Show simple item record

 
dc.contributorVall d'Hebron Barcelona Hospital Campus
dc.contributor.authorKushibar, Kaisar
dc.contributor.authorSalem, Mostafa
dc.contributor.authorValverde, Sergi
dc.contributor.authorRovira Cañellas, Alex
dc.contributor.authorSalvi, Joaquim
dc.contributor.authorOliver, Arnau
dc.contributor.authorLlado, Xavier
dc.date.accessioned2021-12-17T07:16:15Z
dc.date.available2021-12-17T07:16:15Z
dc.date.issued2021-04-29
dc.identifier.citationKushibar K, Salem M, Valverde S, Rovira À, Salvi J, Oliver A, et al. Transductive Transfer Learning for Domain Adaptation in Brain Magnetic Resonance Image Segmentation. Front Neurosci. 2021 Apr 29;15:608808.
dc.identifier.issn1662-453X
dc.identifier.urihttp://hdl.handle.net/11351/6704
dc.descriptionBrain; Magnetic resonance imaging; Transductive learning
dc.description.abstractSegmentation of brain images from Magnetic Resonance Images (MRI) is an indispensable step in clinical practice. Morphological changes of sub-cortical brain structures and quantification of brain lesions are considered biomarkers of neurological and neurodegenerative disorders and used for diagnosis, treatment planning, and monitoring disease progression. In recent years, deep learning methods showed an outstanding performance in medical image segmentation. However, these methods suffer from generalisability problem due to inter-centre and inter-scanner variabilities of the MRI images. The main objective of the study is to develop an automated deep learning segmentation approach that is accurate and robust to the variabilities in scanner and acquisition protocols. In this paper, we propose a transductive transfer learning approach for domain adaptation to reduce the domain-shift effect in brain MRI segmentation. The transductive scenario assumes that there are sets of images from two different domains: (1) source—images with manually annotated labels; and (2) target—images without expert annotations. Then, the network is jointly optimised integrating both source and target images into the transductive training process to segment the regions of interest and to minimise the domain-shift effect. We proposed to use a histogram loss in the feature level to carry out the latter optimisation problem. In order to demonstrate the benefit of the proposed approach, the method has been tested in two different brain MRI image segmentation problems using multi-centre and multi-scanner databases for: (1) sub-cortical brain structure segmentation; and (2) white matter hyperintensities segmentation. The experiments showed that the segmentation performance of a pre-trained model could be significantly improved by up to 10%. For the first segmentation problem it was possible to achieve a maximum improvement from 0.680 to 0.799 in average Dice Similarity Coefficient (DSC) metric and for the second problem the average DSC improved from 0.504 to 0.602. Moreover, the improvements after domain adaptation were on par or showed better performance compared to the commonly used traditional unsupervised segmentation methods (FIRST and LST), also achieving faster execution time. Taking this into account, this work presents one more step toward the practical implementation of deep learning algorithms into the clinical routine.
dc.language.isoeng
dc.publisherFrontiers Media
dc.relation.ispartofseriesFrontiers in Neuroscience;15
dc.rightsAttribution 4.0 International
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.sourceScientia
dc.subjectCervell - Imatgeria per ressonància magnètica
dc.subjectImatgeria (Tècnica)
dc.subject.meshBrain
dc.subject.mesh/diagnostic imaging
dc.subject.meshMagnetic Resonance Imaging
dc.titleTransductive Transfer Learning for Domain Adaptation in Brain Magnetic Resonance Image Segmentation
dc.typeinfo:eu-repo/semantics/article
dc.identifier.doi10.3389/fnins.2021.608808
dc.subject.decsencéfalo
dc.subject.decs/diagnóstico por imagen
dc.subject.decsimagen por resonancia magnética
dc.relation.publishversionhttps://doi.org/10.3389/fnins.2021.608808
dc.type.versioninfo:eu-repo/semantics/publishedVersion
dc.audienceProfessionals
dc.contributor.organismesInstitut Català de la Salut
dc.contributor.authoraffiliation[Kushibar K, Valverde S, Salvi J, Oliver A, Lladó X] Institute of Computer Vision and Robotics, University of Girona, Girona, Spain. [Salem M] Institute of Computer Vision and Robotics, University of Girona, Girona, Spain. Computer Science Department, Faculty of Computers and Information, Assiut University, Asyut, Egypt. [Rovira À] Unitat de Ressonància Magnètica, Servei de Radiologia, Vall d'Hebron Hospital Universitari, Barcelona, Spain
dc.identifier.pmid33994917
dc.identifier.wos000649783300001
dc.relation.projectidinfo:eu-repo/grantAgreement/ES/PE2013-2016/DPI2017-86696-R
dc.rights.accessrightsinfo:eu-repo/semantics/openAccess


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record