Classification of Glaucoma Stages Using Image Empirical Mode Decomposition from Fundus Images

One of the most prevalent causes of visual loss and blindness is glaucoma. Conventionally, instrument-based tools are employed for glaucoma screening. However, they are inefficient, time-consuming, and manual. Hence, computerized methodologies are needed for fast and accurate diagnosis of glaucoma. Therefore, we proposed a Computer-Aided Diagnosis (CAD) method for the classification of glaucoma stages using Image Empirical Mode decomposition (IEMD). In this study, IEMD is applied to decompose the preprocessed fundus photographs into different Intrinsic Mode Functions (IMFs) to capture the pixel variations. Then, the significant texture-based descriptors have been computed from the IMFs. A dimensionality reduction approach called Principal Component Analysis (PCA) has been employed to pick the robust descriptors from the retrieved feature set. We used the Analysis of Variance (ANOVA) test for feature ranking. Finally, the LS-SVM classifier has been employed to classify glaucoma stages. The proposed CAD system achieved a classification accuracy of 94.45% for the binary classification on the RIM-ONE r12 database. Our approach demonstrated better glaucoma classification performance than the existing automated systems.

Automated summary

In this study, a Computer-Aided Diagnosis (CAD) method using Image Empirical Mode Decomposition (IEMD) was proposed for the classification of glaucoma stages. The preprocessed fundus photographs were decomposed into different Intrinsic Mode Functions (IMFs) to capture the pixel variations, and significant texture-based descriptors were computed from the IMFs. Dimensionality reduction using Principal Component Analysis (PCA) and feature ranking using Analysis of Variance (ANOVA) were employed. The LS-SVM classifier was used for glaucoma stage classification, achieving a high classification accuracy of 94.45% on the RIM-ONE r12 database.