Show simple item record

GraphXCOVID: Explainable Deep Graph Diffusion Pseudo-Labelling for Identifying COVID-19 on Chest X-rays

hal.structure.identifierDepartment of Applied Mathematics and Theoretical Physics [DAMTP]
dc.contributor.authorAVILES-RIVERO, Angelica I
hal.structure.identifierDepartment of Applied Mathematics and Theoretical Physics [DAMTP]
dc.contributor.authorSELLARS, Philip
hal.structure.identifierDepartment of Applied Mathematics and Theoretical Physics [DAMTP]
dc.contributor.authorSCHÖNLIEB, Carola-Bibiane
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorPAPADAKIS, Nicolas
dc.date2022
dc.date.accessioned2024-04-04T02:49:20Z
dc.date.available2024-04-04T02:49:20Z
dc.date.issued2022
dc.identifier.issn0031-3203
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/191815
dc.description.abstractEnCan one learn to diagnose COVID-19 under extreme minimal supervision? Since the outbreak of the novel COVID-19 there has been a rush for developing Artificial Intelligence techniques for expert-level disease identification on Chest X-ray data. In particular, the use of deep supervised learning has become the go-to paradigm. However, the performance of such models is heavily dependent on the availability of a large and representative labelled dataset. The creation of which is a heavily expensive and time consuming task, and especially imposes a great challenge for a novel disease. Semi-supervised learning has shown the ability to match the incredible performance of supervised models whilst requiring a small fraction of the labelled examples. This makes the semi-supervised paradigm an attractive option for identifying COVID-19. In this work, we introduce a graph based deep semi-supervised framework for classifying COVID-19 from chest X-rays. Our framework introduces an optimisation model for graph diffusion that reinforces the natural relation among the tiny labelled set and the vast unlabelled data. We then connect the diffusion prediction output as pseudo-labels that are used in an iterative scheme in a deep net. We demonstrate, through our experiments, that our model is able to outperform the current leading supervised model with a tiny fraction of the labelled examples. Finally, we provide attention maps to accommodate the radiologist's mental model, better fitting their perceptual and cognitive abilities. These visualisation aims to assist the radiologist in judging whether the diagnostic is correct or not, and in consequence to accelerate the decision.
dc.language.isoen
dc.publisherElsevier
dc.title.enGraphXCOVID: Explainable Deep Graph Diffusion Pseudo-Labelling for Identifying COVID-19 on Chest X-rays
dc.typeArticle de revue
dc.identifier.doi10.1016/j.patcog.2021.108274
dc.subject.halInformatique [cs]/Traitement du signal et de l'image
dc.identifier.arxiv2010.00378
dc.description.sponsorshipEuropeNonlocal Methods for Arbitrary Data Sources
bordeaux.journalPattern Recognition
bordeaux.page108274
bordeaux.volume122
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.peerReviewedoui
hal.identifierhal-02957465
hal.version1
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-02957465v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Pattern%20Recognition&rft.date=2022&rft.volume=122&rft.spage=108274&rft.epage=108274&rft.eissn=0031-3203&rft.issn=0031-3203&rft.au=AVILES-RIVERO,%20Angelica%20I&SELLARS,%20Philip&SCH%C3%96NLIEB,%20Carola-Bibiane&PAPADAKIS,%20Nicolas&rft.genre=article


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record