A Federated Machine Learning Approach for the Detection and Visualisation of Eye Diseases Using Activation Maps

Eye diseases, particularly glaucoma and cataracts, are the leading causes of visual impairment, compromising quality of life. Automatic classification of these diseases can lead to more accurate and timely diagnosis, thereby limiting their progression and complications. In recent years, advances in Deep Learning (DL) have shown promising results in the study of images in ophthalmology. However, traditional DL models are based on a centralised approach to data, sharing sensitive patient information and compromising privacy; moreover, the models are often difficult to interpret. In this paper we propose a method aimed to solve the issues of privacy and transparency in decision-making related to eye diseases detection and localisation. As a matter of fact, we consider Federated Learning (FL), an approach based on data decentralisation that enables collaborative learning between different clients and sends only the model weights to the central server. In this way, sensitive patient data are not shared, ensuring security and privacy. With regard to eye disease classification we exploit a Vision Transformer, which allows global relationships within retinal images to be highlighted, improving representation capabilities compared to traditional convolutional architectures. Furthermore, the proposed method also aims to make the model explainable using explainability techniques, in this way we make diagnostic decisions transparent. The experimental analysis shows an accuracy of 0.8480, a precision of 0.8645, a recall of 0.8477, showing the effectiveness of the proposed method on eye disease detection.