Survey on Diagnosing Retina Diseases in Optical Coherence Tomography Images Based on Deep Learning

Source abstract

This study provides a comprehensive and extensive review of the use of deep learning techniques in diagnosing a variety of retinal diseases, such as Drusen, choroidal neovascularization (CNV), and diabetic macular edema (DME) using optical coherence tomography images (OCT). The research reviews the different models used in this field and evaluates their effectiveness, robustness, and reliability in distinguishing and diagnosing retinal diseases with high accuracy. The research analyzes the most effective and most widely used models in this field, focusing on the results achieved in terms of accuracy and reliability, highlighting the methods that showed the best performance in diagnosis, and improving and developing them in the future to achieve better results. The specialized data sets used to train and test these models are also reviewed, with an assessment of their role and importance in promoting and supporting scientific research in this field. Furthermore, the paper discusses recent advances in research that have been achieved in recent years. In addition, the research addresses current research gaps and challenges facing researchers and provides a comprehensive vision of future work that can contribute to the further development of this field. One of the topics that the research aims for is the importance of using deep learning techniques in the medical field to enhance the accuracy and speed of diagnosis. The research concludes by providing recommendations on future directions that research in this field can take, with the aim of achieving sustainable progress and improving the quality of healthcare for patients with retinal diseases using deep learning techniques