Keywords
Support Vector Machine
Coronary Artery Disease
Image Semantic Segmentation
Invasive Coronary Angiography
How to Cite
Funding data
-
Michigan Technological University
Grant numbers new faculty startup grant from Michigan Technological University Institute of Computing and Cybersystems -
Michigan Technological University
Grant numbers seed grant from Michigan Technological University Health Research Institute
Abstract
Accurate semantic segmentation of each coronary artery using invasive coronary angiography (ICA) is important for stenosis assessment and coronary artery disease (CAD) diagnosis. In this paper, we propose a multi-step semantic segmentation algorithm based on analyzing arterial segments extracted from ICAs. The proposed algorithm firstly extracts the entire arterial binary mask (binary vascular tree) using a deep learning-based method. Then we extract the centerline of the binary vascular tree and separate it into different arterial segments. Finally, by extracting the underlying arterial topology, position, and pixel features, we construct a powerful coronary artery segment classifier based on a support vector machine. Each arterial segment is classified into the left coronary artery (LCA), left anterior descending (LAD), and other types of arterial segments. The proposed method was tested on a dataset with 225 ICAs and achieved a mean accuracy of 70.33% for the multi-class artery classification and a mean intersection over union of 0.6868 for semantic segmentation of arteries. The experimental results show the effectiveness of the proposed algorithm, which provides impressive performance for analyzing the individual arteries in ICAs.
References
Benjamin EJ, Muntner P, Alonso A, Bittencourt MS, Callaway CW, Carson AP, Chamberlain AM, Chang AR, Cheng S, Das SR. Heart disease and stroke statistics-2019 update: a report from the American Heart Association. Circulation. Am Heart Assoc; 2019; 139(10): e56-e528.
Boden WE, O'Rourke RA, Teo KK, Hartigan PM, Maron DJ, Kostuk WJ, Knudtson M, Dada M, Casperson P, Harris CL, Chaitman BR, Shaw L, Gosselin G, Nawaz S, Title LM, Gau G, Blaustein AS, Booth DC, Bates ER, Spertus JA, Berman DS, Mancini GBJ, Weintraub WS. Optimal Medical Therapy with or without PCI for Stable Coronary Disease. N Engl J Med. 2007 Apr 12; 356(15): 1503-1516. https: //doi.org/10.1056/NEJMoa070829
Wu D, Wang X, Bai J, Xu X, Ouyang B, Li Y, Zhang H, Song Q, Cao K, Yin Y. Automated anatomical labeling of coronary arteries via bidirectional tree LSTMs. Int J Comput Assist Radiol Surg. 2019 Feb 1; 14(2): 271-280. https: //doi.org/10.1007/s11548-018-1884-6
Gifani P, Behnam H, Shalbaf A, Sani ZA. Automatic detection of end-diastole and end-systole from echocardiography images using manifold learning. Physiol Meas. IOP Publishing; 2010; 31(9): 1091. https: //doi.org/10.1088/0967-3334/31/9/002
Yang G, Broersen A, Petr R, Kitslaar P, de Graaf MA, Bax JJ, Reiber JHC, Dijkstra J. Automatic coronary artery tree labeling in coronary computed tomographic angiography datasets. 2011 Comput Cardiol. 2011. p. 109-112.
Nasr-Esfahani E, Karimi N, Jafari MH, Soroushmehr SMR, Samavi S, Nallamothu BK, Najarian K. Segmentation of vessels in angiograms using convolutional neural networks. Biomed Signal Process Control. 2018 Feb; 40: 240-251. https: //doi.org/10.1016/j.bspc.2017.09.012
Nasr-Esfahani E, Samavi S, Karimi N, Soroushmehr SR, Ward K, Jafari MH, Felfeliyan B, Nallamothu B, Najarian K. Vessel extraction in X-ray angiograms using deep learning. 2016 38th Annu Int Conf IEEE Eng Med Biol Soc EMBC. IEEE; 2016. p. 643-646. https: //doi.org/10.1109/EMBC.2016.7590784
Iyer K, Najarian CP, Fattah AA, Arthurs CJ, Soroushmehr SM, Subban V, Sankardas MA, Nadakuditi RR, Nallamothu BK, Figueroa CA. Angionet: a convolutional neural network for vessel segmentation in X-ray angiography. Sci Rep. Nature Publishing Group; 2021; 11(1): 1-13. https: //doi.org/10.1038/s41598-021-97355-8
Zhao C, Vij A, Malhotra S, Tang J, Tang H, Pienta D, Xu Z, Zhou W. Automatic extraction and stenosis evaluation of coronary arteries in invasive coronary angiograms. Comput Biol Med. 2021; 136: 104667. https: //doi.org/10.1016/j.compbiomed.2021.104667
Zhai M, Du T, Yang R, Zhang H. Coronary Artery Vascular Segmentation on Limited Data via Pseudo-Precise Label. 2019 41st Annu Int Conf IEEE Eng Med Biol Soc EMBC. 2019. p. 816-819. https: //doi.org/10.1109/EMBC.2019.8856682
Xian Z, Wang X, Yan S, Yang D, Chen J, Peng C. Main Coronary Vessel Segmentation Using Deep Learning in Smart Medical. Huang C, editor. Math Probl Eng. 2020 Oct 21; 2020: 1-9. https: //doi.org/10.1155/2020/8858344
Yang S, Kweon J, Roh J-H, Lee J-H, Kang H, Park L-J, Kim DJ, Yang H, Hur J, Kang D-Y, Lee PH, Ahn J-M, Kang S-J, Park D-W, Lee S-W, Kim Y-H, Lee CW, Park S-W, Park S-J. Deep learning segmentation of major vessels in X-ray coronary angiography. Sci Rep. 2019 Dec; 9(1): 16897. https: //doi.org/10.1038/s41598-019-53254-7
Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. Int Conf Med Image Comput Comput-Assist Interv. Springer; 2015. p. 234-241. https: //doi.org/10.1007/978-3-319-24574-4_28
Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L. Imagenet: A large-scale hierarchical image database. 2009 IEEE Conf Comput Vis Pattern Recognit. Ieee; 2009. p. 248-255. https: //doi.org/10.1109/CVPR.2009.5206848
Zhou Z, Rahman Siddiquee MM, Tajbakhsh N, Liang J. Unet++: A nested u-net architecture for medical image segmentation. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support. Springer; 2018. p. 3-11. https: //doi.org/10.1007/978-3-030-00889-5_1
Edward D. An Introduction to Morphological Image Processing | (1992) | Dougherty | Publications | Spie [Internet]. [cited 2022 May 16]. Available from: https: //spie.org/Publications/Book/48126?SSO=1
Xie J, Zhao Y, Liu Y, Su P, Zhao Y, Cheng J, Zheng Y, Liu J. Topology reconstruction of tree-like structure in images via structural similarity measure and dominant set clustering. Proc IEEECVF Conf Comput Vis Pattern Recognit. 2019. p. 8505-8513. https: //doi.org/10.1109/CVPR.2019.00870
Dashtbozorg B, Mendonça AM, Campilho A. An automatic graph-based approach for artery/vein classification in retinal images. IEEE Trans Image Process. IEEE; 2013; 23(3): 1073-1083. https: //doi.org/10.1109/TIP.2013.2263809
Maurer CR, Qi R, Raghavan V. A linear time algorithm for computing exact Euclidean distance transforms of binary images in arbitrary dimensions. IEEE Trans Pattern Anal Mach Intell. IEEE; 2003; 25(2): 265-270. https: //doi.org/10.1109/TPAMI.2003.1177156
Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH. The WEKA data mining software: an update. ACM SIGKDD Explor Newsl. ACM New York, NY, USA; 2009; 11(1): 10-18. https: //doi.org/10.1145/1656274.1656278
Kovesi PD. MATLAB and Octave functions for computer vision and image processing. Cent Explor Target Sch Earth Environ Univ West Aust Available https: //www.peterkovesi.com/matlabfns/. 2000; 147: 230.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2022 Chen Zhao, Robert Bober, Haipeng Tang, Jinshan Tang, Minghao Dong, Chaoyang Zhang, Zhuo He, Michele L. Esposito, Zhihui Xu, Weihua Zhou