Related Experiment Video
Updated: Dec 30, 2025
Quantifying Microglia Morphology from Photomicrographs of Immunohistochemistry Prepared Tissue Using ImageJ
Published on: June 5, 2018
Algorithm Variability in Quantification of Epithelial Defect Size in Microbial Keratitis Images
Matthias F Kriegel1,2, Jennifer Huang1, Hamza A Ashfaq1
1Department of Ophthalmology and Visual Sciences, W. K. Kellogg Eye Center, University of Michigan, Ann Arbor, MI.
Purpose:
To investigate the sources of measurement variability when quantifying the morphology of microbial keratitis (MK) from slit-lamp photography (SLP) images using a semiautomated, image-analysis algorithm.
Methods:
Prospectively enrolled patients with MK underwent SLP to obtain images of their epithelial defects (ED). Eyes were stained with fluorescein and imaged multiple times under blue light, at low and high magnifications. A masked research assistant chose the 3 best images and annotated each 3 times to provide seed regions corresponding to ED and healthy cornea. The algorithm returned the ED area for each seeded image. Eyes without EDs and algorithm failures were excluded. Variance components were estimated with a random effects model and intraclass correlation coefficients estimated with intragrader reliability.
Results:
A total of 42 eyes from 42 MK participants were photographed. After excluding poor quality images, eyes with no EDs, and algorithm failures, 34 patients with 92 images and 274 seeds were analyzed. No significant differences in the average ED area were found between seedings or high- versus low-SLP magnifications (all P > 0.5, paired t tests). Minimal measurement variability was because of image (0.9%), magnification (0.2%), or seed (0.1%). Most variability was attributable to differences in ED sizes between patients (85.2%). 13.7% of variability was unexplained. Multiple iterations of the algorithm on the same image showed good consistency (intraclass correlation coefficient = 0.98, 95% confidence interval, 0.97-0.99).
Conclusions:
Image-analysis algorithms showed good reliability for measuring the ED area from SLP images. Most measurement variability was because of between-patient differences, not imaging settings or application of the algorithm by the user.
Insights
This study found that image analysis algorithms reliably measure microbial keratitis (MK) epithelial defects from slit-lamp photos. Variability mainly stems from patient differences, not imaging or algorithm use.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computational Biology
Background:
- Microbial keratitis (MK) diagnosis and monitoring rely on accurate measurement of epithelial defects (ED).
- Slit-lamp photography (SLP) is a common imaging modality for ocular surface diseases.
- Semiautomated image-analysis algorithms offer potential for objective quantification of ED morphology.
Purpose of the Study:
- To identify sources of measurement variability in quantifying microbial keratitis (MK) epithelial defects (ED) using slit-lamp photography (SLP) and a semiautomated image-analysis algorithm.
- To assess the reliability and consistency of the image-analysis algorithm in measuring ED area.
- To determine the contribution of imaging parameters and user application to overall measurement variability.
Main Methods:
- Prospective enrollment of MK patients undergoing SLP with fluorescein staining.
- Multiple imaging sessions under blue light at varying magnifications.
- Annotation of epithelial defects and healthy cornea by a masked research assistant for algorithm input.
- Estimation of variance components using a random effects model and calculation of intraclass correlation coefficients for reliability.
Main Results:
- Analysis of 34 eyes (92 images, 274 seeds) after exclusions.
- No significant differences in average ED area based on seeding or magnification (P > 0.5).
- Minimal variability attributed to image (0.9%), magnification (0.2%), or seeding (0.1%).
- Major variability (85.2%) originated from inter-patient differences in ED size.
- High algorithm consistency demonstrated (ICC = 0.98).
Conclusions:
- Semiautomated image-analysis algorithms demonstrate reliable performance for measuring ED area from SLP images.
- The primary source of measurement variability is inherent differences in ED size between patients.
- Imaging settings and user application of the algorithm contribute minimally to measurement variability, indicating robustness.
More Related Videos
12:28Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
Published on: March 12, 2022
14:23Quantitative Measurement of Invadopodia-mediated Extracellular Matrix Proteolysis in Single and Multicellular Contexts
Published on: August 27, 2012