Skip connections for medical image synthesis with generative adversarial networks

Simple item page
buir.contributor.authorMirza, Muhammad Usama
buir.contributor.authorDalmaz, Onat
buir.contributor.authorÇukur, Tolga
buir.contributor.orcidÇukur, Tolga|0000-0002-2296-851X
dc.citation.epage[4]en_US
dc.citation.spage[1]en_US
dc.contributor.authorMirza, Muhammad Usama
dc.contributor.authorDalmaz, Onat
dc.contributor.authorÇukur, Tolga
dc.coverage.spatialSafranbolu, Turkeyen_US
dc.date.accessioned2023-02-15T10:48:36Z
dc.date.available2023-02-15T10:48:36Z
dc.date.issued2022-08-29
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionConference Name: 2022 30th Signal Processing and Communications Applications Conference (SIU)en_US
dc.descriptionDate of Conference: 15-18 May 2022en_US
dc.description.abstractMagnetic 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.en_US
dc.description.provenanceSubmitted by Betül Özen (ozen@bilkent.edu.tr) on 2023-02-15T10:48:36Z No. of bitstreams: 1 Skip_Connections_for_Medical_Image_Synthesis_with_Generative_Adversarial_Networks.pdf: 875090 bytes, checksum: e4ea56b879935306452aa6c3d0055db3 (MD5)en
dc.description.provenanceMade available in DSpace on 2023-02-15T10:48:36Z (GMT). No. of bitstreams: 1 Skip_Connections_for_Medical_Image_Synthesis_with_Generative_Adversarial_Networks.pdf: 875090 bytes, checksum: e4ea56b879935306452aa6c3d0055db3 (MD5) Previous issue date: 2022-08-29en
dc.identifier.doi10.1109/SIU55565.2022.9864939en_US
dc.identifier.eisbn978-1-6654-5092-8
dc.identifier.issn2165-0608
dc.identifier.urihttp://hdl.handle.net/11693/111328
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttps://www.doi.org/10.1109/SIU55565.2022.9864939en_US
dc.source.titleSignal Processing and Communications Applications Conference (SIU)en_US
dc.subjectMedical image synthesisen_US
dc.subjectMagnetic resonance imaging (MRI)en_US
dc.subjectMulti-contrast MRIen_US
dc.subjectGenerative adversarial networken_US
dc.subjectSkip connectionsen_US
dc.titleSkip connections for medical image synthesis with generative adversarial networksen_US
dc.title.alternativeÜretken çekişmeli ağlar ile medikal görüntü sentezi için atlamalı bağlantılaren_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Skip_Connections_for_Medical_Image_Synthesis_with_Generative_Adversarial_Networks.pdf
Size:
854.58 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Scholarly Publications - Electrical and Electronics Engineering