Phase quantized polar transformative with cellular automaton for early glaucoma detection

Abstract

Glaucoma is the leading cause of blindness worldwide. Glaucoma being a chronic eye disease results in irreversible loss of vision. Everyone is at danger for glaucoma. But, certain groups are greater risk. Hence, accurate Classification of normal and glaucoma images is significant one. In the screening and early detection of glaucoma, Cup to Disc Ratio (CDR) method plays a significant role. The automatic segmentation for early detection from Optimal Coherence Tomography (OCT) images is a fundamental task. Several research works based on OCT were contributed for early detection of glacuoma. However, inherent feature extraction and over fitting issues while performing early glaucoma detection have been researched by the research community for long time. In this paper, we propose Artificial Intelligence architecture, called Phase Quantized Polar Transformed Cellular Automaton (PQPT-CA) method that use the displacement gradients and distance gradients for early glaucoma detection. The proposed PQPT-CA method comprises of inherent feature extraction, robust feature segmentation and early glaucoma detection based on OCT. To start with, First Order Phase Quantization model is applied to the raw input image for extracting inherent features. Next, with the extracted features, Differential Polar Transformation is applied to generate robust segmentation map. Finally, glaucoma detection is performed for three different state employing Cellular Automaton model. The experiments show that our PQPT-CA method achieves state-of-the-art early detection on ACRIMA database. Simultaneously, the proposed method also obtains the satisfactory glaucoma screening performances with calculated diagnosis accuracy on ACRIMA database. The PQPT-CA method increases the Diagnosis Accuracy by 24% and minimizes computational time and false positive rate by 21% and 54% respectively.