Lucía Ramos

Texture and color analysis for the automatic classification of the eye lipid layer

This paper describes a methodology for the automatic classification of the eye lipid layer based on the categories enumerated by Guillon [1]. From a photography of the eye, the system detects the region of interest where the analysis will take place, extracts its low-level features, generates a feature vector that describes it and classifies the feature vector in one of the target categories. We have tested our methodology on a dataset composed of 105 images, with a classification rate of over

Colour Texture Analysis for Classifying the Tear Film Lipid Layer: A Comparative Study

This paper presents a comparative study of different texture extraction methods for the automatic classification of the tear film lipid layer based on the categories enumerated by Guillon. From a photography of the eye, a region of interest is detected and its low-level features are extracted, generating a feature vector that describes it, to be finally classified in one of the target categories. This paper discusses several texture analysis methods and colour spaces to generate the feature vectors. The proposed methods have been tested on a dataset composed of 105 images, with a classification rate of over 95\% in some cases.

Analysis of parameters for the automatic computation of the tear film break-up time test based on CCLRU standards

Dry eye syndrome is affecting a remarkable percentage of population. The prevalence is 10-15% of normal population, and 18-30% of contact lenses users. The break-up time (BUT) is a clinical test used for the diagnosis of this disease. In this work, we perform an analysis of parameters for a global and a local automatic computation of the BUT measure, based on criteria of specificity and sensitivity. We have tested our methodology on a dataset composed of 18 videos annotated by 4 different experts. The local analysis preserves the results of the global approach providing useful additional information about the break-up tear zone.

Automation of the tear film break-up time test

The Break-Up Time test (BUT) evaluates the quality and stability of the tear film. It is used for the diagnosis of the dry eye syndrome, a widespread disease in the developed world. This paper describes an automatic methodology to evaluate the BUT test. This methodology locates the different measurement areas from a video of the tear film, extracts the region of interest and performs the BUT test in each measurement area. We have tested our methodology on a dataset composed of 18 videos annotated by 4 different experts. The difference between the automatic measurement and the value provided by the experts is in the same range as between the experts themselves.

Diurnal variations in tear film break‐up time determined in healthy subjects by software‐assisted interpretation of tear film video recordings

This study was designed to examine diurnal variations in tear film break‐up time (BUT) and maximum blink interval (MBI) and to assess two different ways of calculating these variables on video recordings of the BUT test interpreted with the help of especially designed software. The repeatability of interpreting BUT video recordings was also addressed.

On the Automation of the Tear Film Non-invasive Break-up Test

Dry eye syndrome (DES) is a common disorder of the tear film, affecting a significant percentage of the population. The Non Invasive Break-Up Time (NIBUT) is a clinical test used for the diagnosis of DES. In this work, we propose a methodology for the semi-automatic computation of the NIBUT test. We tested our methodology on a dataset composed of 15 videos manually annotated and high success rates were obtained. The promising results of this approach mean a step forward on the development of computer aided tools for DES assessment.

Colour Texture Segmentation of Tear Film Lipid Layer Images

Dry eye is a symptomatic disease which can be diagnosed by several clinical tests. One of them is the evaluation of the interference lipid pattern and its classification into one of the Guillon categories. Previous researches have automatised this manual test, saving time for experts and providing unbiased results. However, the heterogeneity of the tear film lipid layer makes its classification into a single category per eye impossible. For this reason, this paper presents a first approximation to segment tear film images into the Guillon categories, in order to detect several categories in each patient. The adequacy of the methodology was demonstrated since it achieves reliable results in comparison with the annotations done by optometrists.

Break-Up Analysis of the Tear Film Based on Time, Location, Size and Shape of the Rupture Area

The Break-Up Time test (BUT) evaluates the quality and stability of the tear film. It is used for the diagnosis of the dry eye syndrome, a common disorder of the tear film, affecting a significant percentage of the population. This work describes a fully automatic methodology to compute the time in which the break-up occurs and to analyze the rupture zone. This analysis provides useful quantitative and qualitative information for the clinical practice about the location, size and shape of the break-up areas.

Computational Approach for Measuring the Tear Film Break-Up Time in an Unsupervised Manner

Dry eye syndrome is a common disorder of the tear film, affecting a significant percentage of the population. The Break-Up Time (BUT) is a clinical test used for the diagnosis of this disease. In this research, it is proposed an automatic methodology to evaluate the BUT test. This methodology locates the different measurement areas from a video of the tear film, extracts the Region Of Interest (ROI) and performs the BUT test in each measurement area. Furthermore, it is independent of some specific features of each video such as the eye size, the intensity variation, or the starting point of the measurement frame sequence. This methodology has been tested on a dataset composed of 18 videos that have been annotated by four different experts. The average difference between the automatic measurement and the experts’ measures is on the acceptable range considering the high inter-observer variance.

Multi-expert analysis and validation of objective vascular tortuosity measurements

Abstract The retinal vascular tortuosity is a commonly used parameter for the early diagnosis of several diseases that affects the circulatory system. The manual analysis of fundus images for the tortuosity characterization is a time-consuming and subjective task that presents a high inter-rater variability. Thus, automatic image processing methods allow the efficient computation of objective and stable parameters for the issue. The validation of these methods is crucial to ensure an objective and reliable environment for the retinal experts. This paper describes a multi-expert analysis that measures the clinical performance as well as a validation procedure of the computational tortuosity module of the Sirius framework, a computer-aided diagnosis platform for analyzing retinal images.