Neovascularization Detection in Diabetic Retinopathy from Fluorescein Angiograms

Benjamin Béouche-Hélias (1) , David Helbert (2, 3) , Cynthia de Malézieu (1) , Nicolas Leveziel (1) , Christine Fernandez-Maloigne (2, 3)

1 CHU de Poitiers [La Milétrie] - Centre hospitalier universitaire de Poitiers = Poitiers University Hospital
2 XLIM-ASALI - Synthèse et analyse d'images
3 UP - Université de Poitiers = University of Poitiers

Even if a lot of work has been done on Optical Coherence Tomography (OCT) and color images in order to detect and quantify diseases such as diabetic retinopathy, exudates or neovascularizations, none of them is able to evaluate the diffusion of the neovascularizations in retinas. Our work has been to develop a tool able to quantify a neo-vascularization and the fluorescein leakage during an angiography. The proposed method has been developed following a clinical trial protocol, images are taken by a Spectralis (Heidelberg Engineering). Detections are done using a supervised classification using specific features. Images and their detected neovascularizations are then spatially matched by an image registration.We compute the expansion speed of the liquid that we call diffusion index. This last one specifies the state of the disease and permits to indicate the activity of neovascularizations and allows a follow-up of patients. The method proposed in this paper has been built to be robust, even with laser impacts, to compute a diffusion index.

Mots clés: diabetes; Diabetic retinopathy; neovascularization; classification; anti-VEGF

Domaines: Imagerie; Imagerie médicale; Traitement du signal et de l'image [eess.SP]; Organes des sens

Benjamin Béouche-Hélias, David Helbert, Cynthia de Malézieu, Nicolas Leveziel, Christine Fernandez-Maloigne. Neovascularization Detection in Diabetic Retinopathy from Fluorescein Angiograms. Journal of Medical Imaging, 2017, 4 (4), pp.044503. ⟨10.1117/1.JMI.4.4.044503⟩. ⟨hal-01625993⟩