Authors:
Beatriz Remeseiro
1
;
Antonio Mosquera
2
;
Manuel G. Penedo
1
and
Carlos García-Resúa
2
Affiliations:
1
University of A Coruña, Spain
;
2
University of Santiago de Compostela, Spain
Keyword(s):
Tear Film, Interference Patterns, Color Texture Analysis, Image Segmentation, Machine Learning.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Data Manipulation
;
Evolutionary Computing
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Machine Learning
;
Methodologies and Methods
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Soft Computing
;
Symbolic Systems
Abstract:
Dry eye syndrome is characterized by symptoms of discomfort, ocular surface damage, reduced tear film stability, and tear hyperosmolarity. These features can be identified by several types of diagnostic tests, although there may not be a direct correlation between the severity of symptoms and the degree of damage. One of the most used clinical tests is the analysis of the lipid interference patterns, which can be observed on the tear film, and their classification into the Guillon categories. Our previous researches have demonstrated that the interference patterns can be characterized as color texture patterns. Thus, the manual test done by experts can be performed through an automatic process which saves time for experts and provides unbiased results. Nevertheless, the heterogeneity of the tear film makes the classification of a patient’s image into a single category impossible. For this reason, this paper presents a methodology to create tear film maps based on the lipid interferen
ce patterns. In this way, the output image represents the distribution and prevalence of the Guillon categories on the tear film. The adequacy of the proposed methodology was demonstrated since it achieves reliable results in comparison with the annotations done by experts.
(More)