% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Reinke:288084,
author = {A. Reinke$^*$ and M. D. Tizabi$^*$ and M. Baumgartner$^*$
and M. Eisenmann$^*$ and D. Heckmann-Nötzel$^*$ and A. E.
Kavur$^*$ and T. Rädsch$^*$ and C. H. Sudre and L. Acion
and M. Antonelli and T. Arbel and S. Bakas and A. Benis and
F. Büttner$^*$ and M. J. Cardoso and V. Cheplygina and J.
Chen and E. Christodoulou$^*$ and B. A. Cimini and K.
Farahani and L. Ferrer and A. Galdran and B. van Ginneken
and B. Glocker and P. Godau$^*$ and D. A. Hashimoto and M.
M. Hoffman and M. Huisman and F. Isensee$^*$ and P. Jannin
and C. E. Kahn and D. Kainmueller and B. Kainz and A.
Karargyris and J. Kleesiek and F. Kofler and T. Kooi and A.
Kopp-Schneider$^*$ and M. Kozubek and A. Kreshuk and T. Kurc
and B. A. Landman and G. Litjens and A. Madani and K.
Maier-Hein$^*$ and A. L. Martel and E. Meijering and B.
Menze and K. G. M. Moons and H. Müller and B. Nichyporuk
and F. Nickel and J. Petersen and S. M. Rafelski and N.
Rajpoot and M. Reyes and M. A. Riegler and N. Rieke and J.
Saez-Rodriguez and C. I. Sánchez and S. Shetty and R. M.
Summers and A. A. Taha and A. Tiulpin and S. A. Tsaftaris
and B. Van Calster and G. Varoquaux and Z. R. Yaniv and P.
Jäger$^*$ and L. Maier-Hein$^*$},
title = {{U}nderstanding metric-related pitfalls in image analysis
validation.},
journal = {Nature methods},
volume = {21},
number = {2},
issn = {1548-7091},
address = {London [u.a.]},
publisher = {Nature Publishing Group},
reportid = {DKFZ-2024-00338},
pages = {182 - 194},
year = {2024},
note = {#EA:E130#LA:E130#LA:E290#},
abstract = {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.},
subtyp = {Review Article},
cin = {E130 / E230 / C060 / E290 / FM01},
ddc = {610},
cid = {I:(DE-He78)E130-20160331 / I:(DE-He78)E230-20160331 /
I:(DE-He78)C060-20160331 / I:(DE-He78)E290-20160331 /
I:(DE-He78)FM01-20160331},
pnm = {315 - Bildgebung und Radioonkologie (POF4-315)},
pid = {G:(DE-HGF)POF4-315},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:38347140},
doi = {10.1038/s41592-023-02150-0},
url = {https://inrepo02.dkfz.de/record/288084},
}