5 March 2018 Fast detection of vascular plaque in optical coherence tomography images using a reduced feature set
Author Affiliations +
Proceedings Volume 10591, 2nd Canterbury Conference on OCT with Emphasis on Broadband Optical Sources; 105910P (2018) https://doi.org/10.1117/12.2283017
Event: Second Canterbury Conference on Optical Coherence Tomography, 2017, Canterbury, United Kingdom
Abstract
Optical coherence tomography (OCT) images are capable of detecting vascular plaque by using the full set of 26 Haralick textural features and a standard K-means clustering algorithm. However, the use of the full set of 26 textural features is computationally expensive and may not be feasible for real time implementation. In this work, we identified a reduced set of 3 textural feature which characterizes vascular plaque and used a generalized Fuzzy C-means clustering algorithm. Our work involves three steps: 1) the reduction of a full set 26 textural feature to a reduced set of 3 textural features by using genetic algorithm (GA) optimization method 2) the implementation of an unsupervised generalized clustering algorithm (Fuzzy C-means) on the reduced feature space, and 3) the validation of our results using histology and actual photographic images of vascular plaque. Our results show an excellent match with histology and actual photographic images of vascular tissue. Therefore, our results could provide an efficient pre-clinical tool for the detection of vascular plaque in real time OCT imaging.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ammu Prakash, Ammu Prakash, Mariano Ocana Macias, Mariano Ocana Macias, Mark Hewko, Mark Hewko, Michael Sowa, Michael Sowa, Sherif Sherif, Sherif Sherif, } "Fast detection of vascular plaque in optical coherence tomography images using a reduced feature set ", Proc. SPIE 10591, 2nd Canterbury Conference on OCT with Emphasis on Broadband Optical Sources, 105910P (5 March 2018); doi: 10.1117/12.2283017; https://doi.org/10.1117/12.2283017
PROCEEDINGS
4 PAGES


SHARE
Back to Top