A smart intraocular pressure risk assessment framework using frontal eye image analysis

Abstract

Intraocular pressure (IOP) in general refers to the pressure in the eyes. Gradual increase of IOP and high IOP are conditions/symptoms that may lead to certain diseases such as glaucoma and therefore must be closely monitored. While the pressure in the eye increases, different parts of the eye may become affected until the eye parts are damaged. An effective way to prevent rise in eye pressure is by early detection. A new smart healthcare framework is presented to evaluate the intraocular pressure risk from frontal eye images. The framework monitors the status of IOP risk by analyzing frontal eye images using image processing and machine learning techniques. A database of images collected from Princess Basma Hospital in Jordan was used in this work. The database contains 400 eye images: 200 images with normal IOP and 200 high eye pressure case images. The framework extracts five features from the frontal eye image: the pupil and iris diameter ratio, mean redness level of the sclera, red area percentage of the sclera, and two other features measured from the extracted contour of the sclera (contour height and contour area). Once the features were extracted, a neural network is trained and tested to obtain the status of the patients in terms of eye pressure. The framework detects the status of IOP (normal or high IOP) and produces evidence of the relationship between the five extracted frontal eye image features and IOP, which has not been previously investigated through automated image processing and machine learning techniques using frontal eye images.

Automated Vision-Based High Intraocular Pressure Detection Using Frontal Eye Images

“…Vision-based approaches such as image processing and machine learning techniques have been used to assist in detecting high eye pressure symptoms that may lead to Glaucoma. This research has been built on top of the preliminary data found in [13], [14], [46], [47] to assist clinicians and patients for early screening of IOP.…”

“…Building over our work in [13], [14], this research studies several algorithms and certain algorithms are selected to direct this research to be automated such that it can eventually be applied on smart-phones. The main contributions of the proposed work can be specified in the following points: Proposing a new framework to help both ophthalmologists and high IOP candidates in the initial diagnosis of IOP early-on, as it is the most effective approach to prevent full or partial IOP/Glaucoma based vision loss.Introducing a novel vision-based architecture, structure and features for initial IOP screening using frontal eye images.…”

Eye-SCOR: A Supply Chain Operations Reference-Based Framework for Smart Eye Status Monitoring Using System Dynamics Modeling

“…Figure 2 illustrates our proposed causal model for the Eye-SCOR framework. The factors deemed most important for Eye-SCOR have been selected as a result of comprehensively reviewing the literature related to causal models for healthcare applications [9] and specifically eye status monitoring systems [20,21]. The model carries hypothesized information among the factors and their inter-relationships.…”

“…Automated decision support frameworks for smart healthcare monitoring rely on artificial intelligence (AI)-assisted models using machine/deep learning and/or signal/image processing, as well as data analysis techniques applied to the acquired digital health data. Examples include techniques monitoring heart status using electrocardiogram (ECG) signal [12], brain and mental status from electroencephalogram (EEG) signal [13,14], breathing and respiratory status from breathing sounds [15][16][17][18], skin lesion analysis from images [19], eye disease determination [7,[20][21][22][23][24], and so on, some of which have been translated into smartphone apps [10,25].…”

“…Many researchers have proposed several works for IOP and glaucoma detection and analysis of the eye from images. However, there is a lack of studies regarding IOP based on frontal eye images in the computer vision field [20,21]. Most prior related work either focuses on fundus/optic disc images or requires additional hardware sensors for eye blood vessel detection, pupil/Iris detection, and/or eye redness determination.…”