Publication Date: 2023/11/18
Abstract: Central Serous Retinopathy (CSR) is a retinal disease that results in blindness and visual loss. The accumulation of watery fluid behind the retina causes the CSR. Detection and prevention of CSR disease is desirable, it helpsto take preventive measures to avoid and overcome any damages to the human eye. For the purpose of detecting CSR disease and analyzing the results 2 imaging approaches are used. Optical Coherence Tomography Angiography (OCT), Fundus Imaging are the two imaging (dataset) techniques used in this work. Before classification of the input dataset pre- preparation of the image dataset plays an important role classification using machine learning methods. Image processing increases the accuracy in detection of disease. The preprocessing stage in our proposed system consists of four main phases, namely noise removal, gray-scale conversion, median filtering, and data transformation. Data transformation in the proposed system consists of five image transformation steps such as random horizontal flip, random rotation, random resizing, transforming to tensor and normalizing the data.
Keywords: Central Serous Retinopathy (CSR), OCT and Fundus imaging.
DOI: https://doi.org/10.5281/zenodo.10153576
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT23AUG599.pdf
REFERENCES