Novel Application Software for the Semi-Automated Analysis of Infrared Meibography Images

Abstract

Purpose: To develop semi-automated application software that quickly analyzes infrared meibography images taken with the CSO Sirius Topographer (CSO, Italy) and to compare them to the manual analysis system on the device (Phoenix software platform). Methods: A total of 52 meibography images verified as high quality were used and analyzed through manual and semi-automated meibomian gland (MG) detector software in this study. For the manual method, an experienced researcher circumscribed the MGs by putting dots around grape-like clusters in a predetermined rectangular area, and Phoenix software measured the MG loss area by percentage, which took around 10 to 15 minutes. MG loss was graded from 1 (<25%) to 4 (severe >75%). For the semi-automated method, 2 blind physicians (I and II) determined the area to be masked by putting 5 to 6 dots on the raw images and measured the MG loss area using the newly developed semi-automated MG detector application software in less than 1 minute. Semi-automated measurements were repeated 3 times on different days, and the results were evaluated using paired-sample t test, Bland–Altman, and kappa κ analysis. Results: The mean MG loss area was 37.24% with the manual analysis and 40.09%, 37.89%, and 40.08% in the first, second, and third runs with the semi-automated analysis (P < 0.05). Manual analysis scores showed a remarkable correlation with the semi-automated analysis performed by 2 operators (r = 0.950 and r = 0.959, respectively) (P < 0.001). According to Bland–Altman analysis, the 95% limits of agreement between manual analysis and semi-automated analysis by operator I were between −10.69% and 5% [concordance correlation coefficient (CCC) = 0.912] and between −9.97% and 4.3% (CCC = 0.923) for operator II. The limit of interoperator agreement in semi-automated analysis was between −4.89% and 4.92% (CCC = 0.973). There was good to very good agreement in grading between manual and semi-automated analysis results (κ 0.76–0.84) and very good interoperator agreement with semi-automated software (κ 0.91) (P < 0.001). Conclusions: For the manual analysis of meibography images, around one hundred dots have to be put around grape-like clusters to determine the MGs, which makes the process too long and prone to errors. The newly developed semi-automated software is a highly reproducible, practical, and faster method to analyze infrared meibography images with excellent correlation with the manual analysis.

Characterization and Prediction of the Clinical Outcome of Intense Pulsed Light-Based Treatment in Dry Eye Associated to Meibomian Gland Dysfunction

“…This examination included measurement of uncorrected and corrected distance visual acuity, manifest refraction, meibography and measurement of the NIBUT with the Sirius system (CSO, Firenze, Italy), slit lamp biomicroscopy, Schirmer test with anesthesia (fluorescein + topic anaesthesia, 5 min), measurement of tear osmolarity (TearLab, TearLab Inc., Escondido, CA, USA), characterization of dry eye symptomatology using the validated questionnaire OSDI (Ocular Surface Disease Index) [34], predominant meibum quality in right and left lower eyelid of each patient (0, clear liquid; 1, yellow liquid; 2, granular; 3, solid) expressed using the Collins TM expressor forceps (OptiMed, Sydney, Australia) and fundus evaluation. The non-invasive meibography and measurement of NIBUT provided by the Sirius system has been previously demonstrated to be valid and precise [35,36]. This same examination was repeated one month after finishing the last IPL treatment session to confirm the efficacy of the therapy.…”

Imaging the tarsal plate: A Mini-Review

“…This lack of agreement might be due to the poorer contrast and to the increased glare of the images. Shehzad et al (2019) developed and compared semiautomated software for MG analysis. The authors acquired 52 images from MGD and healthy patients through a CSO Sirius Topographer (CSO, Florence, Italy) which is based on a Placido disk technology with a Scheimpflug camera equipped with IR illumination.…”

Assessment of meibomian gland drop-out and visibility through a new quantitative method in scleral lens wearers: A one-year follow-up study

“…Therefore, the Tear Film and Ocular Surface Society Dry Eye Workshop II (TFOS DEWS II) Diagnostic Methodology Report acknowledged the need of developing new clinical tests as objective as possible to assess the ocular surface [29]. Some algorithms [13,14,[31][32][33][34][35][36][37][38] have been recently developed to assess the meibomian glands objectively, avoiding subjective grading scales since they depend on the ability of the examiner to detect gland alterations, decreasing repeatability and agreement between clinicians [39].…”