OculusNet: Detection of Retinal Diseases Using A Tailored Web-Deployed Neural Network and Saliency Maps for Explainable AI

Muhammad Umair¹Jawad Ahmad²Oumaima Saidani³Mohammed Alshehri⁴Alanoud Al Mazroa³Muhammad Hanif^5*Rahmat Ullah⁶Muhammad Shahbaz Khan⁷

• ¹Multimedia University, Cyberjaya, Selangor Darul Ehsan, Malaysia
• ²Prince Mohammad bin Fahd University, Khobar, Saudi Arabia
• ³Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia
• ⁴Najran University, Najran, Saudi Arabia
• ⁵Örebro University, Örebro, Örebro, Sweden
• ⁶University of Essex, Colchester, East of England, United Kingdom
• ⁷Edinburgh Napier University, Edinburgh, United Kingdom

Retinal diseases are among the leading causes of blindness globally, requiring an early detection for effective treatment. Manual interpretation of ophthalmic imaging, such as Optical Coherence Tomography (OCT), is traditionally time-consuming, prone to inconsistencies, and requires specialized ophthalmic expertise. This study introduces OculusNet, an efficient and explainable Deep learning (DL) approach to detect retinal diseases using OCT images. The proposed approach is tailored specifically for complex medical image patterns in OCTs to identify retinal disorders, such as Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), and age-related macular degeneration disorder called Drusen. The proposed model benefits from Saliency Map visualization, an Explainable AI (XAI) technique, to interpret and explain how the model reached its decisions while identifying retinal disorders. Furthermore, the proposed model is deployed on a web-page, allowing users to upload retinal OCT images and receive instant detection results. This deployment demonstrates significant potential for integration into ophthalmic departments, enhancing diagnostic accuracy and efficiency. In addition, to ensure an equitable comparison, transfer learning approach has been applied on four pre-trained models,