Principal component analysis of indocyanine green fluorescence dynamics for diagnosis of vascular diseases

Jihye Seo; Yuri An; Jungsul Lee; Chulhee Choi

doi:10.1117/12.2076875

4 March 2015 Principal component analysis of indocyanine green fluorescence dynamics for diagnosis of vascular diseases

Jihye Seo, Yuri An, Jungsul Lee, Chulhee Choi

Proceedings Volume 9313, Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XIII; 93131C (2015) https://doi.org/10.1117/12.2076875
Event: SPIE BiOS, 2015, San Francisco, California, United States

Abstract

Indocyanine green (ICG), a near-infrared fluorophore, has been used in visualization of vascular structure and non-invasive diagnosis of vascular disease. Although many imaging techniques have been developed, there are still limitations in diagnosis of vascular diseases. We have recently developed a minimally invasive diagnostics system based on ICG fluorescence imaging for sensitive detection of vascular insufficiency. In this study, we used principal component analysis (PCA) to examine ICG spatiotemporal profile and to obtain pathophysiological information from ICG dynamics. Here we demonstrated that principal components of ICG dynamics in both feet showed significant differences between normal control and diabetic patients with vascula complications. We extracted the PCA time courses of the first three components and found distinct pattern in diabetic patient. We propose that PCA of ICG dynamics reveal better classification performance compared to fluorescence intensity analysis. We anticipate that specific feature of spatiotemporal ICG dynamics can be useful in diagnosis of various vascular diseases.

Citation Download Citation

Jihye Seo, Yuri An, Jungsul Lee, and Chulhee Choi "Principal component analysis of indocyanine green fluorescence dynamics for diagnosis of vascular diseases", Proc. SPIE 9313, Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XIII, 93131C (4 March 2015); https://doi.org/10.1117/12.2076875

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