Article,

Glaucoma Images Classification Using Fuzzy Min-Max Neural Network Based on Data-Core

, and .
International Journal of Innovative Science and Modern Engineering (IJISME), 1 (7): 9-15 (June 2013)

Abstract

Glaucoma is the major cause of blindness in worldwide. It is an ophthalmologist disease characterized by an increase in Intraocular Pressure (IOP). The types of glaucoma are primary open angle or chronic glaucoma (POAG) and closed angle (or) acute glaucoma (CAG) which causes a slow (or) rapid rise in Intraocular Pressure (IOP). The iridocorneal angle between the iris and the cornea is the key used to differentiate OAG and CAG. The stratus Anterior Optical Coherence Tomography (AS-OCT) images with these diseases are detected and classified from the normal images using the proposed fuzzy min-max neural network based on Data-Core (DCFMN). Data-core fuzzy min-max neural network (DCFMN) has strong robustness and high accuracy in classification. DCFMN contains two classes of neurons: classifying neurons (CNs) and overlapping neurons (OLNs).CNs are used to classify the patterns of data. The OLN can handle all kinds of overlap in different hyper boxes. A new type of membership function considering the characteristics of data and the influence of noise is designed for CNs in the DCFMN. The membership function of Overlapping Neurons (OLNs) deals with the relative position of data in the hyper boxes. This algorithm is performed on a batch of 39 anterior segmentOptical Coherence Tomography (AS-OCT) images obtained from the Vasan Eye Care Hospital, Chennai. The performance of the proposed system is excellent and a classification rate of 97% is achieved. Hence using this neural network, the performance of classification of normal or abnormal (glaucoma affected images) is improved. This method also reduces the time taken for the diagnosis by the ophthalmologist.

Tags

Users

  • @ijisme_beiesp

Comments and Reviewsshow / hide

  • @ijisme_beiesp
    3 years ago (last updated 3 years ago)
    good
Please log in to take part in the discussion (add own reviews or comments).