000144770 001__ 144770
000144770 005__ 20240229112637.0
000144770 0247_ $$2doi$$a10.1016/j.ejca.2019.07.019
000144770 0247_ $$2pmid$$apmid:31518967
000144770 0247_ $$2ISSN$$a0014-2964
000144770 0247_ $$2ISSN$$a0959-8049
000144770 0247_ $$2ISSN$$a1879-0852
000144770 0247_ $$2ISSN$$a1879-2995
000144770 0247_ $$2altmetric$$aaltmetric:66598192
000144770 037__ $$aDKFZ-2019-02202
000144770 041__ $$aeng
000144770 082__ $$a610
000144770 1001_ $$0P:(DE-HGF)0$$aHekler, Achim$$b0$$eFirst author
000144770 245__ $$aSuperior skin cancer classification by the combination of human and artificial intelligence.
000144770 260__ $$aAmsterdam [u.a.]$$bElsevier$$c2019
000144770 3367_ $$2DRIVER$$aarticle
000144770 3367_ $$2DataCite$$aOutput Types/Journal article
000144770 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1568617950_17480
000144770 3367_ $$2BibTeX$$aARTICLE
000144770 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000144770 3367_ $$00$$2EndNote$$aJournal Article
000144770 520__ $$aIn recent studies, convolutional neural networks (CNNs) outperformed dermatologists in distinguishing dermoscopic images of melanoma and nevi. In these studies, dermatologists and artificial intelligence were considered as opponents. However, the combination of classifiers frequently yields superior results, both in machine learning and among humans. In this study, we investigated the potential benefit of combining human and artificial intelligence for skin cancer classification.Using 11,444 dermoscopic images, which were divided into five diagnostic categories, novel deep learning techniques were used to train a single CNN. Then, both 112 dermatologists of 13 German university hospitals and the trained CNN independently classified a set of 300 biopsy-verified skin lesions into those five classes. Taking into account the certainty of the decisions, the two independently determined diagnoses were combined to a new classifier with the help of a gradient boosting method. The primary end-point of the study was the correct classification of the images into five designated categories, whereas the secondary end-point was the correct classification of lesions as either benign or malignant (binary classification).Regarding the multiclass task, the combination of man and machine achieved an accuracy of 82.95%. This was 1.36% higher than the best of the two individual classifiers (81.59% achieved by the CNN). Owing to the class imbalance in the binary problem, sensitivity, but not accuracy, was examined and demonstrated to be superior (89%) to the best individual classifier (CNN with 86.1%). The specificity in the combined classifier decreased from 89.2% to 84%. However, at an equal sensitivity of 89%, the CNN achieved a specificity of only 81.5% INTERPRETATION: Our findings indicate that the combination of human and artificial intelligence achieves superior results over the independent results of both of these systems.
000144770 536__ $$0G:(DE-HGF)POF3-311$$a311 - Signalling pathways, cell and tumor biology (POF3-311)$$cPOF3-311$$fPOF III$$x0
000144770 588__ $$aDataset connected to CrossRef, PubMed,
000144770 7001_ $$0P:(DE-He78)a229f7724466e7efadf4a1ace1ff8af3$$aUtikal, Jochen S$$b1$$udkfz
000144770 7001_ $$aEnk, Alexander H$$b2
000144770 7001_ $$aHauschild, Axel$$b3
000144770 7001_ $$aWeichenthal, Michael$$b4
000144770 7001_ $$aMaron, Roman C$$b5
000144770 7001_ $$aBerking, Carola$$b6
000144770 7001_ $$aHaferkamp, Sebastian$$b7
000144770 7001_ $$aKlode, Joachim$$b8
000144770 7001_ $$aSchadendorf, Dirk$$b9
000144770 7001_ $$aSchilling, Bastian$$b10
000144770 7001_ $$0P:(DE-He78)457c042884c901eb0a02c18bb1d30103$$aHolland-Letz, Tim$$b11$$udkfz
000144770 7001_ $$aIzar, Benjamin$$b12
000144770 7001_ $$0P:(DE-He78)5bacb661d5d7c0220d8f996d980ad8de$$avon Kalle, Christof$$b13$$udkfz
000144770 7001_ $$0P:(DE-He78)f0144d171d26dbedb67c9db1df35629d$$aFröhling, Stefan$$b14$$udkfz
000144770 7001_ $$0P:(DE-HGF)0$$aBrinker, Titus J$$b15
000144770 7001_ $$aCollaborators$$b16$$eCollaboration Author
000144770 7001_ $$aSchmitt, Laurenz$$b17
000144770 7001_ $$aPeitsch, Wiebke K$$b18
000144770 7001_ $$aHoffmann, Friederike$$b19
000144770 7001_ $$aBecker, Jürgen C$$b20
000144770 7001_ $$aDrusio, Christina$$b21
000144770 7001_ $$aJansen, Philipp$$b22
000144770 7001_ $$aKlode, Joachim$$b23
000144770 7001_ $$aLodde, Georg$$b24
000144770 7001_ $$aSammet, Stefanie$$b25
000144770 7001_ $$aSchadendorf, Dirk$$b26
000144770 7001_ $$aSondermann, Wiebke$$b27
000144770 7001_ $$aUgurel, Selma$$b28
000144770 7001_ $$aZader, Jeannine$$b29
000144770 7001_ $$aEnk, Alexander$$b30
000144770 7001_ $$aSalzmann, Martin$$b31
000144770 7001_ $$aSchäfer, Sarah$$b32
000144770 7001_ $$aSchäkel, Knut$$b33
000144770 7001_ $$aWinkler, Julia$$b34
000144770 7001_ $$aWölbing, Priscilla$$b35
000144770 7001_ $$aAsper, Hiba$$b36
000144770 7001_ $$aBohne, Ann-Sophie$$b37
000144770 7001_ $$aBrown, Victoria$$b38
000144770 7001_ $$aBurba, Bianca$$b39
000144770 7001_ $$aDeffaa, Sophia$$b40
000144770 7001_ $$aDietrich, Cecilia$$b41
000144770 7001_ $$aDietrich, Matthias$$b42
000144770 7001_ $$aDrerup, Katharina Antonia$$b43
000144770 7001_ $$aEgberts, Friederike$$b44
000144770 7001_ $$aErkens, Anna-Sophie$$b45
000144770 7001_ $$aGreven, Salim$$b46
000144770 7001_ $$aHarde, Viola$$b47
000144770 7001_ $$aJost, Marion$$b48
000144770 7001_ $$aKaeding, Merit$$b49
000144770 7001_ $$aKosova, Katharina$$b50
000144770 7001_ $$aLischner, Stephan$$b51
000144770 7001_ $$aMaagk, Maria$$b52
000144770 7001_ $$aMessinger, Anna Laetitia$$b53
000144770 7001_ $$aMetzner, Malte$$b54
000144770 7001_ $$aMotamedi, Rogina$$b55
000144770 7001_ $$aRosenthal, Ann-Christine$$b56
000144770 7001_ $$aSeidl, Ulrich$$b57
000144770 7001_ $$aStemmermann, Jana$$b58
000144770 7001_ $$aTorz, Kaspar$$b59
000144770 7001_ $$aVelez, Juliana Giraldo$$b60
000144770 7001_ $$aHaiduk, Jennifer$$b61
000144770 7001_ $$aAlter, Mareike$$b62
000144770 7001_ $$aBär, Claudia$$b63
000144770 7001_ $$aBergenthal, Paul$$b64
000144770 7001_ $$aGerlach, Anne$$b65
000144770 7001_ $$aHoltorf, Christian$$b66
000144770 7001_ $$aKaroglan, Ante$$b67
000144770 7001_ $$aKindermann, Sophie$$b68
000144770 7001_ $$aKraas, Luise$$b69
000144770 7001_ $$aFelcht, Moritz$$b70
000144770 7001_ $$aGaiser, Maria R$$b71
000144770 7001_ $$aKlemke, Claus-Detlev$$b72
000144770 7001_ $$aKurzen, Hjalmar$$b73
000144770 7001_ $$aLeibing, Thomas$$b74
000144770 7001_ $$aMüller, Verena$$b75
000144770 7001_ $$aReinhard, Raphael R$$b76
000144770 7001_ $$0P:(DE-He78)a229f7724466e7efadf4a1ace1ff8af3$$aUtikal, Jochen$$b77$$udkfz
000144770 7001_ $$aWinter, Franziska$$b78
000144770 7001_ $$aBerking, Carola$$b79
000144770 7001_ $$aEicher, Laurie$$b80
000144770 7001_ $$aHartmann, Daniela$$b81
000144770 7001_ $$aHeppt, Markus$$b82
000144770 7001_ $$aKilian, Katharina$$b83
000144770 7001_ $$aKrammer, Sebastian$$b84
000144770 7001_ $$aLill, Diana$$b85
000144770 7001_ $$aNiesert, Anne-Charlotte$$b86
000144770 7001_ $$aOppel, Eva$$b87
000144770 7001_ $$aSattler, Elke$$b88
000144770 7001_ $$aSenner, Sonja$$b89
000144770 7001_ $$aWallmichrath, Jens$$b90
000144770 7001_ $$aWolff, Hans$$b91
000144770 7001_ $$aGesierich, Anja$$b92
000144770 7001_ $$aGiner, Tina$$b93
000144770 7001_ $$aGlutsch, Valerie$$b94
000144770 7001_ $$aKerstan, Andreas$$b95
000144770 7001_ $$aPresser, Dagmar$$b96
000144770 7001_ $$aSchrüfer, Philipp$$b97
000144770 7001_ $$aSchummer, Patrick$$b98
000144770 7001_ $$aStolze, Ina$$b99
000144770 7001_ $$aWeber, Judith$$b100
000144770 7001_ $$aDrexler, Konstantin$$b101
000144770 7001_ $$aHaferkamp, Sebastian$$b102
000144770 7001_ $$aMickler, Marion$$b103
000144770 7001_ $$aStauner, Camila Toledo$$b104
000144770 7001_ $$aThiem, Alexander$$b105
000144770 773__ $$0PERI:(DE-600)1468190-0$$a10.1016/j.ejca.2019.07.019$$gVol. 120, p. 114 - 121$$p114 - 121$$tEuropean journal of cancer$$v120$$x0959-8049$$y2019
000144770 909CO $$ooai:inrepo02.dkfz.de:144770$$pVDB
000144770 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b0$$kDKFZ
000144770 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)a229f7724466e7efadf4a1ace1ff8af3$$aDeutsches Krebsforschungszentrum$$b1$$kDKFZ
000144770 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)457c042884c901eb0a02c18bb1d30103$$aDeutsches Krebsforschungszentrum$$b11$$kDKFZ
000144770 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)5bacb661d5d7c0220d8f996d980ad8de$$aDeutsches Krebsforschungszentrum$$b13$$kDKFZ
000144770 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)f0144d171d26dbedb67c9db1df35629d$$aDeutsches Krebsforschungszentrum$$b14$$kDKFZ
000144770 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b15$$kDKFZ
000144770 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)a229f7724466e7efadf4a1ace1ff8af3$$aDeutsches Krebsforschungszentrum$$b77$$kDKFZ
000144770 9131_ $$0G:(DE-HGF)POF3-311$$1G:(DE-HGF)POF3-310$$2G:(DE-HGF)POF3-300$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lKrebsforschung$$vSignalling pathways, cell and tumor biology$$x0
000144770 9141_ $$y2019
000144770 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz
000144770 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000144770 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline
000144770 915__ $$0StatID:(DE-HGF)0310$$2StatID$$aDBCoverage$$bNCBI Molecular Biology Database
000144770 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bEUR J CANCER : 2017
000144770 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search
000144770 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC
000144770 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List
000144770 915__ $$0StatID:(DE-HGF)0110$$2StatID$$aWoS$$bScience Citation Index
000144770 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000144770 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded
000144770 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine
000144770 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences
000144770 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews
000144770 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bEUR J CANCER : 2017
000144770 9201_ $$0I:(DE-He78)A370-20160331$$kA370$$lKKE Dermatoonkologie$$x0
000144770 9201_ $$0I:(DE-He78)C060-20160331$$kC060$$lBiostatistik$$x1
000144770 9201_ $$0I:(DE-He78)B340-20160331$$kB340$$lTranslationale Medizinische Onkologie$$x2
000144770 980__ $$ajournal
000144770 980__ $$aVDB
000144770 980__ $$aI:(DE-He78)A370-20160331
000144770 980__ $$aI:(DE-He78)C060-20160331
000144770 980__ $$aI:(DE-He78)B340-20160331
000144770 980__ $$aUNRESTRICTED