Statistical evaluation of confocal microscopy images.

BACKGROUND: The coefficient of variation (CV) is defined as the standard deviation (sigma) of the fluorescent intensity of a population of beads or pixels expressed as a proportion or percentage of the mean (mu) intensity (CV = sigma/mu). The field of flow cytometry has used the CV of a population of bead intensities to determine if the flow cytometer is aligned correctly and performing properly. In a similar manner, the analysis of CV has been applied to the confocal laser scanning microscope (CLSM) to determine machine performance and sensitivity.
METHODS: Instead of measuring 10,000 beads using a flow cytometer and determining the CV of this distribution of intensities, thousands of pixels are measured from within one homogeneous Spherotech 10-microm bead. Similar to a typical flow cytometry population that consists of 10,000 beads, a CLSM scanned image consists of a distribution of pixel intensities representing a population of approximately 100,000 pixels. In order to perform this test properly, it is important to have a population of homogeneous particles. A biological particle usually has heterogeneous pixel intensities that correspond to the details in the biological image and thus shows more variability as a test particle.
RESULTS: The bead CV consisting of a population of pixel intensities is dependent on a number of machine variables that include frame averaging, photomultiplier tube (PMT) voltage, PMT noise, and laser power. The relationship among these variables suggests that the machine should be operated with lower PMT values in order to generate superior image quality. If this cannot be achieved, frame averaging will be necessary to reduce the CV and improve image quality. There is more image noise at higher PMT settings, making it is necessary to average more frames to reduce the CV values and improve image quality. The sensitivity of a system is related to system noise, laser light efficiency, and proper system alignment. It is possible to compare different systems for system performance and sensitivity if the laser power is maintained at a constant value. Using this bead CV test, 1 mW of 488 nm laser light measured on the scan head yielded a CV value of 4% with a Leica TCS-SP1 (75-mW argon-krypton laser) and a CV value of 1.3% with a Zeiss 510 (25-mW argon laser). A biological particle shows the same relationship between laser power, averaging, PMT voltage, and CV as do the beads. However, because the biological particle has heterogeneous pixel intensities, there is more particle variability, which does not make as useful as a test particle.
CONCLUSIONS: This CV analysis of a 10-microm Spherotech fluorescent bead can help determine the sensitivity in a confocal microscope and the system performance. The relationship among the factors that influence image quality is explained from a statistical endpoint. The data obtained from this test provides a systematic method of reducing noise and increasing image clarity. Many components of a CLSM, including laser power, laser stability, PMT functionality, and alignment, influence the CV and determine if the equipment is performing properly. Preliminary results have shown that the bead CV can be used to compare different confocal microscopy systems with regard to performance and sensitivity. The test appears to be analogous to CV tests made on the flow cytometer to assess instrument performance and sensitivity. Published 2001 Wiley-Liss, Inc.