Fully automated calcium detection using optical coherence tomography

• Published in: 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) Vol. 2013; pp. 1430 - 1433
• Main Authors: Athanasiou, Lambros S., Bourantas, Christos V., Rigas, George A., Exarchos, Themis P., Sakellarios, Antonis I., Siogkas, Panagiotis K., Papafaklis, Michail I., Naka, Katerina K., Michalis, Lampros K., Prati, Francesco, Fotiadis, Dimitrios I.
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01.01.2013
• Subjects: Algorithms; Calcium; Calcium - chemistry; Catheters; Cluster Analysis; Coherence; Coronary Vessels - pathology; Diagnostic Imaging - instrumentation; Diagnostic Imaging - methods; Humans; Optical imaging; Optical sensors; Pattern Recognition, Automated; Plaque, Atherosclerotic - diagnosis; Predictive Value of Tests; Reproducibility of Results; Sensitivity; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Tomography; Tomography, Optical Coherence - instrumentation; Tomography, Optical Coherence - methods
• ISSN: 1094-687X; 1557-170X
• DOI: 10.1109/EMBC.2013.6609779

Optical Coherence Tomography (OCT) is a new invasive technology for performing high-resolution cross-sectional imaging of the coronary arteries. In OCT images only Calcified plaque (CA) components can be accurately depicted as light penetrates hard tissue. In this work we present an automated method for detecting CA in OCT images. The method is fully automated as no user intervention is needed and includes three steps. In the first step the region between the lumen and the maximum penetration depth of OCT from the lumen border is determined. In the second step the region is classified into 3 clusters using the K-means algorithm. CA is identified using the results of k-means. The method was validated using expeerts' annotations on 27 images. The sensitivity of the method is 83% with Positive predictive value (PVV) 74 %.