Early Detection of Retinitis Pigmentosa

Retinitis pigmentosa (RP) is a debilitating inherited retinal disorder that affects a significant number of individuals worldwide. Existing diagnostic methods have limitations in detecting early-stage RP and they highlight the need for using additional imaging modalities. In this paper, a groundbreaking approach for RP diagnosis is proposed using three imaging modalities and a CNN-based classification model achieving 97.7% accuracy. The proposed model demonstrates superior performance compared to previous work as it achieves higher accuracy. A segmentation model was also proposed to segment pigment spots and provide doctors with effective monitoring of the disease. The proposed segmentation model outperforms previously used methods by achieving 99.61% accuracy and higher values in most of the performance metrics, including specificity, precision, and Area Under Curve (AUC). The Segmentation and classification models were integrated into a web application providing a user-friendly and intuitive tool for RP diagnosis and paving the way for more accessible and effective diagnostic tools. This innovative approach democratizes healthcare by making RP diagnosis affordable and accessible to more people and improving the speed of clinical decision-making.