Yu Qiang Soh1, Gary Sl Peh2, Sacha L Naso3, Viridiana Kocaba3, Jodhbir S Mehta4. 1. Tissue Engineering and Stem Cell Group, Singapore Eye Research Institute, Singapore; Singapore National Eye Centre, Singapore; Ophthalmology Academic Clinical Program, Duke-NUS Graduate Medical School, Singapore. 2. Tissue Engineering and Stem Cell Group, Singapore Eye Research Institute, Singapore; Ophthalmology Academic Clinical Program, Duke-NUS Graduate Medical School, Singapore. 3. Tissue Engineering and Stem Cell Group, Singapore Eye Research Institute, Singapore. 4. Tissue Engineering and Stem Cell Group, Singapore Eye Research Institute, Singapore; Singapore National Eye Centre, Singapore; Ophthalmology Academic Clinical Program, Duke-NUS Graduate Medical School, Singapore; Department of Clinical Sciences, Duke-NUS Graduate Medical School, Singapore; Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore. Electronic address: jodmehta@gmail.com.
Abstract
PURPOSE: To describe the validation and implementation of an automated system, for the detection and quantification of guttae in Fuchs Endothelial Corneal Dystrophy (FECD). DESIGN: Observational reliability study METHODS: Patients with FECD underwent retroillumination corneal photography, followed by determination of the distributions and sizes of corneal guttae by an automated image analysis algorithm. Performance of the automated system was assessed via: a) validation against manual guttae segmentation, b) reproducibility studies to ensure consistency and c) evaluation for agreement with the Krachmer scale. It was then deployed to perform large-scale guttae assessment with anatomical subregion analysis in a batch of 40 eyes. RESULTS: Compared to manual segmentation, the automated system was reasonably accurate in identifying the correct number of guttae (mean count of 78 guttae per 1x1mm test-frame, overestimation: +10 per frame), but had a tendency to significantly over-estimate guttae size (mean guttae size 1073 μm2, overestimation: +255 μm2). Automated measurements of guttae counts and sizes were reproducible within a 1% discrepancy range across repeat intra-eye assessments. Automated guttae counts, inter-guttae distances, and density of inter-guttae gaps lesser than 40 μm (i.e. D40 density) were highly correlated with the Krachmer scale (p<0.001 for all). Large-scale guttae assessment demonstrated the automated system's potential to selectively identify a region of the corneal endothelium most affected by densely packed guttae. CONCLUSIONS: Automated guttae assessment facilitates the precise identification and quantification of guttae characteristics in FECD patients. This can be utilized clinically as a personalized descemetorhexis zone for Descemet Stripping Only and/or Descemet Membrane Transplantation.
PURPOSE: To describe the validation and implementation of an automated system, for the detection and quantification of guttae in Fuchs Endothelial Corneal Dystrophy (FECD). DESIGN: Observational reliability study METHODS:Patients with FECD underwent retroillumination corneal photography, followed by determination of the distributions and sizes of corneal guttae by an automated image analysis algorithm. Performance of the automated system was assessed via: a) validation against manual guttae segmentation, b) reproducibility studies to ensure consistency and c) evaluation for agreement with the Krachmer scale. It was then deployed to perform large-scale guttae assessment with anatomical subregion analysis in a batch of 40 eyes. RESULTS: Compared to manual segmentation, the automated system was reasonably accurate in identifying the correct number of guttae (mean count of 78 guttae per 1x1mm test-frame, overestimation: +10 per frame), but had a tendency to significantly over-estimate guttae size (mean guttae size 1073 μm2, overestimation: +255 μm2). Automated measurements of guttae counts and sizes were reproducible within a 1% discrepancy range across repeat intra-eye assessments. Automated guttae counts, inter-guttae distances, and density of inter-guttae gaps lesser than 40 μm (i.e. D40 density) were highly correlated with the Krachmer scale (p<0.001 for all). Large-scale guttae assessment demonstrated the automated system's potential to selectively identify a region of the corneal endothelium most affected by densely packed guttae. CONCLUSIONS: Automated guttae assessment facilitates the precise identification and quantification of guttae characteristics in FECDpatients. This can be utilized clinically as a personalized descemetorhexis zone for Descemet Stripping Only and/or Descemet Membrane Transplantation.
Authors: Orlando Özer; Mert Mestanoglu; Antonia Howaldt; Thomas Clahsen; Petra Schiller; Sebastian Siebelmann; Niklas Reinking; Claus Cursiefen; Björn Bachmann; Mario Matthaei Journal: J Clin Med Date: 2022-05-17 Impact factor: 4.964