% 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{Loeffler:168506, author = {C. M. L. Loeffler and N. Ortiz Bruechle and M. Jung and L. Seillier and M. Rose and N. G. Laleh and R. Knuechel and T. J. Brinker$^*$ and C. Trautwein and N. T. Gaisa and J. N. Kather}, title = {{A}rtificial {I}ntelligence-based {D}etection of {FGFR}3 {M}utational {S}tatus {D}irectly from {R}outine {H}istology in {B}ladder {C}ancer: {A} {P}ossible {P}reselection for {M}olecular {T}esting?}, journal = {European urology focus}, volume = {8}, number = {2}, issn = {2405-4569}, address = {Amsterdam}, publisher = {Elsevier}, reportid = {DKFZ-2021-00938}, pages = {472-479}, year = {2022}, note = {2022 Mar;8(2):472-479}, abstract = {Fibroblast growth factor receptor (FGFR) inhibitor treatment has become the first clinically approved targeted therapy in bladder cancer. However, it requires previous molecular testing of each patient, which is costly and not ubiquitously available.To determine whether an artificial intelligence system is able to predict mutations of the FGFR3 gene directly from routine histology slides of bladder cancer.We trained a deep learning network to detect FGFR3 mutations on digitized slides of muscle-invasive bladder cancers stained with hematoxylin and eosin from the Cancer Genome Atlas (TCGA) cohort (n = 327) and validated the algorithm on the 'Aachen' cohort (n = 182; n = 121 pT2-4, n = 34 stroma-invasive pT1, and n = 27 noninvasive pTa tumors).The primary endpoint was the area under the receiver operating curve (AUROC) for mutation detection. Performance of the deep learning system was compared with visual scoring by an uropathologist.In the TCGA cohort, FGFR3 mutations were detected with an AUROC of 0.701 (p < 0.0001). In the Aachen cohort, FGFR3 mutants were found with an AUROC of 0.725 (p < 0.0001). When trained on TCGA, the network generalized to the Aachen cohort, and detected FGFR3 mutants with an AUROC of 0.625 (p = 0.0112). A subgroup analysis and histological evaluation found highest accuracy in papillary growth, luminal gene expression subtypes, females, and American Joint Committee on Cancer (AJCC) stage II tumors. In a head-to-head comparison, the deep learning system outperformed the uropathologist in detecting FGFR3 mutants.Our computer-based artificial intelligence system was able to detect genetic alterations of the FGFR3 gene of bladder cancer patients directly from histological slides. In the future, this system could be used to preselect patients for further molecular testing. However, analyses of larger, multicenter, muscle-invasive bladder cancer cohorts are now needed in order to validate and extend our findings.In this report, a computer-based artificial intelligence (AI) system was applied to histological slides to predict genetic alterations of the FGFR3 gene in bladder cancer. We found that the AI system was able to find the alteration with high accuracy. In the future, this system could be used to preselect patients for further molecular testing.}, keywords = {Artificial intelligence (Other) / Bladder cancer (Other) / Deep learning (Other) / FGFR3 mutations (Other) / Molecular testing for fibroblast growth factor receptor therapy (Other)}, cin = {C140}, ddc = {610}, cid = {I:(DE-He78)C140-20160331}, pnm = {313 - Krebsrisikofaktoren und Prävention (POF4-313)}, pid = {G:(DE-HGF)POF4-313}, typ = {PUB:(DE-HGF)16}, pubmed = {pmid:33895087}, doi = {10.1016/j.euf.2021.04.007}, url = {https://inrepo02.dkfz.de/record/168506}, }