Robert Koprowski1, Sławomir Wilczyński2, Paweł Olczyk3, Anna Nowińska4, Beata Węglarz5, Edward Wylęgała6. 1. Department of Biomedical Computer Systems, University of Silesia, Faculty of Computer Science and Materials Science, Institute of Computer Science, ul. Będzińska 39, Sosnowiec 41-200, Poland. Electronic address: robert.koprowski@us.edu.pl. 2. School of Pharmacy, Medical University of Silesia in Katowice, Poland. Electronic address: swilczynski@sum.edu.pl. 3. School of Pharmacy, Medical University of Silesia in Katowice, Poland. Electronic address: polczyk@sum.edu.pl. 4. Department of Ophthalmology, District Railway Hospital, ul. Panewnicka 65, 40-760 Katowice, Poland. Electronic address: atrum2@gmail.com. 5. Department of Ophthalmology, District Railway Hospital, ul. Panewnicka 65, 40-760 Katowice, Poland. Electronic address: weglarz.beata@gmail.com. 6. Department of Ophthalmology, District Railway Hospital, ul. Panewnicka 65, 40-760 Katowice, Poland. Electronic address: wylegala@gmail.com.
Abstract
INTRODUCTION: Meibomian gland dysfunction is a common cause of dry eye syndrome which can also lead to eyelid inflammation. Today, diagnostics of meibomian glands is not fully automatic yet and is based on a qualitative assessment made by an ophthalmologist. Therefore, this article proposes a new automatic analysis method which provides a quantitative assessment of meibomian gland dysfunction. METHOD: The new algorithm involves a sequence of operations: image acquisition (acquisition of data from OCULUS Keratograph® 5M); image pre-processing (image conversion to gray levels, median filtering, removal of uneven lighting, normalization); main image processing (binarization, morphological opening, labeling, Gaussian filtering, skeletonization, distance transform, watersheds). The algorithm was implemented in Matlab with Image Processing Toolbox (Matlab: Version 7.11.0.584, R2010b) on a PC running Windows 7 Professional, 64-bit with the Intel Core i7-4960X CPU @ 3.60GHz. RESULTS AND CONCLUSIONS: The algorithm described in this article has the following features: it is fully automatic, provides fully reproducible results - sensitivity of 99.3% and specificity of 97.5% in the diagnosis of meibomian glands, and is insensitive to parameter changes. The time of image analysis for a single subject does not exceed 0.5s. Currently, the presented algorithm is tested in the Railway Hospital in Katowice, Poland.
INTRODUCTION:Meibomian gland dysfunction is a common cause of dry eye syndrome which can also lead to eyelid inflammation. Today, diagnostics of meibomian glands is not fully automatic yet and is based on a qualitative assessment made by an ophthalmologist. Therefore, this article proposes a new automatic analysis method which provides a quantitative assessment of meibomian gland dysfunction. METHOD: The new algorithm involves a sequence of operations: image acquisition (acquisition of data from OCULUS Keratograph® 5M); image pre-processing (image conversion to gray levels, median filtering, removal of uneven lighting, normalization); main image processing (binarization, morphological opening, labeling, Gaussian filtering, skeletonization, distance transform, watersheds). The algorithm was implemented in Matlab with Image Processing Toolbox (Matlab: Version 7.11.0.584, R2010b) on a PC running Windows 7 Professional, 64-bit with the Intel Core i7-4960X CPU @ 3.60GHz. RESULTS AND CONCLUSIONS: The algorithm described in this article has the following features: it is fully automatic, provides fully reproducible results - sensitivity of 99.3% and specificity of 97.5% in the diagnosis of meibomian glands, and is insensitive to parameter changes. The time of image analysis for a single subject does not exceed 0.5s. Currently, the presented algorithm is tested in the Railway Hospital in Katowice, Poland.
Authors: Clara Llorens-Quintana; Laura Rico-Del-Viejo; Piotr Syga; David Madrid-Costa; D Robert Iskander Journal: Transl Vis Sci Technol Date: 2019-08-02 Impact factor: 3.283