Suchergebnisse

Although unprecedented sensitivity and specificity values are reported, recent glaucoma detection deep learning models lack in decision transparency. Here, we propose a methodology that advances explainable deep learning in the field of glaucoma detection and vertical cup-disc ratio (VCDR), an important risk factor. We trained and evaluated deep learning models using fundus images that underwent a certain cropping policy. We defined the crop radius as a percentage of image size, centered on the optic nerve head (ONH), with an equidistant spaced range from 10-60% (ONH crop policy). The inverse of the cropping mask was also applied (periphery crop policy). Trained models using original images resulted in an area under the curve (AUC) of 0.94 [95% CI 0.92-0.96] for glaucoma detection, and a coefficient of determination (R-2) equal to 77% [95% CI 0.77-0.79] for VCDR estimation. Models that were trained on images with absence of the ONH are still able to obtain significant performance (0.88 [95% CI 0.85-0.90] AUC for glaucoma detection and 37% [95% CI 0.35-0.40] R-2 score for VCDR estimation in the most extreme setup of 60% ONH crop). Our findings provide the first irrefutable evidence that deep learning can detect glaucoma from fundus image regions outside the ONH. ; Research Group Ophthalmology, KU Leuven; VITO NV; Flemish Government; European Commission

In this study, we report the results of a comprehensive phenotyping of the retina of the App(NL-G-F) mouse. We demonstrate that soluble A beta accumulation is present in the retina of these mice early in life and progresses to A beta plaque formation by midlife. This rising A beta burden coincides with local microglia reactivity, astrogliosis, and abnormalities in retinal vein morphology. Electrophysiological recordings revealed signs of neuronal dysfunction yet no overt neurodegeneration was observed and visual performance outcomes were unaffected in the App(NL-G-F) mouse. Furthermore, we show that hyperspectral imaging can be used to quantify retinal A beta, underscoring its potential as a biomarker for AD diagnosis and monitoring. These findings suggest that the App(NL-G-F) retina mimics the early, preclinical stages of AD, and, together with retinal imaging techniques, offers unique opportunities for drug discovery and fundamental research into preclinical AD. ; MV, LV, LuM and LDG are fellows of the Research Foundation Flanders (FWO). This research was supported by the Alzheimer's Research Foundation (SAO-FRA), the European Union Horizon 2020 Research and Innovation Program (2014-2020) (HERALD project, granted by the ATTRAC T consortium). The Centre for Eye Research Australia receives Operational Infrastructure Support from the Victorian Government. XH and PvW acknowledge funding support from the H & L Hecht Trust and the Yulgilbar Alzheimer's Research Program. ; De Groef, L (corresponding author), Univ Leuven KU Leuven, Dept Biol, Neural Circuit Dev & Regenerat Res Grp, Naamsestr 61,Box 2464, B-3000 Leuven, Belgium. Lies.Degroef@kuleuven.be