% 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{Walger:277419,
author = {Walger, Lennart and Bauer, Tobias and Kügler, David and
Schmitz, Matthias H and Schuch, Fabiane and Arendt,
Christophe and Baumgartner, Tobias and Birkenheier, Johannes
and Borger, Valeri and Endler, Christoph and Grau, Franziska
and Immanuel, Christian and Kölle, Markus and Kupczyk,
Patrick and Lakghomi, Asadeh and Mackert, Sarah and Neuhaus,
Elisabeth and Nordsiek, Julia and Odenthal, Anna-Maria and
Dague, Karmele Olaciregui and Ostermann, Laura and
Pukropski, Jan and Racz, Attila and von der Ropp, Klaus and
Schmeel, Frederic Carsten and Schrader, Felix and Sitter,
Aileen and Unruh-Pinheiro, Alexander and Voigt, Marilia and
Vychopen, Martin and von Wedel, Philip and von Wrede, Randi
and Attenberger, Ulrike and Vatter, Hartmut and Philipsen,
Alexandra and Becker, Albert and Reuter, Martin and
Hattingen, Elke and Sander, Josemir W and Radbruch,
Alexander and Surges, Rainer and Rüber, Theodor},
title = {{A} {Q}uantitative {C}omparison {B}etween {H}uman and
{A}rtificial {I}ntelligence in the {D}etection of {F}ocal
{C}ortical {D}ysplasia.},
journal = {Investigative radiology},
volume = {60},
number = {4},
issn = {0020-9996},
address = {Philadelphia, Pa.},
publisher = {Lippincott Williams $\&$ Wilkins},
reportid = {DZNE-2025-00402},
pages = {253 - 259},
year = {2025},
abstract = {Artificial intelligence (AI) is thought to improve lesion
detection. However, a lack of knowledge about human
performance prevents a comparative evaluation of AI and an
accurate assessment of its impact on clinical
decision-making. The objective of this work is to
quantitatively evaluate the ability of humans to detect
focal cortical dysplasia (FCD), compare it to
state-of-the-art AI, and determine how it may aid
diagnostics.We prospectively recorded the performance of
readers in detecting FCDs using single points and
3-dimensional bounding boxes. We acquired predictions of 3
AI models for the same dataset and compared these to
readers. Finally, we analyzed pairwise combinations of
readers and models.Twenty-eight readers, including 20
nonexpert and 5 expert physicians, reviewed 180 cases: 146
subjects with FCD (median age: 25, interquartile range: 18)
and 34 healthy control subjects (median age: 43,
interquartile range: 19). Nonexpert readers detected $47\%$
$(95\%$ confidence interval [CI]: 46, 49) of FCDs, whereas
experts detected $68\%$ $(95\%$ CI: 65, 71). The 3 AI models
detected $32\%,$ $51\%,$ and $72\%$ of FCDs, respectively.
The latter, however, also predicted more than 13
false-positive clusters per subject on average. Human
performance was improved in the presence of a transmantle
sign ( P < 0.001) and cortical thickening ( P < 0.001). In
contrast, AI models were sensitive to abnormal gyration ( P
< 0.01) or gray-white matter blurring ( P < 0.01). Compared
with single experts, expert-expert pairs detected $13\%$
$(95\%$ CI: 9, 18) more FCDs ( P < 0.001). All AI models
increased expert detection rates by up to $19\%$ $(95\%$ CI:
15, 24) ( P < 0.001). Nonexpert+AI pairs could still
outperform single experts by up to $13\%$ $(95\%$ CI: 10,
17).This study pioneers the comparative evaluation of humans
and AI for FCD lesion detection. It shows that AI and human
predictions differ, especially for certain MRI features of
FCD, and, thus, how AI may complement the diagnostic
workup.},
keywords = {Humans / Artificial Intelligence / Female / Male / Magnetic
Resonance Imaging: methods / Adult / Prospective Studies /
Malformations of Cortical Development: diagnostic imaging /
Image Interpretation, Computer-Assisted: methods / Young
Adult / Adolescent / Sensitivity and Specificity / Middle
Aged / Reproducibility of Results / Focal Cortical
Dysplasia},
cin = {AG Reuter / AG Radbruch},
ddc = {610},
cid = {I:(DE-2719)1040310 / I:(DE-2719)5000075},
pnm = {354 - Disease Prevention and Healthy Aging (POF4-354) / 353
- Clinical and Health Care Research (POF4-353)},
pid = {G:(DE-HGF)POF4-354 / G:(DE-HGF)POF4-353},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:39437019},
doi = {10.1097/RLI.0000000000001125},
url = {https://pub.dzne.de/record/277419},
}