Detection of retinal changes from illumination normalized fundus images using convolutional neural networks

Kedir M. Adal, Peter G. Van Etten, Jose P Martinez, Kenneth Rouwen, Koenraad A. Vermeer, Lucas J. Van Vliet

    Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

    2 Citations (Scopus)
    55 Downloads (Pure)


    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.

    Original languageEnglish
    Title of host publicationMedical Imaging 2017: Computer-Aided Diagnosis
    EditorsSamuel G. Armato, Nicholas A. Petrick
    Place of PublicationBellingham, WA, USA
    Number of pages6
    ISBN (Electronic)978-1-510607132
    Publication statusPublished - 2017
    EventMedical Imaging 2017: Computer-Aided Diagnosis - Orlando, United States
    Duration: 13 Feb 201716 Feb 2017

    Publication series

    NameProceedings of SPIE
    ISSN (Electronic)1605-7422


    ConferenceMedical Imaging 2017: Computer-Aided Diagnosis
    CountryUnited States


    • Convolutional Neural Net-work
    • Diabetic Retinopathy
    • Fundus Images
    • Hemorrhages
    • Longitudinal DR Screening
    • Microaneurysms

    Fingerprint Dive into the research topics of 'Detection of retinal changes from illumination normalized fundus images using convolutional neural networks'. Together they form a unique fingerprint.

    Cite this