000143587 001__ 143587
000143587 005__ 20240229112558.0
000143587 0247_ $$2doi$$a10.1016/j.ejca.2019.04.001
000143587 0247_ $$2pmid$$apmid:30981091
000143587 0247_ $$2ISSN$$a0014-2964
000143587 0247_ $$2ISSN$$a0959-8049
000143587 0247_ $$2ISSN$$a1879-0852
000143587 0247_ $$2ISSN$$a1879-2995
000143587 0247_ $$2altmetric$$aaltmetric:58866490
000143587 037__ $$aDKFZ-2019-01167
000143587 041__ $$aeng
000143587 082__ $$a610
000143587 1001_ $$0P:(DE-HGF)0$$aBrinker, Titus J$$b0$$eFirst author
000143587 245__ $$aDeep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task.
000143587 260__ $$aAmsterdam [u.a.]$$bElsevier$$c2019
000143587 3367_ $$2DRIVER$$aarticle
000143587 3367_ $$2DataCite$$aOutput Types/Journal article
000143587 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1576238645_12740
000143587 3367_ $$2BibTeX$$aARTICLE
000143587 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000143587 3367_ $$00$$2EndNote$$aJournal Article
000143587 520__ $$aRecent studies have successfully demonstrated the use of deep-learning algorithms for dermatologist-level classification of suspicious lesions by the use of excessive proprietary image databases and limited numbers of dermatologists. For the first time, the performance of a deep-learning algorithm trained by open-source images exclusively is compared to a large number of dermatologists covering all levels within the clinical hierarchy.We used methods from enhanced deep learning to train a convolutional neural network (CNN) with 12,378 open-source dermoscopic images. We used 100 images to compare the performance of the CNN to that of the 157 dermatologists from 12 university hospitals in Germany. Outperformance of dermatologists by the deep neural network was measured in terms of sensitivity, specificity and receiver operating characteristics.The mean sensitivity and specificity achieved by the dermatologists with dermoscopic images was 74.1% (range 40.0%-100%) and 60% (range 21.3%-91.3%), respectively. At a mean sensitivity of 74.1%, the CNN exhibited a mean specificity of 86.5% (range 70.8%-91.3%). At a mean specificity of 60%, a mean sensitivity of 87.5% (range 80%-95%) was achieved by our algorithm. Among the dermatologists, the chief physicians showed the highest mean specificity of 69.2% at a mean sensitivity of 73.3%. With the same high specificity of 69.2%, the CNN had a mean sensitivity of 84.5%.A CNN trained by open-source images exclusively outperformed 136 of the 157 dermatologists and all the different levels of experience (from junior to chief physicians) in terms of average specificity and sensitivity.
000143587 536__ $$0G:(DE-HGF)POF3-312$$a312 - Functional and structural genomics (POF3-312)$$cPOF3-312$$fPOF III$$x0
000143587 588__ $$aDataset connected to CrossRef, PubMed,
000143587 7001_ $$0P:(DE-HGF)0$$aHekler, Achim$$b1
000143587 7001_ $$aEnk, Alexander H$$b2
000143587 7001_ $$aKlode, Joachim$$b3
000143587 7001_ $$aHauschild, Axel$$b4
000143587 7001_ $$aBerking, Carola$$b5
000143587 7001_ $$aSchilling, Bastian$$b6
000143587 7001_ $$aHaferkamp, Sebastian$$b7
000143587 7001_ $$aSchadendorf, Dirk$$b8
000143587 7001_ $$0P:(DE-He78)457c042884c901eb0a02c18bb1d30103$$aHolland-Letz, Tim$$b9
000143587 7001_ $$0P:(DE-He78)a229f7724466e7efadf4a1ace1ff8af3$$aUtikal, Jochen S$$b10$$eLast author
000143587 7001_ $$0P:(DE-He78)5bacb661d5d7c0220d8f996d980ad8de$$avon Kalle, Christof$$b11$$eLast author
000143587 7001_ $$aCollaborators$$b12$$eCollaboration Author
000143587 7001_ $$aLudwig-Peitsch, Wiebke$$b13
000143587 7001_ $$aSirokay, Judith$$b14
000143587 7001_ $$aHeinzerling, Lucie$$b15
000143587 7001_ $$aAlbrecht, Magarete$$b16
000143587 7001_ $$aBaratella, Katharina$$b17
000143587 7001_ $$aBischof, Lena$$b18
000143587 7001_ $$aChorti, Eleftheria$$b19
000143587 7001_ $$aDith, Anna$$b20
000143587 7001_ $$aDrusio, Christina$$b21
000143587 7001_ $$aGiese, Nina$$b22
000143587 7001_ $$aGratsias, Emmanouil$$b23
000143587 7001_ $$aGriewank, Klaus$$b24
000143587 7001_ $$aHallasch, Sandra$$b25
000143587 7001_ $$aHanhart, Zdenka$$b26
000143587 7001_ $$aHerz, Saskia$$b27
000143587 7001_ $$aHohaus, Katja$$b28
000143587 7001_ $$aJansen, Philipp$$b29
000143587 7001_ $$aJockenhöfer, Finja$$b30
000143587 7001_ $$aKanaki, Theodora$$b31
000143587 7001_ $$aKnispel, Sarah$$b32
000143587 7001_ $$aLeonhard, Katja$$b33
000143587 7001_ $$aMartaki, Anna$$b34
000143587 7001_ $$aMatei, Liliana$$b35
000143587 7001_ $$aMatull, Johanna$$b36
000143587 7001_ $$aOlischewski, Alexandra$$b37
000143587 7001_ $$aPetri, Maximilian$$b38
000143587 7001_ $$aPlacke, Jan-Malte$$b39
000143587 7001_ $$aRaub, Simon$$b40
000143587 7001_ $$aSalva, Katrin$$b41
000143587 7001_ $$aSchlott, Swantje$$b42
000143587 7001_ $$aSody, Elsa$$b43
000143587 7001_ $$aSteingrube, Nadine$$b44
000143587 7001_ $$aStoffels, Ingo$$b45
000143587 7001_ $$aUgurel, Selma$$b46
000143587 7001_ $$aZaremba, Anne$$b47
000143587 7001_ $$aGebhardt, Christoffer$$b48
000143587 7001_ $$aBooken, Nina$$b49
000143587 7001_ $$aChristolouka, Maria$$b50
000143587 7001_ $$aBuder-Bakhaya, Kristina$$b51
000143587 7001_ $$aBokor-Billmann, Therezia$$b52
000143587 7001_ $$aEnk, Alexander$$b53
000143587 7001_ $$aGholam, Patrick$$b54
000143587 7001_ $$aHänßle, Holger$$b55
000143587 7001_ $$aSalzmann, Martin$$b56
000143587 7001_ $$aSchäfer, Sarah$$b57
000143587 7001_ $$aSchäkel, Knut$$b58
000143587 7001_ $$aSchank, Timo$$b59
000143587 7001_ $$aBohne, Ann-Sophie$$b60
000143587 7001_ $$aDeffaa, Sophia$$b61
000143587 7001_ $$aDrerup, Katharina$$b62
000143587 7001_ $$aEgberts, Friederike$$b63
000143587 7001_ $$aErkens, Anna-Sophie$$b64
000143587 7001_ $$aEwald, Benjamin$$b65
000143587 7001_ $$aFalkvoll, Sandra$$b66
000143587 7001_ $$aGerdes, Sascha$$b67
000143587 7001_ $$aHarde, Viola$$b68
000143587 7001_ $$aHauschild, Axel$$b69
000143587 7001_ $$aJost, Marion$$b70
000143587 7001_ $$aKosova, Katja$$b71
000143587 7001_ $$aMessinger, Laetitia$$b72
000143587 7001_ $$aMetzner, Malte$$b73
000143587 7001_ $$aMorrison, Kirsten$$b74
000143587 7001_ $$aMotamedi, Rogina$$b75
000143587 7001_ $$aPinczker, Anja$$b76
000143587 7001_ $$aRosenthal, Anne$$b77
000143587 7001_ $$aScheller, Natalie$$b78
000143587 7001_ $$aSchwarz, Thomas$$b79
000143587 7001_ $$aStölzl, Dora$$b80
000143587 7001_ $$aThielking, Federieke$$b81
000143587 7001_ $$aTomaschewski, Elena$$b82
000143587 7001_ $$aWehkamp, Ulrike$$b83
000143587 7001_ $$aWeichenthal, Michael$$b84
000143587 7001_ $$aWiedow, Oliver$$b85
000143587 7001_ $$aBär, Claudia Maria$$b86
000143587 7001_ $$aBender-Säbelkampf, Sophia$$b87
000143587 7001_ $$aHorbrügger, Marc$$b88
000143587 7001_ $$aKaroglan, Ante$$b89
000143587 7001_ $$aKraas, Luise$$b90
000143587 7001_ $$aFaulhaber, Jörg$$b91
000143587 7001_ $$aGeraud, Cyrill$$b92
000143587 7001_ $$aGuo, Ze$$b93
000143587 7001_ $$aKoch, Philipp$$b94
000143587 7001_ $$aLinke, Miriam$$b95
000143587 7001_ $$aMaurier, Nolwenn$$b96
000143587 7001_ $$aMüller, Verena$$b97
000143587 7001_ $$aThomas, Benjamin$$b98
000143587 7001_ $$0P:(DE-He78)a229f7724466e7efadf4a1ace1ff8af3$$aUtikal, Jochen Sven$$b99
000143587 7001_ $$aAlamri, Ali Saeed M$$b100
000143587 7001_ $$aBaczako, Andrea$$b101
000143587 7001_ $$aBerking, Carola$$b102
000143587 7001_ $$aBetke, Matthias$$b103
000143587 7001_ $$aHaas, Carolin$$b104
000143587 7001_ $$aHartmann, Daniela$$b105
000143587 7001_ $$aHeppt, Markus V$$b106
000143587 7001_ $$aKilian, Katharina$$b107
000143587 7001_ $$aKrammer, Sebastian$$b108
000143587 7001_ $$aLapczynski, Natalie Lidia$$b109
000143587 7001_ $$aMastnik, Sebastian$$b110
000143587 7001_ $$aNasifoglu, Suzan$$b111
000143587 7001_ $$aRuini, Cristel$$b112
000143587 7001_ $$aSattler, Elke$$b113
000143587 7001_ $$aSchlaak, Max$$b114
000143587 7001_ $$aWolff, Hans$$b115
000143587 7001_ $$aAchatz, Birgit$$b116
000143587 7001_ $$aBergbreiter, Astrid$$b117
000143587 7001_ $$aDrexler, Konstantin$$b118
000143587 7001_ $$aEttinger, Monika$$b119
000143587 7001_ $$aHaferkamp, Sebastian$$b120
000143587 7001_ $$aHalupczok, Anna$$b121
000143587 7001_ $$aHegemann, Marie$$b122
000143587 7001_ $$aDinauer, Verena$$b123
000143587 7001_ $$aMaagk, Maria$$b124
000143587 7001_ $$aMickler, Marion$$b125
000143587 7001_ $$aPhilipp, Biance$$b126
000143587 7001_ $$aWilm, Anna$$b127
000143587 7001_ $$aWittmann, Constanze$$b128
000143587 7001_ $$aGesierich, Anja$$b129
000143587 7001_ $$aGlutsch, Valerie$$b130
000143587 7001_ $$aKahlert, Katrin$$b131
000143587 7001_ $$aKerstan, Andreas$$b132
000143587 7001_ $$aSchilling, Bastian$$b133
000143587 7001_ $$aSchrüfer, Philipp$$b134
000143587 773__ $$0PERI:(DE-600)1468190-0$$a10.1016/j.ejca.2019.04.001$$gVol. 113, p. 47 - 54$$p47 - 54$$tEuropean journal of cancer$$v113$$x0959-8049$$y2019
000143587 909CO $$ooai:inrepo02.dkfz.de:143587$$pVDB
000143587 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b0$$kDKFZ
000143587 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b1$$kDKFZ
000143587 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)457c042884c901eb0a02c18bb1d30103$$aDeutsches Krebsforschungszentrum$$b9$$kDKFZ
000143587 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)a229f7724466e7efadf4a1ace1ff8af3$$aDeutsches Krebsforschungszentrum$$b10$$kDKFZ
000143587 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)5bacb661d5d7c0220d8f996d980ad8de$$aDeutsches Krebsforschungszentrum$$b11$$kDKFZ
000143587 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)a229f7724466e7efadf4a1ace1ff8af3$$aDeutsches Krebsforschungszentrum$$b99$$kDKFZ
000143587 9131_ $$0G:(DE-HGF)POF3-312$$1G:(DE-HGF)POF3-310$$2G:(DE-HGF)POF3-300$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lKrebsforschung$$vFunctional and structural genomics$$x0
000143587 9141_ $$y2019
000143587 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz
000143587 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000143587 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline
000143587 915__ $$0StatID:(DE-HGF)0310$$2StatID$$aDBCoverage$$bNCBI Molecular Biology Database
000143587 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bEUR J CANCER : 2017
000143587 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search
000143587 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC
000143587 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List
000143587 915__ $$0StatID:(DE-HGF)0110$$2StatID$$aWoS$$bScience Citation Index
000143587 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000143587 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded
000143587 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine
000143587 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences
000143587 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews
000143587 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bEUR J CANCER : 2017
000143587 9201_ $$0I:(DE-He78)B340-20160331$$kB340$$lTranslationale Medizinische Onkolologie$$x0
000143587 9201_ $$0I:(DE-He78)C060-20160331$$kC060$$lBiostatistik$$x1
000143587 9201_ $$0I:(DE-He78)A370-20160331$$kA370$$lKKE Dermatoonkologie$$x2
000143587 980__ $$ajournal
000143587 980__ $$aVDB
000143587 980__ $$aI:(DE-He78)B340-20160331
000143587 980__ $$aI:(DE-He78)C060-20160331
000143587 980__ $$aI:(DE-He78)A370-20160331
000143587 980__ $$aUNRESTRICTED