Print Email Facebook Twitter Detection of retinal changes from illumination normalized fundus images using convolutional neural networks Title Detection of retinal changes from illumination normalized fundus images using convolutional neural networks Author Adal, K.M. (TU Delft ImPhys/Quantitative Imaging; Rotterdam Ophthalmic Institute) Van Etten, Peter G. (Rotterdam Eye Hospital) Martinez, Jose P (Rotterdam Eye Hospital) Rouwen, Kenneth (Rotterdam Eye Hospital) Vermeer, K.A. (TU Delft ImPhys/Quantitative Imaging; Rotterdam Ophthalmic Institute) van Vliet, L.J. (TU Delft ImPhys/Quantitative Imaging) Contributor Armato, Samuel G. (editor) Petrick, Nicholas A. (editor) Date 2017 Abstract Automated detection and quantification of spatio-temporal retinal changes is an important step to objectively assess disease progression and treatment effects for dynamic retinal diseases such as diabetic retinopathy (DR). However, detecting retinal changes caused by early DR lesions such as microaneurysms and dot hemorrhages from longitudinal pairs of fundus images is challenging due to intra and inter-image illumination variation between fundus images. This paper explores a method for automated detection of retinal changes from illumination normalized fundus images using a deep convolutional neural network (CNN), and compares its performance with two other CNNs trained separately on color and green channel fundus images. Illumination variation was addressed by correcting for the variability in the luminosity and contrast estimated from a large scale retinal regions. The CNN models were trained and evaluated on image patches extracted from a registered fundus image set collected from 51 diabetic eyes that were screened at two different time-points. The results show that using normalized images yield better performance than color and green channel images, suggesting that illumination normalization greatly facilitates CNNs to quickly and correctly learn distinctive local image features of DR related retinal changes. Subject Convolutional Neural Net-workDiabetic RetinopathyFundus ImagesHemorrhagesLongitudinal DR ScreeningMicroaneurysms To reference this document use: http://resolver.tudelft.nl/uuid:eb0eb773-7a31-4a78-98fa-8b225622f586 DOI https://doi.org/10.1117/12.2254342 Publisher SPIE, Bellingham, WA, USA ISBN 978-1-510607132 Source Medical Imaging 2017: Computer-Aided Diagnosis Event Medical Imaging 2017: Computer-Aided Diagnosis, 2017-02-13 → 2017-02-16, Orlando, United States Series Proceedings of SPIE, 1605-7422, 10134 Part of collection Institutional Repository Document type conference paper Rights © 2017 K.M. Adal, Peter G. Van Etten, Jose P Martinez, Kenneth Rouwen, K.A. Vermeer, L.J. van Vliet Files PDF 101341N.pdf 542.05 KB Close viewer /islandora/object/uuid:eb0eb773-7a31-4a78-98fa-8b225622f586/datastream/OBJ/view