Imperial College London

DR BERNHARD KAINZ

Faculty of EngineeringDepartment of Computing

Reader in Medical Image Computing
 
 
 
//

Contact

 

+44 (0)20 7594 8349b.kainz Website CV

 
 
//

Location

 

372Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Reinke:2024:10.1038/s41592-023-02150-0,
author = {Reinke, A and Tizabi, MD and Baumgartner, M and Eisenmann, M and Heckmann-Nötzel, D and Kavur, AE and Rädsch, T and Sudre, CH and Acion, L and Antonelli, M and Arbel, T and Bakas, S and Benis, A and Buettner, F and Cardoso, MJ and Cheplygina, V and Chen, J and Christodoulou, E and Cimini, BA and Farahani, K and Ferrer, L and Galdran, A and van, Ginneken B and Glocker, B and Godau, P and Hashimoto, DA and Hoffman, MM and Huisman, M and Isensee, F and Jannin, P and Kahn, CE and Kainmueller, D and Kainz, B and Karargyris, A and Kleesiek, J and Kofler, F and Kooi, T and Kopp-Schneider, A and Kozubek, M and Kreshuk, A and Kurc, T and Landman, BA and Litjens, G and Madani, A and Maier-Hein, K and Martel, AL and Meijering, E and Menze, B and Moons, KGM and Müller, H and Nichyporuk, B and Nickel, F and Petersen, J and Rafelski, SM and Rajpoot, N and Reyes, M and Riegler, MA and Rieke, N and Saez-Rodriguez, J and Sánchez, CI and Shetty, S and Summers, RM and Taha, AA and Tiulpin, A and Tsaftari},
doi = {10.1038/s41592-023-02150-0},
journal = {Nature Methods},
pages = {182--194},
title = {Understanding metric-related pitfalls in image analysis validation},
url = {http://dx.doi.org/10.1038/s41592-023-02150-0},
volume = {21},
year = {2024}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence research and its translation into practice. However, increasing evidence shows that, particularly in image analysis, metrics are often chosen inadequately. Although taking into account the individual strengths, weaknesses and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multistage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides a reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Although focused on biomedical image analysis, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. The work serves to enhance global comprehension of a key topic in image analysis validation.
AU - Reinke,A
AU - Tizabi,MD
AU - Baumgartner,M
AU - Eisenmann,M
AU - Heckmann-Nötzel,D
AU - Kavur,AE
AU - Rädsch,T
AU - Sudre,CH
AU - Acion,L
AU - Antonelli,M
AU - Arbel,T
AU - Bakas,S
AU - Benis,A
AU - Buettner,F
AU - Cardoso,MJ
AU - Cheplygina,V
AU - Chen,J
AU - Christodoulou,E
AU - Cimini,BA
AU - Farahani,K
AU - Ferrer,L
AU - Galdran,A
AU - van,Ginneken B
AU - Glocker,B
AU - Godau,P
AU - Hashimoto,DA
AU - Hoffman,MM
AU - Huisman,M
AU - Isensee,F
AU - Jannin,P
AU - Kahn,CE
AU - Kainmueller,D
AU - Kainz,B
AU - Karargyris,A
AU - Kleesiek,J
AU - Kofler,F
AU - Kooi,T
AU - Kopp-Schneider,A
AU - Kozubek,M
AU - Kreshuk,A
AU - Kurc,T
AU - Landman,BA
AU - Litjens,G
AU - Madani,A
AU - Maier-Hein,K
AU - Martel,AL
AU - Meijering,E
AU - Menze,B
AU - Moons,KGM
AU - Müller,H
AU - Nichyporuk,B
AU - Nickel,F
AU - Petersen,J
AU - Rafelski,SM
AU - Rajpoot,N
AU - Reyes,M
AU - Riegler,MA
AU - Rieke,N
AU - Saez-Rodriguez,J
AU - Sánchez,CI
AU - Shetty,S
AU - Summers,RM
AU - Taha,AA
AU - Tiulpin,A
AU - Tsaftaris,SA
AU - Van,Calster B
AU - Varoquaux,G
AU - Yaniv,ZR
AU - Jäger,PF
AU - Maier-Hein,L
DO - 10.1038/s41592-023-02150-0
EP - 194
PY - 2024///
SN - 1548-7091
SP - 182
TI - Understanding metric-related pitfalls in image analysis validation
T2 - Nature Methods
UR - http://dx.doi.org/10.1038/s41592-023-02150-0
UR - https://www.ncbi.nlm.nih.gov/pubmed/38347140
UR - https://www.nature.com/articles/s41592-023-02150-0
VL - 21
ER -