Povilas Treigys

Automated Positioning of Overlapping Eye Fundus Images

Changes in eye fundus images can be associated with numerous vision threatening diseases such as glaucoma, optic neuropathy, swelling of the optic nerve head, or related to some systemic disease. Tracking the progress of a possible disease of the patient becomes very difficult from separated retinal images. In this article we present a method which registers two retinal images so that the fundus images overlaps each other in the best way. As a separate case, this article shows that in order to solve the optic nerve disc registration problem a linear transformation of retinal image is sufficient. A human identification possibility via retinal image registration will be disclosed as well.

A new web-based solution for modelling data mining processes

Abstract The conventional technologies and methods are not able to store and analyse recent data that come from different sources: various devices, sensors, networks, transactional applications, the web, and social media. Due to a complexity of data, data mining methods should be implemented using the capabilities of the Cloud technologies. In this paper, a new web-based solution named DAMIS, inspired by the Cloud, is proposed and implemented. It allows making massive data mining simpler, effective, and easily understandable for data scientists and business intelligence professionals by constructing scientific workflows for data mining using a drag and drop interface. The usage of scientific workflows allows composing convenient tools for modelling data mining processes and for simulation of real-world time- and resource-consuming data mining problems. The solution is useful to solve data classification, clustering, and dimensionality reduction problems. The DAMIS architecture is designed to ensure easy accessibility, usability, scalability, and portability of the solution. The proposed solution has a wide range of applications and allows to get deep insights into the data during the process of knowledge discovery.

ANALYSIS OF IRIS AND PUPIL PARAMETERS FOR STRESS RECOGNITION

The aim of this study was to automatically identify the iris and pupil of the eye in the video stream and to parameterize the identified structures in order to make assumptions if the subjected is stressed or not. During tests subjects were given a number of issues which they had to respond by selecting only one correct answer. Visual material was gathered using a helmet-fitted stationary near-infrared camera that recorded iris and pupil of the eye reactions to stimuli. Subsequently it was made an automatic iris and pupil recognition and approximation by curves in the gathered sequence of images. Each change in the pupil size is described by different time series length. Thus, it is impossible to compare the obtained data using the Euclidean distance measures. For this reason, the metrics based on periodograms was used to compare the data series. The differences calculated between the eye pupil reaction to stimuli and question show-up time was introduced in multidimensional scaling algorithms for dimension reduction. It was noticed that the stimulus to the false answers tend to cluster. DOI: http://dx.doi.org/10.5755/j01.itc.41.1.1206

Cloud Computing Approach for Intelligent Visualization of Multidimensional Data

In this paper, a Cloud computing approach for intelligent visualization of multidimensional data is proposed. Intelligent visualization enables to create visualization models based on the best practices and experience. A new Cloud computing-based data mining system DAMIS is introduced for the intelligent data analysis including data visualization methods. It can assist researchers to handle large amounts of multidimensional data when executing resource-expensive and time-consuming data mining tasks by considerably reducing the information load. The application of DAMIS is illustrated by the visual analysis of medical streaming data.

Automatization of Eye Fundus Vessel Width Measurements

Many diseases can be early detected from eye fundus images by several different features. One of the features is the artery and vein ratio. Width measurement is made on the main vessels. The aim of this automatization process is to create a fully automated method for eye fundus analysis. The fully automated system consists of blood vessel tree extraction and optic nerve disc detection in order to perform measurements at the standard place. Vessel tree extraction is complicated in some situations, so the vessel measurement algorithm is developed independently of the extracted blood vessel tree, and the tree is used only for direction enhancement and only when it is available. Vessel measurements are compared with manual measurements, performed by an expert. Automated measurements are not different from the expert’s measurements with the confidence level of 95%. For this investigation, the Optomed OY digital mobile eye fundus camera Smartscope M5 PRO was used, but the algorithm can be used on any type of eye fundus images.

Detection of the Road Pothole Contour in Raster Images

This article analyses issues related to detection and contour approximation of road surface defects, in particular road potholes, which were captured by smart device camera. Assessment of measurements obtained after image analysis and real objects will be disclosed with the view to depict measurement bias. The difference from all the other methods mentioned in the literature is that only 2D images captured by one camera were used in this investigation with the view to identify contour of road potholes and get its parameterised representation. In practice according to other authors, the most common approach to obtain parameterised description of a pothole incorporates not only cameras but also other and various sensors such as accelerometer, global positioning systems, laser, hyperspectral imagery, infrared or ultrasonic ones. In this article authors presents method that allows to recognise pothole object in terms of its colour, shape, and structure. The method discussed was applied to real world images for detection and outline road potholes contour. Finally, evaluation of approximation accuracy by empirical research techniques has be accomplished. DOI: http://dx.doi.org/10.5755/j01.itc.45.3.13446

Application of Teleophthalmology in Screening and Monitoring of Elderly Population in Rural Areas in Lithuania

A small regional telenetwork has been established in Lithuania and used for piloting homecare and remote care health care service delivery models on the grounds of the work of the Telemedicine Centre of the Lithuanian University of Health Sciences (formerly Kaunas University of Medicine) and private initiative of clinicians and researchers with the aim to promote bottom-up, self-sustainable telemedicine development and to increase accessibility to, and quality of, healthcare especially in rural or underserved areas. Stratelus, a small medical company, together with several family clinics in the rural areas of Lithuania and with support of the Family Medicine Centre of the Kaunas University of Medicine started screening and monitoring of elderly population for diabetic retinopathy, aging macular degeneration, optic nerve head evaluation, and glaucoma in their homes and near-home locations, in a mobile telenetwork mode, bringing the access point to the patient. The project demonstrated innovation in terms of the methodology (telehomecare), organization (small bottom-up structure), and technology (high quality handheld fundus camera). The argument behind this project was to test the viability of homecare and remote care service delivery in a small/medium scale, bottom-up organisational setting. This is important for elderly population with limited mobility in rural or remote areas.