% 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{Echle:156827,
author = {A. Echle and H. I. Grabsch and P. Quirke and P. A. van den
Brandt and N. P. West and G. G. A. Hutchins and L. R. Heij
and X. Tan and S. D. Richman and J. Krause and E. Alwers$^*$
and J. Jenniskens and K. Offermans and R. Gray and H.
Brenner$^*$ and J. Chang-Claude$^*$ and C. Trautwein and A.
T. Pearson and P. Boor and T. Luedde and N. T. Gaisa and M.
Hoffmeister$^*$ and J. Nikolas Kather$^*$},
title = {{C}linical-grade {D}etection of {M}icrosatellite
{I}nstability in {C}olorectal {T}umors by {D}eep
{L}earning.},
journal = {Gastroenterology},
volume = {159},
number = {4},
issn = {0016-5085},
address = {Philadelphia, Pa. [u.a.]},
publisher = {Saunders},
reportid = {DKFZ-2020-01144},
pages = {1406-1416.e11},
year = {2020},
note = {2020 Oct;159(4):1406-1416.e11},
abstract = {Microsatellite instability (MSI) and mismatch-repair
deficiency (dMMR) in colorectal tumors are used to select
treatment for patients. Deep learning can detect MSI and
dMMR in tumor samples on routine histology slides faster and
cheaper than molecular assays. But clinical application of
this technology requires high performance and multisite
validation, which have not yet been performed.We collected
hematoxylin and eosin-stained slides, and findings from
molecular analyses for MSI and dMMR, from 8836 colorectal
tumors (of all stages) included in the MSIDETECT consortium
study, from Germany, the Netherlands, the United Kingdom,
and the United States. Specimens with dMMR were identified
by immunohistochemistry analyses of tissue microarrays for
loss of MLH1, MSH2, MSH6, and/or PMS2. Specimens with MSI
were identified by genetic analyses. We trained a
deep-learning detector to identify samples with MSI from
these slides; performance was assessed by cross-validation
(n=6406 specimens) and validated in an external cohort
(n=771 specimens). Prespecified endpoints were area under
the receiver operating characteristic (AUROC) curve and area
under the precision-recall curve (AUPRC).The deep-learning
detector identified specimens with dMMR or MSI with a mean
AUROC curve of 0.92 (lower bound 0.91, upper bound 0.93) and
an AUPRC of 0.63 (range, 0.59-0.65), or $67\%$ specificity
and $95\%$ sensitivity, in the cross-validation development
cohort. In the validation cohort, the classifier identified
samples with dMMR with an AUROC curve of 0.95 (range,
0.92-0.96) without image-preprocessing and an AUROC curve of
0.96 (range, 0.93-0.98) after color normalization.We
developed a deep-learning system that detects colorectal
cancer specimens with dMMR or MSI using hematoxylin and
eosin-stained slides; it detected tissues with dMMR with an
AUROC of 0.96 in a large, international validation cohort.
This system might be used for high-throughput, low-cost
evaluation of colorectal tissue specimens.},
cin = {C070 / C020 / HD01 / C120},
ddc = {610},
cid = {I:(DE-He78)C070-20160331 / I:(DE-He78)C020-20160331 /
I:(DE-He78)HD01-20160331 / I:(DE-He78)C120-20160331},
pnm = {314 - Tumor immunology (POF3-314)},
pid = {G:(DE-HGF)POF3-314},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:32562722},
doi = {10.1053/j.gastro.2020.06.021},
url = {https://inrepo02.dkfz.de/record/156827},
}