Fusion learning methods for the age-related macular degeneration diagnosis based on multiple sources of ophthalmic digital images
Han Wang, Junjie Zhou, Chengde Huang, Zhoujie Tang, Xiangrong Yu, Guanghui Hou, Jie Yang, Qingting Yuan, Kelvin Kam Lung Chong, Lina Huang
Abstract
Age-related Macular Degeneration (AMD) is one of the major causes of elders’ vision losses, and therefore its early screening and treatment are the most efficient way to reduce the risk of blindness. AI-based methods based on ophthalmic images have great potential for AMD diagnosis. However, low levels of accuracy, robustness, and explainability are challenges for AI approaches to be clinically applied. Traditionally unsupervised methods (Hierarchical Clustering and K-Means) and supervised methods (SVM, VGG-16, and ResNet), are used for AI-based AMD detection using different image datasets. However, single data sources and single models are not able to reflect the real data distribution, thus leading to low accuracy and robustness. Thus, this study proposes a multi-data source fusion method and a multi-model fusion approach for detecting AMD. Based on Optical Coherence Tomography (OCT), Fundus Autofluorescence (FAF), regular color fundus photography (CFP), and Ultra-Wide field Fundus (UWF) images, the multi-data source fusion method preprocesses and enhances each type of data, extracts features using unsupervised ML models, combines and normalizes them, and learns a model using a multi-layer perception (MLP) algorithm. The multi-model fusion method builds the model using different supervised machine learning and deep learning algorithms and adopts a voting mechanism for the model selection and optimization. Findings show that the proposed methods achieve higher accuracy and robustness than the traditional methods.