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

Area of Science:

• Ophthalmology
• Medical Imaging
• Computational Biology

Background:

• Optical Coherence Tomography (OCT) enables noninvasive cellular-level eye examination.
• Previous OCT studies on anterior chamber cells had limitations.
• Automated analysis of anterior chamber cells requires further validation.

Purpose of the Study:

• To supplement existing reports on automated analysis of anterior chamber cell images using spectral domain OCT (SD-OCT).
• To compare SD-OCT automated analysis with the Standardization of Uveitis Nomenclature (SUN) grading system.
• To evaluate cell density, size, and eccentricity using SD-OCT.

Main Methods:

• Analysis of 2398 anterior segment SD-OCT images from 34 patients.
• Development of Python code for automated measurement of cell density, size, and eccentricity.
• Comparison of automated measurements with SUN grading.

Main Results:

• Increases in SUN grade correlated significantly with cell density increases (p < 0.001).
• Significant differences in eccentricity were observed in uveitis, post-surgical inflammation, and vitreous hemorrhage (p < 0.001).
• SD-OCT automated analysis demonstrated high reliability, speed, and accuracy.

Conclusions:

• Anterior segment SD-OCT provides a reliable, fast, and accurate method for anterior chamber cell analysis.
• The SD-OCT automated method shows a strong correlation with the SUN grade system.
• Cell eccentricity measurements may serve as a valuable supplementary evaluation tool.