Abstract
Purpose
Epicardial ultrasound (EUS) can be used to assess the quality of coronary artery bypass graft surgery (CABG) anastomoses by determining stenotic rates. Currently, no objective quantitative methods are available for the analysis of EUS images. Therefore, surgeons have to be trained in interpreting EUS images, which may limit the use of EUS in clinical practice. Automatic detection of vessel structures can enable the objective and quantitative quality assessment of anastomoses without user interaction to facilitate the revision of anastomoses during the primary surgery.
Methods
An automatic vessel detection algorithm extracted and detected image regions that uniquely intersected with the vessel lumen of anastomotic structures. First, an initial pixel-based segmentation was performed from regional minimums using a watershed segmentation and an adaptive thresholding approach. A region-based merging step was then performed to merge oversegmented vessel structures using a Bayesian classification of different region combinations constructed from the pixel-based segmentations. Finally, a vessel classification step was performed on the extracted regions after the region-based merging to determine the probabilities that the regions contained vessel structures.
Results
The performance of the vessel classifier was tested using m-fold cross-validation of 320 EUS images containing anastomotic vessel structures from 16 anastomoses made on healthy porcine vessels. An area under the curve of 0.966 (95 % CI 0.951–0.984) and 0.989 (95 % CI 0.985–0.993, \({ {p}} < 0.001\)) of a precision–recall and receiver operator characteristic curve, respectively, was obtained when detecting vessel regions extracted from the EUS images.
Conclusions
The vessel detection algorithm can detect vessel regions in EUS images at a high accuracy. It can be used to enable the automatic analysis of EUS images for the quality assessment of CABG anastomoses.
Similar content being viewed by others
References
Mack MJ, Magovern JA, Acuff TA, Landreneau RJ, Tennison DM, Tinnerman EJ, Osborne JA (1999) Results of graft patency by immediate angiography in minimally invasive coronary artery surgery. Ann Thorac Surg 68:383–389
Mack MJ (2008) Intraoperative coronary graft assessment. Curr Opin Cardiol 23:568–572
Jaber SF, Koenig SC, BhaskerRao B, VanHimbergen DJ, Cerrito PB, Ewert DJ, Gray LA Jr, Spence PA (1998) Role of graft flow measurement technique in anastomotic quality assessment in minimally invasive cabg. Ann Thorac Surg 66(3):1087–1092
Haaverstad R, Vitale N, Tjomsland O et al (2002) Intraoperative color Doppler ultrasound assessment of LIMA-to-LAD anastomoses in off-pump coronary artery bypass grafting. Ann Thorac Surg 74:S1390–S1394
Hol PK, Andersen K, Skulstad H et al (2007) Epicardial ultrasonography: a potential method for intraoperative quality assessment of coronary bypass anastomoses? Ann Thorac Surg 84:801–807
Di Giammarco G, Canosa C, Foschi M et al (2014) Intraoperative graft verification in coronary surgery: increased diagnostic accuracy adding high-resolution epicardial ultrasonography to transit-time flow measurement. Eur J Cardiothorac Surg 45:e41–e45
Budde RPJ, Meijer R, Dessing TC, Borst C, Gründeman PF (2005) Detection of construction errors in ex vivo coronary artery anastomoses by 13-MHz epicardial ultrasonography. J Thorac Cardiovasc Surg 129:1078–1083
Tjomsland O, Wiseth R, Wahba A, Tromsdal A, Samstad SO, Haaverstad R (2003) Intraoperative color Doppler ultrasound assessment of anastomoses of the left internal mammary artery to the left anterior descending coronary artery during off-pump coronary artery bypass surgery correlates with angiographic evaluation at the 8-month follow-up. Heart Surg Forum 6(5):375–379
Stoitsis J, Golemati S, Kendros S, Nikita KS (2008) Automated detection of the carotid artery wall in B-mode ultrasound images using active contours initialized by the Hough Transform. Conf Proc IEEE Eng Med Biol Soc 2008:3146–3149
Liu S, Padfield D, Mendonca P (2013) Tracking of carotid arteries in ultrasound images. Med Image Comput Comput Assist Interv 16:526–533
Rahmatullah B, Papageorghiou AT, Noble JA (2012) Integration of local and global features for anatomical object detection in ultrasound. MICCAI. 7512:402–409
Moon WK, Lo C-M, Chen R-T et al (2014) Tumor detection in automated breast ultrasound images using quantitative tissue clustering. Med Phys 41:042901
Mori G, Ren X, Efros A, Malik J (2004) Recovering human body configurations: combining segmentation and recognition. IEEE Comput Soc Conf Comput Vis Pattern Recognit 2:1063–1069
Jørgensen AS, Schmidt SE, Staalsen N-H, Østergaard LR (2012) Automatic vessel tracking and segmentation using epicardial ultrasound in bypass surgery. Annu Comput Cardiol 39:9–12
Meyer F (1994) Topographic distance and watershed lines. Signal Process 38:113–125
Gonzalez RC, Woods RE (2008) Digital image processing. Image Process 49:954
Jolliffe IT (2002) Principal component analysis. 2nd edn. Encycl Stat Behav Sci 30:487
Staalsen N-H, Kjaergaard B, Andreasen JJ (2011) A new technique facilitating intraoperative, high-frequency echocardiography of coronary bypass graft anastomoses. J Thorac Cardiovasc Surg 141:295–296
Conflict of interest
Alex Skovsbo Jørgensen, Samuel Emil Schmidt, Niels-Henrik Staalsen and Lasse Riis Østergaard declare that they have no conflicts of interest.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jørgensen, A.S., Schmidt, S.E., Staalsen, NH. et al. Automatic detection of coronary artery anastomoses in epicardial ultrasound images. Int J CARS 10, 1313–1323 (2015). https://doi.org/10.1007/s11548-014-1144-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-014-1144-3