Macular Degeneration Diagnosis Using OLQCT Preprocessing, Fuzzy Segmentation, And BPN Classifier

Macular degeneration is a condition that impairs central vision. It damages the macula which is the part of the retina that is responsible for sharp, straight-ahead vision. Age-related Macular Degeneration (AMD) is a specific age-related form of macular degeneration disease. AMD is a leading cause of vision impairment worldwide, necessitating early and accurate diagnosis for effective treatment. This research proposes an advanced method namely, ‘Macular Degeneration Diagnosis using OLQCT Preprocessing, Fuzzy Segmentation, and BPN classifier (MDD_OFB)’, for AMD diagnosis by combining ‘OLQCT preprocessing’, ‘fuzzy segmentation’, and ‘Back Propagation Neural network (BPN) classifier’. The new contribution of this work is a new preprocessing module, namely ‘Macular region preprocessing using OD elimination, Log enhancement, Quantization, Contrast stretching and Thresholding (OLQCT)’ which enhances the image quality of the macula region. Fuzzy segmentation is used to segment both the macula region and the wet macular region. The BPN classifier further classifies the extracted-features to diagnose the AMD accurately. Another contribution to this research is the new framework that is designed to integrate the four modules such as OLQCT preprocessing, dual-stage FCM segmentation, feature extraction, and BPN classifier. The proposed MDD_OFB method utilizes the KFI_DB, STARE_DB, and RFMI-DB datasets, ensuring robustness across diverse cases. Experimental results demonstrate an enhanced diagnostic performance, with significant improvements in Precision, Average Accuracy, Dice Coefficient, etc., when compared to existing methods. This proposed method enhances the accuracy by 2.056% than the second-best MD_MLC method. This integrated approach offers an advanced tool for early AMD detection, providing significant advantages in clinical practices. The proposed system ensures higher accuracy, lesser time consumption, reliability, and efficiency for AMD diagnosis.