Skip connections for medical image synthesis with generative adversarial networks

Date

2022-08-29

Authors

Mirza, Muhammad Usama
Dalmaz, Onat
Çukur, Tolga

Editor(s)

Advisor

Supervisor

Co-Advisor

Co-Supervisor

Instructor

BUIR Usage Stats
3
views
43
downloads

Citation Stats

Series

Abstract

Magnetic Resonance Imaging (MRI) is an imaging technique used to produce detailed anatomical images. Acquiring multiple contrast MRI images requires long scan times forcing the patient to remain still. Scan times can be reduced by synthesising unacquired contrasts from acquired contrasts. In recent years, deep generative adversarial networks have been used to synthesise contrasts using one-to-one mapping. Deeper networks can solve more complex functions, however, their performance can decline due to problems such as overfitting and vanishing gradients. In this study, we propose adding skip connections to generative models to overcome the decline in performance with increasing complexity. This will allow the network to bypass unnecessary parameters in the model. Our results show an increase in performance in one-to-one image synthesis by integrating skip connections.

Source Title

Signal Processing and Communications Applications Conference (SIU)

Publisher

IEEE

Course

Other identifiers

Book Title

Degree Discipline

Degree Level

Degree Name

Citation

Published Version (Please cite this version)

Language

English

Type

Conference Paper