% 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{Netzer:277857,
author = {N. Netzer$^*$ and C. Eith$^*$ and O. Bethge and T.
Hielscher$^*$ and C. Schwab and A. Stenzinger and R.
Gnirs$^*$ and H.-P. Schlemmer$^*$ and K. H. Maier-Hein$^*$
and L. Schimmöller and D. Bonekamp$^*$},
title = {{A}pplication of a validated prostate {MRI} deep learning
system to independent same-vendor multi-institutional data:
demonstration of transferability.},
journal = {European radiology},
volume = {33},
number = {11},
issn = {0938-7994},
address = {Heidelberg},
publisher = {Springer},
reportid = {DKFZ-2023-01525},
pages = {7463-7476},
year = {2023},
note = {#EA:E010#LA:E010# / 2023 Nov;33(11):7463-7476},
abstract = {To evaluate a fully automatic deep learning system to
detect and segment clinically significant prostate cancer
(csPCa) on same-vendor prostate MRI from two different
institutions not contributing to training of the system.In
this retrospective study, a previously bi-institutionally
validated deep learning system (UNETM) was applied to
bi-parametric prostate MRI data from one external
institution (A), a PI-RADS distribution-matched internal
cohort (B), and a csPCa stratified subset of
single-institution external public challenge data (C). csPCa
was defined as ISUP Grade Group ≥ 2 determined from
combined targeted and extended systematic MRI/transrectal
US-fusion biopsy. Performance of UNETM was evaluated by
comparing ROC AUC and specificity at typical PI-RADS
sensitivity levels. Lesion-level analysis between UNETM
segmentations and radiologist-delineated segmentations was
performed using Dice coefficient, free-response operating
characteristic (FROC), and weighted alternative (waFROC).
The influence of using different diffusion sequences was
analyzed in cohort A.In 250/250/140 exams in cohorts A/B/C,
differences in ROC AUC were insignificant with 0.80 $(95\%$
CI: 0.74-0.85)/0.87 $(95\%$ CI: 0.83-0.92)/0.82 $(95\%$ CI:
0.75-0.89). At sensitivities of $95\%$ and $90\%,$ UNETM
achieved specificity of $30\%/50\%$ in A, $44\%/71\%$ in B,
and $43\%/49\%$ in C, respectively. Dice coefficient of
UNETM and radiologist-delineated lesions was 0.36 in A and
0.49 in B. The waFROC AUC was 0.67 $(95\%$ CI: 0.60-0.83) in
A and 0.7 $(95\%$ CI: 0.64-0.78) in B. UNETM performed
marginally better on readout-segmented than on single-shot
echo-planar-imaging.For same-vendor examinations, deep
learning provided comparable discrimination of csPCa and
non-csPCa lesions and examinations between local and two
independent external data sets, demonstrating the
applicability of the system to institutions not
participating in model training.A previously
bi-institutionally validated fully automatic deep learning
system maintained acceptable exam-level diagnostic
performance in two independent external data sets,
indicating the potential of deploying AI models without
retraining or fine-tuning, and corroborating evidence that
AI models extract a substantial amount of transferable
domain knowledge about MRI-based prostate cancer
assessment.• A previously bi-institutionally validated
fully automatic deep learning system maintained acceptable
exam-level diagnostic performance in two independent
external data sets. • Lesion detection performance and
segmentation congruence was similar on the institutional and
an external data set, as measured by the weighted
alternative FROC AUC and Dice coefficient. • Although the
system generalized to two external institutions without
re-training, achieving expected sensitivity and specificity
levels using the deep learning system requires probability
thresholds to be adjusted, underlining the importance of
institution-specific calibration and quality control.},
keywords = {Deep learning (Other) / Magnetic resonance imaging (Other)
/ Prostatic neoplasms (Other) / Validation study (Other)},
cin = {E010 / C060 / HD01 / E230},
ddc = {610},
cid = {I:(DE-He78)E010-20160331 / I:(DE-He78)C060-20160331 /
I:(DE-He78)HD01-20160331 / I:(DE-He78)E230-20160331},
pnm = {315 - Bildgebung und Radioonkologie (POF4-315)},
pid = {G:(DE-HGF)POF4-315},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:37507610},
doi = {10.1007/s00330-023-09882-9},
url = {https://inrepo02.dkfz.de/record/277857},
}