001035328 001__ 1035328
001035328 005__ 20250203133239.0
001035328 0247_ $$2doi$$a10.1515/cdbme-2024-2059
001035328 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-00382
001035328 037__ $$aFZJ-2025-00382
001035328 082__ $$a570
001035328 1001_ $$0P:(DE-HGF)0$$aFonck, Simon$$b0$$eCorresponding author
001035328 245__ $$aRobustness of a DenseNet-121 for the Classification of ARDS in Chest X-Rays
001035328 260__ $$aBerlin$$bDe Gruyter$$c2024
001035328 3367_ $$2DRIVER$$aarticle
001035328 3367_ $$2DataCite$$aOutput Types/Journal article
001035328 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1736780128_16364
001035328 3367_ $$2BibTeX$$aARTICLE
001035328 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001035328 3367_ $$00$$2EndNote$$aJournal Article
001035328 520__ $$aResearch in the field of artificial intelligence (AI) in medicine is increasingly relying on algorithms based on deep learning (DL), especially for radiology. Despite producing promising results, DL models have a major drawback: their reliance on large training datasets. Especially in medicine, large, annotated datasets are hard to obtain, leading to low robustness and a performance loss when exposed to unseen, new data. To address this problem, our research evaluates how well data augmentation is able to expand the used dataset and thus improve a DL model. We employ 17 different augmentation methods to test the robustness of a DenseNet-121 trained to classify Acute Respiratory Distress Syndrome (ARDS) in chest X-rays. Our experiments show that while the model has low robustness for augmented test data when trained on unaugmented data, the general performance for ARDS classification can be improved by augmenting the training data. Overall, this demonstrates that data augmentation is beneficial in training AI models for ARDS classification in order to create more robust and generalizable models.
001035328 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001035328 536__ $$0G:(BMBF)01IS22095D$$aSDI-S - SDI-S: Smart Data Innovation Services - Experimentelle Erprobung und Entwicklung von KI-Dienstverbünden für Innovationen auf industriellen Daten (01IS22095D)$$c01IS22095D$$x1
001035328 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001035328 7001_ $$0P:(DE-Juel1)185651$$aFritsch, Sebastian$$b1$$ufzj
001035328 7001_ $$0P:(DE-HGF)0$$aNguyen, Alina$$b2
001035328 7001_ $$0P:(DE-HGF)0$$aKowalewski, Stefan$$b3
001035328 7001_ $$0P:(DE-HGF)0$$aStollenwerk, André$$b4
001035328 773__ $$0PERI:(DE-600)2835398-5$$a10.1515/cdbme-2024-2059$$gVol. 10, no. 4, p. 244 - 247$$n4$$p244 - 247$$tCurrent directions in biomedical engineering$$v10$$x2364-5504$$y2024
001035328 8564_ $$uhttps://juser.fz-juelich.de/record/1035328/files/Robustness%20of%20a%20DenseNet-121%20for%20the%20Classification%20of%20ARDS%20in%20Chest%20X-Rays.pdf$$yOpenAccess
001035328 909CO $$ooai:juser.fz-juelich.de:1035328$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001035328 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)185651$$aForschungszentrum Jülich$$b1$$kFZJ
001035328 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001035328 9141_ $$y2024
001035328 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001035328 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001035328 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2023-08-30
001035328 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2023-08-30
001035328 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-30
001035328 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-30
001035328 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-04-03T10:39:59Z
001035328 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-04-03T10:39:59Z
001035328 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2024-04-03T10:39:59Z
001035328 920__ $$lno
001035328 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001035328 9201_ $$0I:(DE-Juel1)CASA-20230315$$kCASA$$lCenter for Advanced Simulation and Analytics$$x1
001035328 980__ $$ajournal
001035328 980__ $$aVDB
001035328 980__ $$aUNRESTRICTED
001035328 980__ $$aI:(DE-Juel1)JSC-20090406
001035328 980__ $$aI:(DE-Juel1)CASA-20230315
001035328 9801_ $$aFullTexts