Deep semantic segmentation of Diabetic Retinopathy lesions: what metrics really tell us

Pedro Furtado

doi:10.1117/12.2549221

3 March 2020 Deep semantic segmentation of Diabetic Retinopathy lesions: what metrics really tell us

Pedro Furtado

Author Affiliations +

Proceedings Volume 11317, Medical Imaging 2020: Biomedical Applications in Molecular, Structural, and Functional Imaging; 113170O (2020) https://doi.org/10.1117/12.2549221
Event: SPIE Medical Imaging, 2020, Houston, Texas, United States

Abstract

Segmentation of lesions in eye fundus images (EFI) is a difficult problem, due to small sizes, varying morphologies, similarities and lack of contrast. Today, deep learning segmentation architectures are state-of-the-art in most segmentation tasks. But metrics need to be interpreted adequately to avoid wrong conclusions, e.g. we show that 90% global accuracy of the Fully Convolutional Network (FCN) does not mean it segments lesions very well. In this work we test and compare deep segmentation networks applied to find lesions in the Eye Fundus Images, focusing on comparison and how metrics really should be interpreted to avoid mistakes and why. In the light of this analysis, we finalize by discussing further challenges that lie ahead.

Conference Presentation

Citation Download Citation

Pedro Furtado "Deep semantic segmentation of Diabetic Retinopathy lesions: what metrics really tell us", Proc. SPIE 11317, Medical Imaging 2020: Biomedical Applications in Molecular, Structural, and Functional Imaging, 113170O (3 March 2020); https://doi.org/10.1117/12.2549221

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE