000274490 001__ 274490
000274490 005__ 20240229154935.0
000274490 0247_ $$2doi$$a10.3390/cancers15061820
000274490 0247_ $$2pmid$$apmid:36980707
000274490 037__ $$aDKFZ-2023-00633
000274490 041__ $$aEnglish
000274490 082__ $$a610
000274490 1001_ $$0P:(DE-He78)a49f791f44268db8fc4e1e3804d46ffd$$aSalome, Patrick$$b0$$eFirst author$$udkfz
000274490 245__ $$aMR-Class: A Python Tool for Brain MR Image Classification Utilizing One-vs-All DCNNs to Deal with the Open-Set Recognition Problem.
000274490 260__ $$aBasel$$bMDPI$$c2023
000274490 3367_ $$2DRIVER$$aarticle
000274490 3367_ $$2DataCite$$aOutput Types/Journal article
000274490 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1680157676_7806
000274490 3367_ $$2BibTeX$$aARTICLE
000274490 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000274490 3367_ $$00$$2EndNote$$aJournal Article
000274490 500__ $$a#EA:E210#LA:E210#
000274490 520__ $$aMR image classification in datasets collected from multiple sources is complicated by inconsistent and missing DICOM metadata. Therefore, we aimed to establish a method for the efficient automatic classification of MR brain sequences.Deep convolutional neural networks (DCNN) were trained as one-vs-all classifiers to differentiate between six classes: T1 weighted (w), contrast-enhanced T1w, T2w, T2w-FLAIR, ADC, and SWI. Each classifier yields a probability, allowing threshold-based and relative probability assignment while excluding images with low probability (label: unknown, open-set recognition problem). Data from three high-grade glioma (HGG) cohorts was assessed; C1 (320 patients, 20,101 MRI images) was used for training, while C2 (197, 11,333) and C3 (256, 3522) were for testing. Two raters manually checked images through an interactive labeling tool. Finally, MR-Class' added value was evaluated via radiomics model performance for progression-free survival (PFS) prediction in C2, utilizing the concordance index (C-I).Approximately 10% of annotation errors were observed in each cohort between the DICOM series descriptions and the derived labels. MR-Class accuracy was 96.7% [95% Cl: 95.8, 97.3] for C2 and 94.4% [93.6, 96.1] for C3. A total of 620 images were misclassified; manual assessment of those frequently showed motion artifacts or alterations of anatomy by large tumors. Implementation of MR-Class increased the PFS model C-I by 14.6% on average, compared to a model trained without MR-Class.We provide a DCNN-based method for the sequence classification of brain MR images and demonstrate its usability in two independent HGG datasets.
000274490 536__ $$0G:(DE-HGF)POF4-315$$a315 - Bildgebung und Radioonkologie (POF4-315)$$cPOF4-315$$fPOF IV$$x0
000274490 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de
000274490 650_7 $$2Other$$aartificial intelligence (AI)
000274490 650_7 $$2Other$$acontent-based image classification
000274490 650_7 $$2Other$$aconvolutional neural networks (CNN)
000274490 650_7 $$2Other$$adata curation and preparation
000274490 650_7 $$2Other$$adeep learning
000274490 7001_ $$0P:(DE-He78)79918c052ca39dd75a283e1a6e50a521$$aSforazzini, Francesco$$b1$$udkfz
000274490 7001_ $$aGrugnara, Gianluca$$b2
000274490 7001_ $$0P:(DE-He78)a3cba63a64575c64aa367077f673531d$$aKudak, Andreas$$b3$$udkfz
000274490 7001_ $$0P:(DE-He78)ff409202a238e135952100d1c56c9c36$$aDostal, Matthias$$b4$$udkfz
000274490 7001_ $$aHerold-Mende, Christel$$b5
000274490 7001_ $$aHeiland, Sabine$$b6
000274490 7001_ $$0P:(DE-He78)8714da4e45acfa36ce87c291443a9218$$aDebus, Jürgen$$b7$$udkfz
000274490 7001_ $$0P:(DE-He78)360c5bc2b71a849e35aca747c041dda7$$aAbdollahi, Amir$$b8$$udkfz
000274490 7001_ $$0P:(DE-He78)34ad9f967b71b1438cf5490a115c02d2$$aKnoll, Maximilian$$b9$$eLast author$$udkfz
000274490 773__ $$0PERI:(DE-600)2527080-1$$a10.3390/cancers15061820$$gVol. 15, no. 6, p. 1820 -$$n6$$p1820$$tCancers$$v15$$x2072-6694$$y2023
000274490 909CO $$ooai:inrepo02.dkfz.de:274490$$pVDB
000274490 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)a49f791f44268db8fc4e1e3804d46ffd$$aDeutsches Krebsforschungszentrum$$b0$$kDKFZ
000274490 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)79918c052ca39dd75a283e1a6e50a521$$aDeutsches Krebsforschungszentrum$$b1$$kDKFZ
000274490 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)a3cba63a64575c64aa367077f673531d$$aDeutsches Krebsforschungszentrum$$b3$$kDKFZ
000274490 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)ff409202a238e135952100d1c56c9c36$$aDeutsches Krebsforschungszentrum$$b4$$kDKFZ
000274490 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)8714da4e45acfa36ce87c291443a9218$$aDeutsches Krebsforschungszentrum$$b7$$kDKFZ
000274490 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)360c5bc2b71a849e35aca747c041dda7$$aDeutsches Krebsforschungszentrum$$b8$$kDKFZ
000274490 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)34ad9f967b71b1438cf5490a115c02d2$$aDeutsches Krebsforschungszentrum$$b9$$kDKFZ
000274490 9131_ $$0G:(DE-HGF)POF4-315$$1G:(DE-HGF)POF4-310$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lKrebsforschung$$vBildgebung und Radioonkologie$$x0
000274490 9141_ $$y2023
000274490 915__ $$0LIC:(DE-HGF)CCBYNV$$2V:(DE-HGF)$$aCreative Commons Attribution CC BY (No Version)$$bDOAJ$$d2022-01-24T07:56:58Z
000274490 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2022-11-30
000274490 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2022-11-30
000274490 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2022-11-30
000274490 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2022-11-30
000274490 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2022-11-30
000274490 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bCANCERS : 2022$$d2023-10-26
000274490 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-10-26
000274490 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-10-26
000274490 915__ $$0StatID:(DE-HGF)0320$$2StatID$$aDBCoverage$$bPubMed Central$$d2023-10-26
000274490 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2023-07-31T16:07:06Z
000274490 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2023-07-31T16:07:06Z
000274490 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2023-07-31T16:07:06Z
000274490 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2023-10-26
000274490 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2023-10-26
000274490 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-10-26
000274490 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2023-10-26
000274490 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-10-26
000274490 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bCANCERS : 2022$$d2023-10-26
000274490 9202_ $$0I:(DE-He78)E210-20160331$$kE210$$lE210 KKE Translationale Radioonkologie$$x0
000274490 9201_ $$0I:(DE-He78)E210-20160331$$kE210$$lE210 KKE Translationale Radioonkologie$$x0
000274490 9201_ $$0I:(DE-He78)HD01-20160331$$kHD01$$lDKTK HD zentral$$x1
000274490 9201_ $$0I:(DE-He78)E050-20160331$$kE050$$lE050 KKE Strahlentherapie$$x2
000274490 9200_ $$0I:(DE-He78)E210-20160331$$kE210$$lE210 KKE Translationale Radioonkologie$$x0
000274490 980__ $$ajournal
000274490 980__ $$aVDB
000274490 980__ $$aI:(DE-He78)E210-20160331
000274490 980__ $$aI:(DE-He78)HD01-20160331
000274490 980__ $$aI:(DE-He78)E050-20160331
000274490 980__ $$aUNRESTRICTED