% 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{Wennmann:302832,
author = {M. Wennmann$^*$ and J. Kächele$^*$ and A. von Salomon$^*$
and T. Nonnenmacher and M. Bujotzek$^*$ and S. Xiao$^*$ and
A. Martinez Mora$^*$ and T. Hielscher$^*$ and M. Hajiyianni
and E. Menis and M. Grözinger$^*$ and F. Bauer$^*$ and V.
Riebl and L. T. Rotkopf$^*$ and K. S. Zhang$^*$ and S. Afat
and B. Besemer and M. Hoffmann and A. Ringelstein and U.
Graeven and D. Fedders and M. Hänel and G. Antoch and R.
Fenk and A. H. Mahnken and C. Mann and T. Mokry and M.-S.
Raab and N. Weinhold and E. K. Mai and H. Goldschmidt and T.
F. Weber and S. Delorme$^*$ and P. Neher$^*$ and H.-P.
Schlemmer$^*$ and K. Maier-Hein$^*$},
title = {{A}utomated {D}etection of {F}ocal {B}one {M}arrow
{L}esions {F}rom {MRI}: {A} {M}ulti-center {F}easibility
{S}tudy in {P}atients with {M}onoclonal {P}lasma {C}ell
{D}isorders.},
journal = {Academic radiology},
volume = {nn},
issn = {1076-6332},
address = {Philadelphia, PA [u.a.]},
publisher = {Elsevier},
reportid = {DKFZ-2025-01372},
pages = {nn},
year = {2025},
note = {#EA:E010#LA:E010#LA:E230# / epub},
abstract = {To train and test an AI-based algorithm for automated
detection of focal bone marrow lesions (FL) from MRI.This
retrospective feasibility study included 444 patients with
monoclonal plasma cell disorders. For this feasibility
study, only FLs in the left pelvis were included. Using the
nnDetection framework, the algorithm was trained based on
334 patients with 494 FLs from center 1, and was tested on
an internal test set (36 patients, 89 FLs, center 1) and a
multicentric external test set (74 patients, 262 FLs,
centers 2-11). Mean average precision (mAP), F1-score,
sensitivity, positive predictive value (PPV), and Spearman
correlation coefficient between automatically determined and
actual number of FLs were calculated.On the
internal/external test set, the algorithm achieved a mAP of
0.44/0.34, F1-Score of 0.54/0.44, sensitivity of 0.49/0.34,
and a PPV of 0.61/0.61, respectively. In two subsets of the
external multicentric test set with high imaging quality,
the performance nearly matched that of the internal test
set, with mAP of 0.45/0.41, F1-Score of 0.50/0.53,
sensitivity of 0.44/0.43, and a PPV of 0.60/0.71,
respectively. There was a significant correlation between
the automatically determined and actual number of FLs on
both the internal (r=0.51, p=0.001) and external
multicentric test set (r=0.59, p<0.001).This study
demonstrates that the automated detection of FLs from MRI,
and thereby the automated assessment of the number of FLs,
is feasible.},
keywords = {AI (Other) / Detection (Other) / Focal lesions (Other) /
Monoclonal plasma cell disorders (Other) / Multicenter
(Other)},
cin = {E230 / C060 / HD01 / E010},
ddc = {610},
cid = {I:(DE-He78)E230-20160331 / I:(DE-He78)C060-20160331 /
I:(DE-He78)HD01-20160331 / I:(DE-He78)E010-20160331},
pnm = {315 - Bildgebung und Radioonkologie (POF4-315)},
pid = {G:(DE-HGF)POF4-315},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:40640054},
doi = {10.1016/j.acra.2025.06.034},
url = {https://inrepo02.dkfz.de/record/302832},
}