% 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:169017,
author = {N. Netzer$^*$ and C. Weißer$^*$ and P. Schelb$^*$ and X.
Wang$^*$ and X. Qin$^*$ and M. Görtz and V. Schütz and J.
P. Radtke$^*$ and T. Hielscher$^*$ and C. Schwab and A.
Stenzinger and T. A. Kuder$^*$ and R. Gnirs$^*$ and M.
Hohenfellner and H.-P. Schlemmer$^*$ and K. H.
Maier-Hein$^*$ and D. Bonekamp$^*$},
title = {{F}ully {A}utomatic {D}eep {L}earning in {B}i-institutional
{P}rostate {M}agnetic {R}esonance {I}maging: {E}ffects of
{C}ohort {S}ize and {H}eterogeneity.},
journal = {Investigative radiology},
volume = {56},
number = {12},
issn = {0020-9996},
address = {[s.l.]},
publisher = {Ovid},
reportid = {DKFZ-2021-01185},
pages = {799-808},
year = {2021},
note = {#EA:E010#LA:E010# /December 2021 - Volume 56 - Issue 12 - p
799-808},
abstract = {The potential of deep learning to support radiologist
prostate magnetic resonance imaging (MRI) interpretation has
been demonstrated.The aim of this study was to evaluate the
effects of increased and diversified training data (TD) on
deep learning performance for detection and segmentation of
clinically significant prostate cancer-suspicious lesions.In
this retrospective study, biparametric (T2-weighted and
diffusion-weighted) prostate MRI acquired with multiple
1.5-T and 3.0-T MRI scanners in consecutive men was used for
training and testing of prostate segmentation and lesion
detection networks. Ground truth was the combination of
targeted and extended systematic MRI-transrectal ultrasound
fusion biopsies, with significant prostate cancer defined as
International Society of Urological Pathology grade group
greater than or equal to 2. U-Nets were internally validated
on full, reduced, and PROSTATEx-enhanced training sets and
subsequently externally validated on the institutional test
set and the PROSTATEx test set. U-Net segmentation was
calibrated to clinically desired levels in cross-validation,
and test performance was subsequently compared using
sensitivities, specificities, predictive values, and Dice
coefficient.One thousand four hundred eighty-eight
institutional examinations (median age, 64 years;
interquartile range, 58-70 years) were temporally split into
training (2014-2017, 806 examinations, supplemented by 204
PROSTATEx examinations) and test (2018-2020, 682
examinations) sets. In the test set, Prostate
Imaging-Reporting and Data System (PI-RADS) cutoffs greater
than or equal to 3 and greater than or equal to 4 on a
per-patient basis had sensitivity of $97\%$ (241/249) and
$90\%$ (223/249) at specificity of $19\%$ (82/433) and
$56\%$ (242/433), respectively. The full U-Net had
corresponding sensitivity of $97\%$ (241/249) and $88\%$
(219/249) with specificity of $20\%$ (86/433) and $59\%$
(254/433), not statistically different from PI-RADS (P > 0.3
for all comparisons). U-Net trained using a reduced set of
171 consecutive examinations achieved inferior performance
(P < 0.001). PROSTATEx training enhancement did not improve
performance. Dice coefficients were 0.90 for prostate and
0.42/0.53 for MRI lesion segmentation at PI-RADS category
3/4 equivalents.In a large institutional test set, U-Net
confirms similar performance to clinical PI-RADS assessment
and benefits from more TD, with neither institutional nor
PROSTATEx performance improved by adding multiscanner or
bi-institutional TD.},
cin = {E010 / C060 / E020 / E230 / HD01},
ddc = {610},
cid = {I:(DE-He78)E010-20160331 / I:(DE-He78)C060-20160331 /
I:(DE-He78)E020-20160331 / I:(DE-He78)E230-20160331 /
I:(DE-He78)HD01-20160331},
pnm = {315 - Bildgebung und Radioonkologie (POF4-315)},
pid = {G:(DE-HGF)POF4-315},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:34049336},
doi = {10.1097/RLI.0000000000000791},
url = {https://inrepo02.dkfz.de/record/169017},
}