001     143587
005     20240229112558.0
024 7 _ |a 10.1016/j.ejca.2019.04.001
|2 doi
024 7 _ |a pmid:30981091
|2 pmid
024 7 _ |a 0014-2964
|2 ISSN
024 7 _ |a 0959-8049
|2 ISSN
024 7 _ |a 1879-0852
|2 ISSN
024 7 _ |a 1879-2995
|2 ISSN
024 7 _ |a altmetric:58866490
|2 altmetric
037 _ _ |a DKFZ-2019-01167
041 _ _ |a eng
082 _ _ |a 610
100 1 _ |a Brinker, Titus J
|0 P:(DE-HGF)0
|b 0
|e First author
245 _ _ |a Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task.
260 _ _ |a Amsterdam [u.a.]
|c 2019
|b Elsevier
336 7 _ |a article
|2 DRIVER
336 7 _ |a Output Types/Journal article
|2 DataCite
336 7 _ |a Journal Article
|b journal
|m journal
|0 PUB:(DE-HGF)16
|s 1576238645_12740
|2 PUB:(DE-HGF)
336 7 _ |a ARTICLE
|2 BibTeX
336 7 _ |a JOURNAL_ARTICLE
|2 ORCID
336 7 _ |a Journal Article
|0 0
|2 EndNote
520 _ _ |a Recent 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.
536 _ _ |a 312 - Functional and structural genomics (POF3-312)
|0 G:(DE-HGF)POF3-312
|c POF3-312
|f POF III
|x 0
588 _ _ |a Dataset connected to CrossRef, PubMed,
700 1 _ |a Hekler, Achim
|0 P:(DE-HGF)0
|b 1
700 1 _ |a Enk, Alexander H
|b 2
700 1 _ |a Klode, Joachim
|b 3
700 1 _ |a Hauschild, Axel
|b 4
700 1 _ |a Berking, Carola
|b 5
700 1 _ |a Schilling, Bastian
|b 6
700 1 _ |a Haferkamp, Sebastian
|b 7
700 1 _ |a Schadendorf, Dirk
|b 8
700 1 _ |a Holland-Letz, Tim
|0 P:(DE-He78)457c042884c901eb0a02c18bb1d30103
|b 9
700 1 _ |a Utikal, Jochen S
|0 P:(DE-He78)a229f7724466e7efadf4a1ace1ff8af3
|b 10
|e Last author
700 1 _ |a von Kalle, Christof
|0 P:(DE-He78)5bacb661d5d7c0220d8f996d980ad8de
|b 11
|e Last author
700 1 _ |a Collaborators
|b 12
|e Collaboration Author
700 1 _ |a Ludwig-Peitsch, Wiebke
|b 13
700 1 _ |a Sirokay, Judith
|b 14
700 1 _ |a Heinzerling, Lucie
|b 15
700 1 _ |a Albrecht, Magarete
|b 16
700 1 _ |a Baratella, Katharina
|b 17
700 1 _ |a Bischof, Lena
|b 18
700 1 _ |a Chorti, Eleftheria
|b 19
700 1 _ |a Dith, Anna
|b 20
700 1 _ |a Drusio, Christina
|b 21
700 1 _ |a Giese, Nina
|b 22
700 1 _ |a Gratsias, Emmanouil
|b 23
700 1 _ |a Griewank, Klaus
|b 24
700 1 _ |a Hallasch, Sandra
|b 25
700 1 _ |a Hanhart, Zdenka
|b 26
700 1 _ |a Herz, Saskia
|b 27
700 1 _ |a Hohaus, Katja
|b 28
700 1 _ |a Jansen, Philipp
|b 29
700 1 _ |a Jockenhöfer, Finja
|b 30
700 1 _ |a Kanaki, Theodora
|b 31
700 1 _ |a Knispel, Sarah
|b 32
700 1 _ |a Leonhard, Katja
|b 33
700 1 _ |a Martaki, Anna
|b 34
700 1 _ |a Matei, Liliana
|b 35
700 1 _ |a Matull, Johanna
|b 36
700 1 _ |a Olischewski, Alexandra
|b 37
700 1 _ |a Petri, Maximilian
|b 38
700 1 _ |a Placke, Jan-Malte
|b 39
700 1 _ |a Raub, Simon
|b 40
700 1 _ |a Salva, Katrin
|b 41
700 1 _ |a Schlott, Swantje
|b 42
700 1 _ |a Sody, Elsa
|b 43
700 1 _ |a Steingrube, Nadine
|b 44
700 1 _ |a Stoffels, Ingo
|b 45
700 1 _ |a Ugurel, Selma
|b 46
700 1 _ |a Zaremba, Anne
|b 47
700 1 _ |a Gebhardt, Christoffer
|b 48
700 1 _ |a Booken, Nina
|b 49
700 1 _ |a Christolouka, Maria
|b 50
700 1 _ |a Buder-Bakhaya, Kristina
|b 51
700 1 _ |a Bokor-Billmann, Therezia
|b 52
700 1 _ |a Enk, Alexander
|b 53
700 1 _ |a Gholam, Patrick
|b 54
700 1 _ |a Hänßle, Holger
|b 55
700 1 _ |a Salzmann, Martin
|b 56
700 1 _ |a Schäfer, Sarah
|b 57
700 1 _ |a Schäkel, Knut
|b 58
700 1 _ |a Schank, Timo
|b 59
700 1 _ |a Bohne, Ann-Sophie
|b 60
700 1 _ |a Deffaa, Sophia
|b 61
700 1 _ |a Drerup, Katharina
|b 62
700 1 _ |a Egberts, Friederike
|b 63
700 1 _ |a Erkens, Anna-Sophie
|b 64
700 1 _ |a Ewald, Benjamin
|b 65
700 1 _ |a Falkvoll, Sandra
|b 66
700 1 _ |a Gerdes, Sascha
|b 67
700 1 _ |a Harde, Viola
|b 68
700 1 _ |a Hauschild, Axel
|b 69
700 1 _ |a Jost, Marion
|b 70
700 1 _ |a Kosova, Katja
|b 71
700 1 _ |a Messinger, Laetitia
|b 72
700 1 _ |a Metzner, Malte
|b 73
700 1 _ |a Morrison, Kirsten
|b 74
700 1 _ |a Motamedi, Rogina
|b 75
700 1 _ |a Pinczker, Anja
|b 76
700 1 _ |a Rosenthal, Anne
|b 77
700 1 _ |a Scheller, Natalie
|b 78
700 1 _ |a Schwarz, Thomas
|b 79
700 1 _ |a Stölzl, Dora
|b 80
700 1 _ |a Thielking, Federieke
|b 81
700 1 _ |a Tomaschewski, Elena
|b 82
700 1 _ |a Wehkamp, Ulrike
|b 83
700 1 _ |a Weichenthal, Michael
|b 84
700 1 _ |a Wiedow, Oliver
|b 85
700 1 _ |a Bär, Claudia Maria
|b 86
700 1 _ |a Bender-Säbelkampf, Sophia
|b 87
700 1 _ |a Horbrügger, Marc
|b 88
700 1 _ |a Karoglan, Ante
|b 89
700 1 _ |a Kraas, Luise
|b 90
700 1 _ |a Faulhaber, Jörg
|b 91
700 1 _ |a Geraud, Cyrill
|b 92
700 1 _ |a Guo, Ze
|b 93
700 1 _ |a Koch, Philipp
|b 94
700 1 _ |a Linke, Miriam
|b 95
700 1 _ |a Maurier, Nolwenn
|b 96
700 1 _ |a Müller, Verena
|b 97
700 1 _ |a Thomas, Benjamin
|b 98
700 1 _ |a Utikal, Jochen Sven
|0 P:(DE-He78)a229f7724466e7efadf4a1ace1ff8af3
|b 99
700 1 _ |a Alamri, Ali Saeed M
|b 100
700 1 _ |a Baczako, Andrea
|b 101
700 1 _ |a Berking, Carola
|b 102
700 1 _ |a Betke, Matthias
|b 103
700 1 _ |a Haas, Carolin
|b 104
700 1 _ |a Hartmann, Daniela
|b 105
700 1 _ |a Heppt, Markus V
|b 106
700 1 _ |a Kilian, Katharina
|b 107
700 1 _ |a Krammer, Sebastian
|b 108
700 1 _ |a Lapczynski, Natalie Lidia
|b 109
700 1 _ |a Mastnik, Sebastian
|b 110
700 1 _ |a Nasifoglu, Suzan
|b 111
700 1 _ |a Ruini, Cristel
|b 112
700 1 _ |a Sattler, Elke
|b 113
700 1 _ |a Schlaak, Max
|b 114
700 1 _ |a Wolff, Hans
|b 115
700 1 _ |a Achatz, Birgit
|b 116
700 1 _ |a Bergbreiter, Astrid
|b 117
700 1 _ |a Drexler, Konstantin
|b 118
700 1 _ |a Ettinger, Monika
|b 119
700 1 _ |a Haferkamp, Sebastian
|b 120
700 1 _ |a Halupczok, Anna
|b 121
700 1 _ |a Hegemann, Marie
|b 122
700 1 _ |a Dinauer, Verena
|b 123
700 1 _ |a Maagk, Maria
|b 124
700 1 _ |a Mickler, Marion
|b 125
700 1 _ |a Philipp, Biance
|b 126
700 1 _ |a Wilm, Anna
|b 127
700 1 _ |a Wittmann, Constanze
|b 128
700 1 _ |a Gesierich, Anja
|b 129
700 1 _ |a Glutsch, Valerie
|b 130
700 1 _ |a Kahlert, Katrin
|b 131
700 1 _ |a Kerstan, Andreas
|b 132
700 1 _ |a Schilling, Bastian
|b 133
700 1 _ |a Schrüfer, Philipp
|b 134
773 _ _ |a 10.1016/j.ejca.2019.04.001
|g Vol. 113, p. 47 - 54
|0 PERI:(DE-600)1468190-0
|p 47 - 54
|t European journal of cancer
|v 113
|y 2019
|x 0959-8049
909 C O |p VDB
|o oai:inrepo02.dkfz.de:143587
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 0
|6 P:(DE-HGF)0
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 1
|6 P:(DE-HGF)0
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 9
|6 P:(DE-He78)457c042884c901eb0a02c18bb1d30103
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 10
|6 P:(DE-He78)a229f7724466e7efadf4a1ace1ff8af3
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 11
|6 P:(DE-He78)5bacb661d5d7c0220d8f996d980ad8de
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 99
|6 P:(DE-He78)a229f7724466e7efadf4a1ace1ff8af3
913 1 _ |a DE-HGF
|l Krebsforschung
|1 G:(DE-HGF)POF3-310
|0 G:(DE-HGF)POF3-312
|2 G:(DE-HGF)POF3-300
|v Functional and structural genomics
|x 0
|4 G:(DE-HGF)POF
|3 G:(DE-HGF)POF3
|b Gesundheit
914 1 _ |y 2019
915 _ _ |a Nationallizenz
|0 StatID:(DE-HGF)0420
|2 StatID
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0200
|2 StatID
|b SCOPUS
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0300
|2 StatID
|b Medline
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0310
|2 StatID
|b NCBI Molecular Biology Database
915 _ _ |a JCR
|0 StatID:(DE-HGF)0100
|2 StatID
|b EUR J CANCER : 2017
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0600
|2 StatID
|b Ebsco Academic Search
915 _ _ |a Peer Review
|0 StatID:(DE-HGF)0030
|2 StatID
|b ASC
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0199
|2 StatID
|b Clarivate Analytics Master Journal List
915 _ _ |a WoS
|0 StatID:(DE-HGF)0110
|2 StatID
|b Science Citation Index
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0150
|2 StatID
|b Web of Science Core Collection
915 _ _ |a WoS
|0 StatID:(DE-HGF)0111
|2 StatID
|b Science Citation Index Expanded
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)1110
|2 StatID
|b Current Contents - Clinical Medicine
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)1030
|2 StatID
|b Current Contents - Life Sciences
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)1050
|2 StatID
|b BIOSIS Previews
915 _ _ |a IF >= 5
|0 StatID:(DE-HGF)9905
|2 StatID
|b EUR J CANCER : 2017
920 1 _ |0 I:(DE-He78)B340-20160331
|k B340
|l Translationale Medizinische Onkolologie
|x 0
920 1 _ |0 I:(DE-He78)C060-20160331
|k C060
|l Biostatistik
|x 1
920 1 _ |0 I:(DE-He78)A370-20160331
|k A370
|l KKE Dermatoonkologie
|x 2
980 _ _ |a journal
980 _ _ |a VDB
980 _ _ |a I:(DE-He78)B340-20160331
980 _ _ |a I:(DE-He78)C060-20160331
980 _ _ |a I:(DE-He78)A370-20160331
980 _ _ |a UNRESTRICTED


LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21