Glaucoma risk assessment based on clinical data and automated nerve fiber layer defects detection

Abstract

Glaucoma is the first leading cause of vision loss in Japan, thus developing a scheme for helping glaucoma diagnosis is important. For this problem, automated nerve fiber layer defects (NFLDs) detection method was proposed, but glaucoma risk assessment using this method was not evaluated. In this paper, computerized risk assessment for having glaucoma was attempted by use of the patients' clinical information, and the performances of the NFLDs detection and the glaucoma risk assessment were compared. The clinical data includes the systemic data, ophthalmologic data, and right and left retinal images. Glaucoma risk assessment was built by using machine learning technique, which were artificial neural network, radial basis function (RBF) network, k-nearest neighbor algorithm, and support vector machine. The inputting parameter was ten clinical ones with/without the results of NFLDs detection. As a result, proposed glaucoma risk assessment showed the higher performance than the NFLD detection. The result of the glaucoma risk assessment indicates that the computerized assessment may be useful for the determination of glaucoma risk.

A study to identify limitations of existing automated systems to detect glaucoma at initial and curable stage

“…For the most part, if CDR is under 0.5, it is considered as normal while greater than 0.5 is considered as glaucomatous. [47][48][49][50][51][52] Figure 3C shows CDR of an normal eye, though Figure 3D shows CDR of a glaucoma eye.…”

Enhanced CAE system for detection of exudates and diagnosis of diabetic retinopathy stages in fundus retinal images using soft computing techniques

“…An improved model of classification using weighting techniques to select the best representative features for classifying retinal fundus image as the normal and severe image is presented in [5]. A new automatic segmentation system based on the morphological operation and thresholding is proposed in [6]. Computational Intelligence based on Fuzzy C Means clustering approach for detection of exudates and multilayer neural network classifier used for classification of exudates and non-exudates parameters in the fundus retinal images of the eye is proposed in [7].…”

“…The role of the classifier is to implement a decision rule that will indicate to which class a given pattern belongs. Some efforts have already been made to automatically predict the risk level [3][4][5][6][7][8]10,[12][13][14][15][16][17]. Risk level classification algorithms are in continuous development and improvement.…”

Glaucoma and Diabetic Retinopathy Diagnosis using Image Mining

“…Classification algorithm are concentrates on improving the prediction ability using weighting techniques and also uses image pre-processing techniques to select the best representative features to classify an image and to avoid the curse of dimensionality. "Yuji Hatanaka [3]" proposed a system to exclude blood vessel regions from potential false positives and the blood vessels were automatically segmented by using morphological operation and thresholding. The identified regions as blood vessels were interpolated by the surrounding pixels for creating "blood-vessel erased" images.…”

“…The result of abnormally high , increased pressure inside the eye over time can erode the optic nerve tissue, which may lead to vision loss or even blindness. If detected early, may be able to prevent additional vision loss [3].…”