Quantization Methodology of Autolfuorescence Bronchoscopy Image in the YUV System
10.3779/j.issn.1009-3419.2014.11.05
- VernacularTitle:在YUV色彩空间中自荧光气管镜图像定量方法的临床应用
- Author:
ZHENG XIAOXUAN
1
;
XIONG HONGKAI
;
LI YONG
;
HAN BAOHUI
;
SUN JIAYUAN
Author Information
1. 上海交通大学附属胸科医院内镜室
- Keywords:
Lung neoplasms;
Diagnosis;
Autolfuorescence bronchoscopy;
White-light bronchoscopy;
Medical im-age processing
- From:
Chinese Journal of Lung Cancer
2014;(11):797-803
- CountryChina
- Language:Chinese
-
Abstract:
Background and objective hTe aim of this study is to determine the best reference values of the opti-mal evaluation indexes that identify different disease types. Disease identiifcation was conducted using the YUV quantitative analysis of autolfuorescence bronchoscopy (AFB) images in the target areas. Furthermore, this study discusses the signiifcance of AFB in the diagnosis of the central-type lung cancer. Methods A biopsy was conducted for cases that showed pathologic changes under either autolfuorescence or white-light bronchoscopy. Moreover, MATLAB was used to carry out the quantita-tive analyses of lesion in multi-color spaces from AFB images. hTe cases were divided into different groups according to the pathological diagnosis of normal bronchial mucosa, inlfammation, low-grade dysplasia (LGD), high-grade dysplasia (HGD), and invasive cancer. SPSS 11.5 was used to process the data for statistical analysis. Results hTe Y values were different and statistically different between invasive cancer and LGD (P<0.001) and invasive cancer and inlfammation (P=0.040), respec-tively. hTe U values between invasive cancer and the other groups were statistically different (P<0.050). Similarly, the V values between invasive cancer and LGD and inlfammation and normal bronchial mucosa were different. Lastly, the V values between normal bronchial mucosa and HGD and inlfammation and normal bronchial mucosa were different. Conclusion hTe YUV values in the AFB effectively identiifed benign and malignant diseases and were proven to be effective scientiifc bases for the ac-curate AFB diagnosis of lung cancer.
