syst Appl 126:54–63. https://doi.org/10.1016/j.eswa.2019.01.055
Jain PK, Sharma N, Giannopoulos AA, et al. (2021) Hybrid deep learning segmentation models for atherosclerotic plaque in internal carotid artery b-mode ultrasound. Computers in Biology and Medicine 136:104,721
Mi S, Bao Q, Wei Z et al (2021) Mbff-net: Multi-branch feature fusion network for carotid plaque segmentation in ultrasound. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 313–322
Jiang M, Zhao Y, Chiu B (2021) Segmentation of common and internal carotid arteries from 3d ultrasound images based on adaptive triple loss. Med Phys 48(9):5096–5114
Zhou T, Tan T, Pan X, et al. (2021) Fully automatic deep learning trained on limited data for carotid artery segmentation from large image volumes. Quantitative Imaging in Medicine and Surgery 11(1):67
Samber DD, Ramachandran S, Sahota A, et al. (2020) Segmentation of carotid arterial walls using neural networks. World Journal of Radiology 12(1):1–9
Tustison NJ, Avants BB, Cook PA, et al. (2010) N4itk: improved n3 bias correction. IEEE Transactions on Medical Imaging 29(6):1310–1320. https://doi.org/10.1109/tmi.2010.2046908
Kroon DJ (2019) Polygon2voxel. Online, mATLAB Central File Exchange. https://www.mathworks.com/matlabcentral/fileexchange/24086-polygon2voxel
Van’t Klooster R, Staring M, Klein S et al (2013) Automated registration of multispectral mr vessel wall images of the carotid artery. Med Phys 121(12):904. https://doi.org/10.1118/1.4829503
Escalera S, Pujol O, Radeva P (2009) Separability of ternary codes for sparse designs of error-correcting output codes. Pattern Recogn Lett 30(3):285–297. https://doi.org/10.1016/j.patrec.2008.10.002
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM et al (eds) Medical image computing and computer-assisted intervention – MICCAI 2015. https://doi.org/10.1007/978-3-319-24574-4∖_28. Springer International Publishing, Cham, pp 234–241
He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), IEEE, pp 770–778. https://doi.org/10.1109/CVPR.2016.90
Funding
This work was supported in part by the National Natural Science Foundation of China under grants U1908210, 11302195, and 61976191; in part by the Natural Science Foundation of Zhejiang Province under grants LQ20H160052, LY19F030015, and LY20H180006; in part by the Zhejiang Provincial Research Project on the Application of Public Welfare Technologies under Grant LGF22F020023.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhu, C., Wang, X., Chen, S. et al. Complex carotid artery segmentation in multi-contrast MR sequences by improved optimal surface graph cuts based on flow line learning. Med Biol Eng Comput 60, 2693–2706 (2022). https://doi.org/10.1007/s11517-022-02622-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-022-02622-z