Experiments with loss function for improvement of multi-class segmentation of diabetic retinopathy lesions

Pedro Furtado

doi:10.1117/12.2599508

30 June 2021 Experiments with loss function for improvement of multi-class segmentation of diabetic retinopathy lesions

Pedro Furtado

Proceedings Volume 11878, Thirteenth International Conference on Digital Image Processing (ICDIP 2021); 118780M (2021) https://doi.org/10.1117/12.2599508
Event: Thirteenth International Conference on Digital Image Processing, 2021, Singapore, Singapore

Abstract

Deep learning is increasingly used in every medical imaging segmentation task, but detection of lesions from eye fundus images (EFI) poses many difficult challenges related to sizes, similarity with other lesions and structures, low contrasts, variant conformations. During training, the loss function directs backpropagation learning in the deep convolutional neural networks (DCNN) that are used. It is therefore a fundamental function to the optimization procedure. There exist alternative formulations, such as cross entropy, jaccard and dice. But does the choice of loss influence quality decisively, in the difficult context of EFI lesions? And what about the network architecture? As part of our effort to improve the approaches, we evaluate alternative loss functions, also alternative architectures. We show that the choice of a convenient architecture and loss function can double the quality detecting some of the small and difficult to detect lesions, but we also show that research is still required to find ways to improve the results further.

Citation Download Citation

Pedro Furtado "Experiments with loss function for improvement of multi-class segmentation of diabetic retinopathy lesions", Proc. SPIE 11878, Thirteenth International Conference on Digital Image Processing (ICDIP 2021), 118780M (30 June 2021); https://doi.org/10.1117/12.2599508

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

Includes PDF, HTML & Video, when available