Influence of decoder size for binary segmentation tasks in medical imaging

Joost van der Putten; Fons van der Sommen; Peter H. N. de With

doi:10.1117/12.2542199

10 March 2020 Influence of decoder size for binary segmentation tasks in medical imaging

Joost van der Putten, Fons van der Sommen, Peter H. N. de With

Proceedings Volume 11313, Medical Imaging 2020: Image Processing; 1131318 (2020) https://doi.org/10.1117/12.2542199
Event: SPIE Medical Imaging, 2020, Houston, Texas, United States

Abstract

Symmetric design of encoder-decoder networks is common in deep learning. For almost all segmentation problems, the output segmentation is vastly less complex compared to the input image. However, the effect of the size of the decoder on segmentation performance has not been investigated in literature. This work investigates the effect of reducing decoder size on binary segmentation performance in a medical imaging application. To this end, we propose a methodology to reduce the size of the decoder in encoder-decoder networks, where residual skip connections are employed in combination with a 1x1 convolution instead of concatenations (as employed by U-Net) to achieve models with asymmetric design. The results on the ISIC2017 data set show that the amount of trainable parameters in the decoder can be reduced by up to a factor 100 compared to standard U-Net, while retaining segmentation performance. Additionally, the reduced amount of trainable decoder parameters in the proposed models leads to inference times up to 3 times faster compared to standard U-Net.

Conference Presentation

Citation Download Citation

Joost van der Putten, Fons van der Sommen, and Peter H. N. de With "Influence of decoder size for binary segmentation tasks in medical imaging", Proc. SPIE 11313, Medical Imaging 2020: Image Processing, 1131318 (10 March 2020); https://doi.org/10.1117/12.2542199

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