Open AccessMulti‐level deep neural network for efficient segmentation of blood vessels in fundus images
Author(s) -
Ngo L.,
Han J.H.
Publication year - 2017
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2017.2066
Subject(s) - dropout (neural networks) , fundus (uterus) , artificial intelligence , computer science , segmentation , artificial neural network , macular degeneration , computer vision , pattern recognition (psychology) , diabetic retinopathy , deep learning , image segmentation , fundus camera , retinal , ophthalmology , medicine , machine learning , ophthalmoscopy , diabetes mellitus , endocrinology
The exact blood vessel trees segmented from fundus images provide important information required for screening and following‐up of diabetic retinopathy and age‐related macular degeneration. The trained deep neural network presents an automated prediction of the blood vessels in retinal fundus camera images in the publicly DRIVE database with accuracy up to 0.9533 and area under the receiver operating characteristic curve up to 0.9752, which is better than manual recognition by expert human eyes. A resizing technique is introduced and applied to the multi‐level network combining dropout and spatial‐dropout layers to obtain more generalised training. The proposed model has the potential for the classification of other types of images.