% 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{Kather:168179,
author = {J. N. Kather$^*$ and L. R. Heij and H. I. Grabsch and C.
Loeffler and A. Echle and H. S. Muti and J. Krause and J. M.
Niehues and K. A. J. Sommer and P. Bankhead and L. F. S.
Kooreman and J. J. Schulte and N. A. Cipriani and R. D.
Buelow and P. Boor and N.-N. Ortiz-Brüchle and A. M. Hanby
and V. Speirs and S. Kochanny and A. Patnaik and A.
Srisuwananukorn and H. Brenner$^*$ and M. Hoffmeister$^*$
and P. A. van den Brandt and D. Jäger$^*$ and C. Trautwein
and A. T. Pearson and T. Luedde},
title = {{P}an-cancer image-based detection of clinically actionable
genetic alterations.},
journal = {Nature cancer},
volume = {1},
number = {8},
issn = {2662-1347},
address = {London},
publisher = {Nature Research},
reportid = {DKFZ-2021-00719},
pages = {789 - 799},
year = {2020},
abstract = {Molecular alterations in cancer can cause phenotypic
changes in tumor cells and their micro-environment. Routine
histopathology tissue slides - which are ubiquitously
available - can reflect such morphological changes. Here, we
show that deep learning can consistently infer a wide range
of genetic mutations, molecular tumor subtypes, gene
expression signatures and standard pathology biomarkers
directly from routine histology. We developed, optimized,
validated and publicly released a one-stop-shop workflow and
applied it to tissue slides of more than 5000 patients
across multiple solid tumors. Our findings show that a
single deep learning algorithm can be trained to predict a
wide range of molecular alterations from routine,
paraffin-embedded histology slides stained with hematoxylin
and eosin. These predictions generalize to other populations
and are spatially resolved. Our method can be implemented on
mobile hardware, potentially enabling point-of-care
diagnostics for personalized cancer treatment. More
generally, this approach could elucidate and quantify
genotype-phenotype links in cancer.},
cin = {HD01 / C070 / C120},
ddc = {610},
cid = {I:(DE-He78)HD01-20160331 / I:(DE-He78)C070-20160331 /
I:(DE-He78)C120-20160331},
pnm = {313 - Cancer risk factors and prevention (POF3-313)},
pid = {G:(DE-HGF)POF3-313},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:33763651},
pmc = {pmc:PMC7610412},
doi = {10.1038/s43018-020-0087-6},
url = {https://inrepo02.dkfz.de/record/168179},
}