001     288083
005     20250326103243.0
024 7 _ |a 10.1038/s41592-023-02151-z
|2 doi
024 7 _ |a pmid:38347141
|2 pmid
024 7 _ |a 1548-7091
|2 ISSN
024 7 _ |a 1548-7105
|2 ISSN
024 7 _ |a altmetric:159461769
|2 altmetric
037 _ _ |a DKFZ-2024-00337
041 _ _ |a English
082 _ _ |a 610
100 1 _ |a Maier-Hein, Lena
|0 P:(DE-He78)26a1176cd8450660333a012075050072
|b 0
|e First author
245 _ _ |a Metrics reloaded: recommendations for image analysis validation.
260 _ _ |a London [u.a.]
|c 2024
|b Nature Publishing Group
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 1710237197_32557
|2 PUB:(DE-HGF)
|x Review Article
336 7 _ |a ARTICLE
|2 BibTeX
336 7 _ |a JOURNAL_ARTICLE
|2 ORCID
336 7 _ |a Journal Article
|0 0
|2 EndNote
500 _ _ |a #EA:E130#LA:E290#
520 _ _ |a Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. In biomedical image analysis, chosen performance metrics often do not reflect the domain interest, and thus fail to adequately measure scientific progress and hinder translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Developed by a large international consortium in a multistage Delphi process, it is based on the novel concept of a problem fingerprint-a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), dataset and algorithm output. On the basis of the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as classification tasks at image, object or pixel level, namely image-level classification, object detection, semantic segmentation and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases.
536 _ _ |a 315 - Bildgebung und Radioonkologie (POF4-315)
|0 G:(DE-HGF)POF4-315
|c POF4-315
|f POF IV
|x 0
588 _ _ |a Dataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de
700 1 _ |a Reinke, Annika
|0 P:(DE-He78)97e904f47dab556a77c0149cd0002591
|b 1
|e First author
700 1 _ |a Godau, Patrick
|0 P:(DE-He78)77a2a5b07dcbd46277a18a32372ea154
|b 2
700 1 _ |a Tizabi, Minu D
|0 P:(DE-He78)26651d9aa10255ad4f35610a56aa91e8
|b 3
700 1 _ |a Büttner, Florian
|0 P:(DE-He78)fdeeec93551e8f3bad68db88a1130c5d
|b 4
|u dkfz
700 1 _ |a Christodoulou, Evangelia
|0 P:(DE-He78)8da2eca0bc6341c8681c317fe2b8e27b
|b 5
700 1 _ |a Glocker, Ben
|0 0000-0002-4897-9356
|b 6
700 1 _ |a Isensee, Fabian
|0 P:(DE-He78)7ea9af59d03ec7deb982a0e0562358fa
|b 7
700 1 _ |a Kleesiek, Jens
|b 8
700 1 _ |a Kozubek, Michal
|0 0000-0001-7902-589X
|b 9
700 1 _ |a Reyes, Mauricio
|b 10
700 1 _ |a Riegler, Michael A
|0 0000-0002-3153-2064
|b 11
700 1 _ |a Wiesenfarth, Manuel
|0 P:(DE-He78)1042737c83ba70ec508bdd99f0096864
|b 12
700 1 _ |a Kavur, A Emre
|0 P:(DE-He78)64296d0922a2da68074f5de2ccf74487
|b 13
700 1 _ |a Sudre, Carole H
|b 14
700 1 _ |a Baumgartner, Michael
|0 P:(DE-He78)6ae68adec0915a4ae2d58aff814aaceb
|b 15
700 1 _ |a Eisenmann, Matthias
|0 P:(DE-He78)c9d6245b17f0ab26eeed345cb00d3359
|b 16
700 1 _ |a Heckmann-Nötzel, Doreen
|0 P:(DE-He78)98dd16a42af0888dd129e1cd2ee2766a
|b 17
700 1 _ |a Rädsch, Tim
|0 P:(DE-He78)683f71d452c83a7f5ec62969c6012466
|b 18
700 1 _ |a Acion, Laura
|0 0000-0001-5213-6012
|b 19
700 1 _ |a Antonelli, Michela
|0 0000-0002-3005-4523
|b 20
700 1 _ |a Arbel, Tal
|0 0000-0001-8870-3007
|b 21
700 1 _ |a Bakas, Spyridon
|0 0000-0001-8734-6482
|b 22
700 1 _ |a Benis, Arriel
|0 0000-0002-9125-8300
|b 23
700 1 _ |a Blaschko, Matthew B
|b 24
700 1 _ |a Cardoso, M Jorge
|0 0000-0003-1284-2558
|b 25
700 1 _ |a Cheplygina, Veronika
|b 26
700 1 _ |a Cimini, Beth A
|0 0000-0001-9640-9318
|b 27
700 1 _ |a Collins, Gary S
|0 0000-0002-2772-2316
|b 28
700 1 _ |a Farahani, Keyvan
|b 29
700 1 _ |a Ferrer, Luciana
|b 30
700 1 _ |a Galdran, Adrian
|b 31
700 1 _ |a van Ginneken, Bram
|b 32
700 1 _ |a Haase, Robert
|b 33
700 1 _ |a Hashimoto, Daniel A
|0 0000-0003-4725-3104
|b 34
700 1 _ |a Hoffman, Michael M
|0 0000-0002-4517-1562
|b 35
700 1 _ |a Huisman, Merel
|b 36
700 1 _ |a Jannin, Pierre
|0 0000-0002-7415-071X
|b 37
700 1 _ |a Kahn, Charles E
|0 0000-0002-6654-7434
|b 38
700 1 _ |a Kainmueller, Dagmar
|b 39
700 1 _ |a Kainz, Bernhard
|b 40
700 1 _ |a Karargyris, Alexandros
|0 0000-0002-1930-3410
|b 41
700 1 _ |a Karthikesalingam, Alan
|b 42
700 1 _ |a Kofler, Florian
|b 43
700 1 _ |a Kopp-Schneider, Annette
|0 P:(DE-He78)bb6a7a70f976eb8df1769944bf913596
|b 44
700 1 _ |a Kreshuk, Anna
|0 0000-0003-1334-6388
|b 45
700 1 _ |a Kurc, Tahsin
|b 46
700 1 _ |a Landman, Bennett A
|0 0000-0001-5733-2127
|b 47
700 1 _ |a Litjens, Geert
|0 0000-0003-1554-1291
|b 48
700 1 _ |a Madani, Amin
|b 49
700 1 _ |a Maier-Hein, Klaus
|0 P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3
|b 50
700 1 _ |a Martel, Anne L
|0 0000-0003-1375-5501
|b 51
700 1 _ |a Mattson, Peter
|0 0000-0002-5984-238X
|b 52
700 1 _ |a Meijering, Erik
|0 0000-0001-8015-8358
|b 53
700 1 _ |a Menze, Bjoern
|0 0000-0003-4136-5690
|b 54
700 1 _ |a Moons, Karel G M
|b 55
700 1 _ |a Müller, Henning
|0 0000-0001-6800-9878
|b 56
700 1 _ |a Nichyporuk, Brennan
|0 0009-0006-8087-6089
|b 57
700 1 _ |a Nickel, Felix
|b 58
700 1 _ |a Petersen, Jens
|b 59
700 1 _ |a Rajpoot, Nasir
|0 0000-0001-6760-1271
|b 60
700 1 _ |a Rieke, Nicola
|0 0000-0003-0241-9334
|b 61
700 1 _ |a Saez-Rodriguez, Julio
|b 62
700 1 _ |a Sánchez, Clara I
|b 63
700 1 _ |a Shetty, Shravya
|b 64
700 1 _ |a van Smeden, Maarten
|b 65
700 1 _ |a Summers, Ronald M
|0 0000-0001-8081-7376
|b 66
700 1 _ |a Taha, Abdel A
|0 0000-0002-7604-9041
|b 67
700 1 _ |a Tiulpin, Aleksei
|0 0000-0002-7852-4141
|b 68
700 1 _ |a Tsaftaris, Sotirios A
|b 69
700 1 _ |a Van Calster, Ben
|b 70
700 1 _ |a Varoquaux, Gaël
|0 0000-0003-1076-5122
|b 71
700 1 _ |a Jäger, Paul
|0 P:(DE-He78)04a0b5a49db132d8f00cee326cb743ca
|b 72
|e Last author
773 _ _ |a 10.1038/s41592-023-02151-z
|g Vol. 21, no. 2, p. 195 - 212
|0 PERI:(DE-600)2163081-1
|n 2
|p 195 - 212
|t Nature methods
|v 21
|y 2024
|x 1548-7091
856 4 _ |u https://inrepo02.dkfz.de/record/288083/files/s41592-023-02151-z.pdf
856 4 _ |u https://inrepo02.dkfz.de/record/288083/files/s41592-023-02151-z.pdf?subformat=pdfa
|x pdfa
909 C O |p VDB
|o oai:inrepo02.dkfz.de:288083
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 0
|6 P:(DE-He78)26a1176cd8450660333a012075050072
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 1
|6 P:(DE-He78)97e904f47dab556a77c0149cd0002591
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 2
|6 P:(DE-He78)77a2a5b07dcbd46277a18a32372ea154
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 3
|6 P:(DE-He78)26651d9aa10255ad4f35610a56aa91e8
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 4
|6 P:(DE-He78)fdeeec93551e8f3bad68db88a1130c5d
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 5
|6 P:(DE-He78)8da2eca0bc6341c8681c317fe2b8e27b
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 7
|6 P:(DE-He78)7ea9af59d03ec7deb982a0e0562358fa
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 12
|6 P:(DE-He78)1042737c83ba70ec508bdd99f0096864
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 13
|6 P:(DE-He78)64296d0922a2da68074f5de2ccf74487
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 15
|6 P:(DE-He78)6ae68adec0915a4ae2d58aff814aaceb
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 16
|6 P:(DE-He78)c9d6245b17f0ab26eeed345cb00d3359
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 17
|6 P:(DE-He78)98dd16a42af0888dd129e1cd2ee2766a
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 18
|6 P:(DE-He78)683f71d452c83a7f5ec62969c6012466
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 44
|6 P:(DE-He78)bb6a7a70f976eb8df1769944bf913596
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 50
|6 P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 72
|6 P:(DE-He78)04a0b5a49db132d8f00cee326cb743ca
913 1 _ |a DE-HGF
|b Gesundheit
|l Krebsforschung
|1 G:(DE-HGF)POF4-310
|0 G:(DE-HGF)POF4-315
|3 G:(DE-HGF)POF4
|2 G:(DE-HGF)POF4-300
|4 G:(DE-HGF)POF
|v Bildgebung und Radioonkologie
|x 0
914 1 _ |y 2024
915 _ _ |a Nationallizenz
|0 StatID:(DE-HGF)0420
|2 StatID
|d 2023-08-29
|w ger
915 _ _ |a DEAL Nature
|0 StatID:(DE-HGF)3003
|2 StatID
|d 2023-08-29
|w ger
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0200
|2 StatID
|b SCOPUS
|d 2023-08-29
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0300
|2 StatID
|b Medline
|d 2023-08-29
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0199
|2 StatID
|b Clarivate Analytics Master Journal List
|d 2023-08-29
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)1050
|2 StatID
|b BIOSIS Previews
|d 2023-08-29
915 _ _ |a WoS
|0 StatID:(DE-HGF)0113
|2 StatID
|b Science Citation Index Expanded
|d 2023-08-29
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0150
|2 StatID
|b Web of Science Core Collection
|d 2023-08-29
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)1030
|2 StatID
|b Current Contents - Life Sciences
|d 2023-08-29
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)1190
|2 StatID
|b Biological Abstracts
|d 2023-08-29
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0160
|2 StatID
|b Essential Science Indicators
|d 2023-08-29
915 _ _ |a JCR
|0 StatID:(DE-HGF)0100
|2 StatID
|b NAT METHODS : 2022
|d 2023-08-29
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0600
|2 StatID
|b Ebsco Academic Search
|d 2023-08-29
915 _ _ |a Peer Review
|0 StatID:(DE-HGF)0030
|2 StatID
|b ASC
|d 2023-08-29
915 _ _ |a IF >= 40
|0 StatID:(DE-HGF)9940
|2 StatID
|b NAT METHODS : 2022
|d 2023-08-29
920 2 _ |0 I:(DE-He78)E290-20160331
|k E290
|l NWG Interaktives maschinelles Lernen
|x 0
920 1 _ |0 I:(DE-He78)E130-20160331
|k E130
|l E130 Intelligente Medizinische Systeme
|x 0
920 1 _ |0 I:(DE-He78)FM01-20160331
|k FM01
|l DKTK Koordinierungsstelle Frankfurt
|x 1
920 1 _ |0 I:(DE-He78)E230-20160331
|k E230
|l E230 Medizinische Bildverarbeitung
|x 2
920 1 _ |0 I:(DE-He78)C060-20160331
|k C060
|l C060 Biostatistik
|x 3
920 1 _ |0 I:(DE-He78)E290-20160331
|k E290
|l NWG Interaktives maschinelles Lernen
|x 4
920 0 _ |0 I:(DE-He78)E130-20160331
|k E130
|l E130 Intelligente Medizinische Systeme
|x 0
980 _ _ |a journal
980 _ _ |a VDB
980 _ _ |a I:(DE-He78)E130-20160331
980 _ _ |a I:(DE-He78)FM01-20160331
980 _ _ |a I:(DE-He78)E230-20160331
980 _ _ |a I:(DE-He78)C060-20160331
980 _ _ |a I:(DE-He78)E290-20160331
980 _ _ |a UNRESTRICTED


LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21