Sensitivity，表示能找到許多真正的斑塊，但 PPV 只有 5%，表示此方法對整組 資料做大量猜測才導致此種情況。而探究原因後發現，因為我們使用的血管範圍
可能鈣化與狹窄的程序中就無法檢測到，導致這種顯著狹窄在此方法下未能被偵 測到。我們亦嘗試過一開始加入半徑判斷條件偵測，但會因為末端血管的影響而 導致整體辨識率下降。未來或許我們可以加入一些其他的特徵幫助判斷，例如面 積、形狀等等。
除此之外，未來我們可以嘗試將提出的兩種方法應用到另外 30 組測試資料 上，將更能評估我們方法的實用性與準確性。
參考文獻
[1] (2012). Rotterdam Coronary Artery Algorithm Evaluation Framework.
Available: http://coronary.bigr.nl/stenoses/
[2] H. Kirişli, M. Schaap, C. Metz, A. Dharampall, W. Meijboom, S.
Papadopoulou, et al., "Standardized evaluation framework for evaluating coronary artery stenosis detection, stenosis quantification and lumen segmentation algorithms in computed tomography angiography," Medical Image Analysis, 2013.
[3] M. A. Luengo-Oroz, M. J. Ledesma-Carbayo, J. Gómez-Diego, M. A.
García-Fernández, M. Desco, and A. Santos, "Extraction of the coronary artery tree in cardiac computer tomographic images using morphological operators,"
in Functional Imaging and Modeling of the Heart, ed: Springer, 2007, pp.
424-432.
[4] A. Hennemuth, T. Boskamp, D. Fritz, C. Kühnel, S. Bock, D. Rinck, et al.,
"One-click coronary tree segmentation in CT angiographic images," in International Congress Series, 2005, pp. 317-321.
[5] C. Metz, M. Schaap, A. van der Giessen, T. van Walsum, and W. Niessen,
"Semi-automatic coronary artery centerline extraction in computed
tomography angiography data," in Biomedical Imaging: From Nano to Macro, 2007. ISBI 2007. 4th IEEE International Symposium on, 2007, pp. 856-859.
[6] B. Bouraoui, C. Ronse, J. Baruthio, N. Passat, and P. Germain, "Fully automatic 3D segmentation of coronary arteries based on mathematical morphology," in Biomedical Imaging: From Nano to Macro, 2008. ISBI 2008.
5th IEEE International Symposium on, 2008, pp. 1059-1062.
[7] P. H. Kitslaar, M. Frenay, E. Oost, J. Dijkstra, B. Stoel, and J. H. Reiber,
"Connected Component and Morpholgy Based Extraction of Arterial Centerlines of the Heart (CocomoBeach)," The MIDAS Journal (09 2008), 2008.
[8] 陳建順, "自動化冠狀動脈分割與註冊方法," 資訊科學與工程研究所, 交 通大學, 2009.
[9] C. Bauer and H. Bischof, "Edge based tube detection for coronary artery centerline extraction," The Insight Journal, 2008.
[10] F. Renard and Y. Yang, "Image segmentation for detection of soft plaques in multidetector CT images," in Image Analysis and Interpretation, 2008. SSIAI 2008. IEEE Southwest Symposium on, 2008, pp. 121-124.
[11] A. Eslami, A. Aboee, Z. Hodaei, M. Javanshir, S. C. Moghaddam, A.
Katouzian, et al. Quantification of Coronary Arterial Stenosis by Inflating
Tubes in CT Angiographic images. Available:
http://coronary.bigr.nl/stenoses/pdf/Eslami_camp_158.pdf
[12] I. Melki, H. Talbot, J. Cousty, C. Pruvot, J. Knoplioch, L. Launay, et al.
Automatic Coronary Arteries Stenoses Detection in 3D CT angiography.
Available: http://coronary.bigr.nl/stenoses/pdf/Melki_A3SI_148.pdf [13] B. Mohr, S. Masood, and C. Plakas, "Accurate lumen segmentation and
stenosis detection and quantification in coronary CTA," in Proceedings of 3D Cardiovascular Imaging: a MICCAI Segmentation Challenge Workshop, 2012.
[14] C. Wang, R. Moreno, and Ö . Smedby. (2012). Vessel Segmentation Using Implicit Model-Guided Level Sets. Available:
http://coronary.bigr.nl/stenoses/pdf/Wang_CMIV_160.pdf
[15] R. Shahzad, T. van Walsum, H. Kirisli, H. Tang, C. Metz, M. Schaap, et al.
(2012). Automatic Stenoses Detection, Quantification and Lumen Segmentation of the Coronary Arteries using a Two Point Centerline Extraction Scheme. Available:
http://link.springer.com/content/pdf/10.1007%2Fs10554-013-0271-1.pdf [16] İ. Öksüz, D. Ünay, and K. Kadıpaşaoğlu. A Hybrid Method for Coronary Artery Stenoses Detection and Quantification in CTA Images. Available:
http://coronary.bigr.nl/stenoses/pdf/Oksuz_BAU_168.pdf
[17] S. Cetin and G. Unal. (2012). Automatic detection of coronary artery stenosis in CTA based on vessel intensity and geometric features. Available:
http://coronary.bigr.nl/stenoses/pdf/Cetin_Simira_226.pdf
[18] A. Broersen, P. H. Kitslaar, M. Frenay, and J. Dijkstra. FrenchCoast: Fast, Robust Extraction for the Nice Challenge on Coronary Artery Segmentation of the Tree. Available:
http://coronary.bigr.nl/stenoses/pdf/Broersen_LKEB_164.pdf
[19] G. Yang, P. Kitslaar, M. Frenay, A. Broersen, M. J. Boogers, J. J. Bax, et al.,
"Automatic centerline extraction of coronary arteries in coronary computed tomographic angiography," The International Journal of Cardiovascular Imaging, vol. 28, pp. 921-933, 2012.
[20] M. J. Boogers, A. Broersen, J. E. van Velzen, F. R. de Graaf, H. M. El-Naggar, P. H. Kitslaar, et al., "Automated quantification of coronary plaque with computed tomography: comparison with intravascular ultrasound using a dedicated registration algorithm for fusion-based quantification," European heart journal, vol. 33, pp. 1007-1016, 2012.
[21] M. Duval, E. Ouzeau, F. Precioso, and B. Matuszewski. Coronary Artery Stenoses Detection with Random Forest. Available:
http://coronary.bigr.nl/stenoses/pdf/Duval_UCLan-UNS_230.pdf
[22] S. Theodoridis and K. Koutroumbas, Pattern recognition, 3rd ed. San Diego, CA: Academic Press, 2006.
[23] T. Birdal. (2011). Maximum Inscribed Circle using Voronoi Diagram.
Available:
http://www.mathworks.com/matlabcentral/fileexchange/32543-maximum-insc ribed-circle-using-voronoi-diagram
[24] K.-L. Lor and C.-M. Chen. Probabilistic Model Based Evaluation of Coronary Artery Stenosis on Computed Tomography Angiography. Available:
http://coronary.bigr.nl/stenoses/pdf/Lor_MIRAGE_174.pdf
[25] L. Flórez-Valencia, M. Orkisz, R. A. C. Jerez, J. S. T. González, E. M. C.
Agudelo, C. Mouton, et al. Coronary artery segmentation and stenosis quantification in CT images with use of a right generalized cylinder model.
Available: http://coronary.bigr.nl/stenoses/pdf/Florez_VesselPUJ_162.pdf