Interocular Symmetry Analysis of Corneal Elevation Using the Fellow Eye as the Reference Surface and Machine Learning
Unilateral corneal indices and topography maps are routinely used in practice, however, although there is consensus that fellow-eye asymmetry can be clinically significant, symmetry studies are limited to local curvature and single-point thickness or elevation measures. To improve our current practi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Healthcare |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9032/9/12/1738 |
| _version_ | 1797504173801996288 |
|---|---|
| author | Shiva Mehravaran Iman Dehzangi Md Mahmudur Rahman |
| author_facet | Shiva Mehravaran Iman Dehzangi Md Mahmudur Rahman |
| author_sort | Shiva Mehravaran |
| collection | DOAJ |
| description | Unilateral corneal indices and topography maps are routinely used in practice, however, although there is consensus that fellow-eye asymmetry can be clinically significant, symmetry studies are limited to local curvature and single-point thickness or elevation measures. To improve our current practices, there is a need to devise algorithms for generating symmetry colormaps, study and categorize their patterns, and develop reference ranges for new global discriminative indices for identifying abnormal corneas. In this work, we test the feasibility of using the fellow eye as the reference surface for studying elevation symmetry throughout the entire corneal surface using 9230 raw Pentacam files from a population-based cohort of 4613 middle-aged adults. The 140 × 140 matrix of anterior elevation data in these files were handled with Python to subtract matrices, create color-coded maps, and engineer features for machine learning. The most common pattern was a monochrome circle (“flat”) denoting excellent mirror symmetry. Other discernible patterns were named “tilt”, “cone”, and “four-leaf”. Clustering was done with different combinations of features and various algorithms using Waikato Environment for Knowledge Analysis (WEKA). Our proposed approach can identify cases that may appear normal in each eye individually but need further testing. This work will be enhanced by including data of posterior elevation, thickness, and common diagnostic indices. |
| first_indexed | 2024-03-10T04:00:54Z |
| format | Article |
| id | doaj.art-de9270b120424096a103bf703c99464f |
| institution | Directory Open Access Journal |
| issn | 2227-9032 |
| language | English |
| last_indexed | 2024-03-10T04:00:54Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Healthcare |
| spelling | doaj.art-de9270b120424096a103bf703c99464f2023-11-23T08:34:54ZengMDPI AGHealthcare2227-90322021-12-01912173810.3390/healthcare9121738Interocular Symmetry Analysis of Corneal Elevation Using the Fellow Eye as the Reference Surface and Machine LearningShiva Mehravaran0Iman Dehzangi1Md Mahmudur Rahman2Department of Biology, School of Computer, Mathematical and Natural Sciences, Morgan State University, Baltimore, MD 21251, USACenter for Computational and Integrative Biology, Department of Computer Science, Rutgers University, Camden, NJ 08102, USADepartment of Computer Science, School of Computer, Mathematical and Natural Sciences, Morgan State University, Baltimore, MD 21251, USAUnilateral corneal indices and topography maps are routinely used in practice, however, although there is consensus that fellow-eye asymmetry can be clinically significant, symmetry studies are limited to local curvature and single-point thickness or elevation measures. To improve our current practices, there is a need to devise algorithms for generating symmetry colormaps, study and categorize their patterns, and develop reference ranges for new global discriminative indices for identifying abnormal corneas. In this work, we test the feasibility of using the fellow eye as the reference surface for studying elevation symmetry throughout the entire corneal surface using 9230 raw Pentacam files from a population-based cohort of 4613 middle-aged adults. The 140 × 140 matrix of anterior elevation data in these files were handled with Python to subtract matrices, create color-coded maps, and engineer features for machine learning. The most common pattern was a monochrome circle (“flat”) denoting excellent mirror symmetry. Other discernible patterns were named “tilt”, “cone”, and “four-leaf”. Clustering was done with different combinations of features and various algorithms using Waikato Environment for Knowledge Analysis (WEKA). Our proposed approach can identify cases that may appear normal in each eye individually but need further testing. This work will be enhanced by including data of posterior elevation, thickness, and common diagnostic indices.https://www.mdpi.com/2227-9032/9/12/1738unsupervised machine learningclusteringcorneacorneal topographyinterocular symmetrycorneal elevation |
| spellingShingle | Shiva Mehravaran Iman Dehzangi Md Mahmudur Rahman Interocular Symmetry Analysis of Corneal Elevation Using the Fellow Eye as the Reference Surface and Machine Learning Healthcare unsupervised machine learning clustering cornea corneal topography interocular symmetry corneal elevation |
| title | Interocular Symmetry Analysis of Corneal Elevation Using the Fellow Eye as the Reference Surface and Machine Learning |
| title_full | Interocular Symmetry Analysis of Corneal Elevation Using the Fellow Eye as the Reference Surface and Machine Learning |
| title_fullStr | Interocular Symmetry Analysis of Corneal Elevation Using the Fellow Eye as the Reference Surface and Machine Learning |
| title_full_unstemmed | Interocular Symmetry Analysis of Corneal Elevation Using the Fellow Eye as the Reference Surface and Machine Learning |
| title_short | Interocular Symmetry Analysis of Corneal Elevation Using the Fellow Eye as the Reference Surface and Machine Learning |
| title_sort | interocular symmetry analysis of corneal elevation using the fellow eye as the reference surface and machine learning |
| topic | unsupervised machine learning clustering cornea corneal topography interocular symmetry corneal elevation |
| url | https://www.mdpi.com/2227-9032/9/12/1738 |
| work_keys_str_mv | AT shivamehravaran interocularsymmetryanalysisofcornealelevationusingthefelloweyeasthereferencesurfaceandmachinelearning AT imandehzangi interocularsymmetryanalysisofcornealelevationusingthefelloweyeasthereferencesurfaceandmachinelearning AT mdmahmudurrahman interocularsymmetryanalysisofcornealelevationusingthefelloweyeasthereferencesurfaceandmachinelearning |