Abstract
In this study, time-resolved laser-induced fluorescence spectroscopy (TR-LIFS) and ultrasonography were applied to detect vulnerable (high-risk) atherosclerotic plaque. A total of 813 TR-LIFS measurements were taken from carotid plaques of 65 patients, and subsequently analyzed using the Laguerre deconvolution technique. The investigated spots were classified by histopathology as Thin, Fibrotic, Calcified, Low-Inflamed, Inflamed and Necrotic lesions. Spectral and time-resolved parameters (normalized intensity values and Laguerre expansion coefficients) were extracted from the TR-LIFS data. Feature selection for classification was performed by either analysis of variance (ANOVA) or principal component analysis (PCA). A stepwise linear discriminant analysis algorithm was developed for detecting Inflamed and Necrotic lesion, representing the most vulnerable plaques. These vulnerable plaques were detected with high sensitivity (>80%) and specificity (>90%). Ultrasound (US) imaging was obtained in 4 carotid plaques in addition to TR-LIFS examination. Preliminary results indicate that US provides important structural information of the plaques that could be combined with the compositional information obtained by TR-LIFS, to obtain a more accurate diagnosis of vulnerable atherosclerotic plaque.
Original language | English |
---|---|
Title of host publication | 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06 |
Pages | 2663-2666 |
Number of pages | 4 |
DOIs | |
Publication status | Published - 1 Dec 2006 |
Externally published | Yes |
Event | 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06 - New York, NY, United States Duration: 30 Aug 2006 → 3 Sept 2006 |
Conference
Conference | 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06 |
---|---|
Country/Territory | United States |
City | New York, NY |
Period | 30/08/06 → 3/09/06 |
Keywords
- Atherosclerosis
- Laguerre expansion technique
- Time-resolved fluorescence spectroscopy
ASJC Scopus subject areas
- Signal Processing
- Biomedical Engineering
- Computer Vision and Pattern Recognition
- Health Informatics