重复性
高光谱成像
再现性
IRIS(生物传感器)
可靠性(半导体)
光谱成像
计算机科学
光学
遥感
生物医学工程
材料科学
人工智能
数学
医学
物理
统计
生物识别
地质学
量子力学
功率(物理)
作者
Luca Di Cecilia,Francesco Marazzi,Luigi Rovati
出处
期刊:2018 IEEE 4th International Forum on Research and Technology for Society and Industry (RTSI)
日期:2018-09-01
卷期号:10045: 1-5
被引量:2
标识
DOI:10.1109/rtsi.2018.8548513
摘要
The present study was conducted to evaluate the measuring performance of a prototype hyperspectral imaging system. This instrument was developed to measure the human iris spectral reflectance in vivo. Several previous works highlighted how changes in the iris pigmentation and morphology may provide an indication of the development and progression of certain eye pathologies. The use of hyperspectral imaging could aid physicians in the early detection of such diseases, by exploiting both the spatial and spectral features that this optical technique is able to collect. We evaluated the measurements repeatability from images acquired across 22 spectral bands in the visible and near-infrared range (480-900 nm), from 8 healthy volunteers. Moreover, we assessed the intra-and inter-session repeatability of the quantitative hyperspectral measurements. Repeatability was lower for darker irises and for wavelengths from 520 to 900nm. In particular, the coefficient of repeatability (95% of confidence interval) for measurements between sessions was ±10% and ±5% for dark and light irises, respectively. The within session repeatability was ±7.5% and ±4%, respectively. The obtained repeatability coefficients confirm the reliability and reproducibility of the hyperspectral data collected by our system.
科研通智能强力驱动
Strongly Powered by AbleSci AI