DVT-Net: A Multimodal Deep Vascular Topology Network for Disease Prediction

Blood vessel networks deliver nutrients, and remove waste, to maintain tissue homeostasis. Disease complications can alter vascular network morphology, which may disrupt tissue functioning. Many systemic and ocular diseases are associated with altered vessel morphology, including diabetic retinopathy (DR), glaucoma, occlusion, hypertension, and Alzheimer’s disease, suggesting their detection may have a diagnostic value. Currently, microvascular diseases are assessed by visual inspection of retinal images. Thus, comprehensive screening is not widely performed, facing challenges related to availability of human assessors. To facilitate a streamlined screening process for DR and other microvascular diseases, we developed ‘DVT-Net’ (Deep Vascular Topology Network): a novel multimodal pipeline that fuses topological summaries of segmented retinal vascular images with deep learning (DL) features for the purpose of enhancing disease detection, interpretability and accuracy. DVT-Net leverages the power of both Topological Data Analysis (TDA) and DL in identifying latent patterns in the retinal vascular network. To the best of our knowledge, this is the first method to combine TDA with DL to classify ocular and systemic disease as they manifest in the retinal vasculature.