Development of fully automated anterior chamber cell analysis based on image software

Abstract

Optical coherence tomography (OCT) is a noninvasive method that can quickly and accurately examine the eye at the cellular level. Several studies have used OCT for analysis of anterior chamber cells. However, these studies have several limitations. This study was performed to supplement existing reports of automated analysis of anterior chamber cell images using spectral domain OCT (SD-OCT) and to compare this method with the Standardization of Uveitis Nomenclature (SUN) grading system. We analyzed 2398 anterior segment SD-OCT images from 34 patients using code written in Python. Cell density, size, and eccentricity were measured automatically. Increases in SUN grade were associated with significant cell density increases at all stages (p < 0.001). Significant differences were observed in eccentricity in uveitis, post-surgical inflammation, and vitreous hemorrhage (p < 0.001). Anterior segment SD-OCT is reliable, fast, and accurate means of anterior chamber cell analysis. This method showed a strong correlation with the SUN grade system. Also, eccentricity could be helpful as a supplementary evaluation tool.

Figure 1

The square root of cell density according to SUN grade. Square root transformation was performed because the intervals between SUN grades are not equal, and the intervals increase with increasing grade. The cell density also increased significantly with increasing SUN grade. The boxes indicate the median and interquartile range, and the whiskers indicate 10–90 percentile.

Figure 2

Cell density according to the location of imaging. Images 0 and 20 refer to the top and bottom of the anterior chamber, respectively. There were no significant differences in cell density in all areas of the anterior chamber (p = 0.2773, Kruskal–Wallis chi-squared test). The boxes indicate the median and interquartile range, and the whiskers indicate 10–90 percentile.

Figure 3

Schematic diagram of the method applied in this study. a The original image. Right image shows the current examination location with a bold green line, and left image shows air, cornea, and anterior chamber in order. The hyperreflective pixels in the anterior chamber are cells. Inverted artifacts in the cornea vertex and reflection artifacts in the center of the image are shown. b Histogram created using the entire pixel reflection. Noise-related pixels are clustered between 0 and 60, and hyperreflective pixels caused by the cornea, iris, and artifacts are clustered between 100 and 255. c After image smoothing with median blur, the histogram has more prominent two peaks and more apparent differences. d Generation of a mask corresponding to the cornea and artifacts. e Hyperreflective pixels in the air are referred to as noise. The histogram of these pixels does not fit the normal distribution. f Anterior chamber image after subtracting the cornea and air. g Binary image created based on the noise threshold. h The anterior chamber cell location was overlaid with color in the original image to verify the program was operating correctly.

Figure 4

Various shape cell images. When one pixel is recognized as a cell, the area is recognized as 0 because of openCV limitation (left arrow). Large oval cells (middle arrow) and small round cells (right arrow) are also observed. Some cells are not recognized because these are too close to the cornea and covered by a mask (arrowheads).