Glaucoma Detection using Mask Region-Based Convolutional Neural Networks

Abstract

Glaucoma is a disease that impairs the vision of the human eyes, and it has grown increasingly common in recent years due to increased pressure in the eyes. It is the result of this disease, which is fatal once it has shown itself, that vision loss occurs. The identification of glaucoma disease has already been achieved via several deep learning (DL) algorithms, as previously stated. The findings of our research on the detection of glaucoma sickness in this paper, in which model used a deep learning technique known as a Convolutional neural network to detect the illness (CNN). The Mask Region-Based convolutional neural network (Mask-RCNN) presents a unique pattern for glaucoma and non-glaucoma affected eyes, which work may utilize to detect glaucoma using machine learning techniques. In this study, the usage of Mask-RCNN is used to create a hierarchical structure for differentiating between images of glaucoma affected and non-affected eyes, allowing for a more accurate categorization of glaucoma patients. With our proposed method may evaluate at six different degrees of complexity and 33 convolutional layers. When detecting glaucoma disease, the proposed research uses the dropout mechanism to enhance the overall efficacy of the performance, as described above. The SCES and ORIGA datasets were used in this research to analyze the intended work, and the results were presented in this paper. The Accuracy of RCNN on the ORIGA dataset was 92.32 percent, Faster-RCNN was 93.89 percent, and Mask RCNN was 95.72 percent, according to the values obtained. When applied to the SCES dataset, the results showed that the Accuracy of the RCNN was 91.56 percent, that of the Faster-RCNN was 94.32 percent, and that of Mask RCNN was 97.56 percent. The mAP of RCNN was 89 percent, Faster-RCNN was 92 percent, and Mask RCNN was 90 percent. mAP of RCNN is 90 percent, Faster-RCNN is 91 percent, and Mask RCNN is 93 percent, according to the results.