Exploring the future of diabetic retinopathy classification: A roadmap from deep learning to quantum computing
Abstract
Diabetic Retinopathy (DR) is one of the leading causes of blindness worldwide. The current technological advancements, such as machine learning and deep learning, significantly enhance the detection of DR. However, the further development of early and accurate diagnostic procedures remains essential to preserve human vision. To support this, the development of deep learning models applied to retinal image analysis has substantially improved the detection and classification accuracy of DR. Especially, transfer learning with pre-trained networks drastically tapers the need for massive, labelled datasets by eliminating the high computational requirements. On the other hand, quantum computing can handle vast datasets by fine-tuning the existing models in less time compared to classical computing. By keeping the above points as a roadmap, this review provides an extensive summary of diagnostic and classification methods for DR. Moreover, this exhaustive review procedure has been performed as a catwalk through machine learning, deep learning, transfer learning, and quantum computing by analyzing their pros and cons. The outcome of the review emphasises that these interdisciplinary strategies have the potential to pioneer a change in DR classification, providing world-class patient care if the technologies are integrated as required. Also, it opened the gateway for future research avenues that will focus on creating hybrid models that harness the advantages of these technologies, as well as the investigation of novel quantum algorithms designed explicitly for DR image analysis.