Support vector machine based classification and mapping of atherosclerotic plaques using fluorescence lifetime imaging (Conference Presentation)

Hussain Fatakdawala; Dimitris S. Gorpas; Julien Bec; Dinglong M. Ma; Diego R. Yankelevich; John W. Bishop M.D.; Laura Marcu

doi:10.1117/12.2214028

27 April 2016 Support vector machine based classification and mapping of atherosclerotic plaques using fluorescence lifetime imaging (Conference Presentation)

Hussain Fatakdawala, Dimitris S. Gorpas, Julien Bec, Dinglong M. Ma, Diego R. Yankelevich, John W. Bishop M.D., Laura Marcu

Author Affiliations +

Proceedings Volume 9689, Photonic Therapeutics and Diagnostics XII; 968934 (2016) https://doi.org/10.1117/12.2214028
Event: SPIE BiOS, 2016, San Francisco, California, United States

Abstract

The progression of atherosclerosis in coronary vessels involves distinct pathological changes in the vessel wall. These changes manifest in the formation of a variety of plaque sub-types. The ability to detect and distinguish these plaques, especially thin-cap fibroatheromas (TCFA) may be relevant for guiding percutaneous coronary intervention as well as investigating new therapeutics. In this work we demonstrate the ability of fluorescence lifetime imaging (FLIm) derived parameters (lifetime values from sub-bands 390/40 nm, 452/45 nm and 542/50 nm respectively) for generating classification maps for identifying eight different atherosclerotic plaque sub-types in ex vivo human coronary vessels. The classification was performed using a support vector machine based classifier that was built from data gathered from sixteen coronary vessels in a previous study. This classifier was validated in the current study using an independent set of FLIm data acquired from four additional coronary vessels with a new rotational FLIm system. Classification maps were compared to co-registered histological data. Results show that the classification maps allow identification of the eight different plaque sub-types despite the fact that new data was gathered with a different FLIm system. Regions with diffuse intimal thickening (n=10), fibrotic tissue (n=2) and thick-cap fibroatheroma (n=1) were correctly identified on the classification map. The ability to identify different plaque types using FLIm data alone may serve as a powerful clinical and research tool for studying atherosclerosis in animal models as well as in humans.

Conference Presentation

Citation Download Citation

Hussain Fatakdawala, Dimitris S. Gorpas, Julien Bec, Dinglong M. Ma, Diego R. Yankelevich, John W. Bishop M.D., and Laura Marcu "Support vector machine based classification and mapping of atherosclerotic plaques using fluorescence lifetime imaging (Conference Presentation)", Proc. SPIE 9689, Photonic Therapeutics and Diagnostics XII, 968934 (27 April 2016); https://doi.org/10.1117/12.2214028

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
PRESENTATION

WATCH
PRESENTATION SAVE TO MY LIBRARY

GET CITATION

KEYWORDS

Fluorescence lifetime imaging

Data modeling

Animal model studies

Classification systems

Clinical research

Data acquisition

Tissues

Show All Keywords

Keywords/Phrases

Search In:

Publication Years