% 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{Pisula:302792,
      author       = {J. I. Pisula and D. Helbig and L. Sancéré and O.-D. Persa
                      and C. Bürger and A. Fröhlich and C. Lorenz and S.
                      Bingmann and D. Niebel and K. Drexler and J. Landsberg and
                      R. Thomas$^*$ and K. Bozek and J. Brägelmann},
      title        = {{E}xplainable, federated deep learning model predicts
                      disease progression risk of cutaneous squamous cell
                      carcinoma.},
      journal      = {npj precision oncology},
      volume       = {9},
      number       = {1},
      issn         = {2397-768X},
      address      = {[London]},
      publisher    = {Springer Nature},
      reportid     = {DKFZ-2025-01332},
      pages        = {205},
      year         = {2025},
      abstract     = {Predicting cancer patient disease progression is a key step
                      towards personalized medicine and secondary prevention. Risk
                      stratification systems based on clinico-pathological
                      criteria aim to identify high-risk patients, but accurate
                      predictions remain challenging. Deep learning models present
                      new opportunities for patient risk prediction, yet their
                      interpretability has been largely unexplored. We developed a
                      transformer-based approach for predicting progression of
                      cutaneous squamous cell carcinoma (cSCC) patients based on
                      diagnostic histopathology tumor slides. Our initial model
                      showed AUROC = 0.92 on a held-out test set, with average
                      AUROC of 0.65 on external validation cohorts. To further
                      increase generalizability and reduce potential privacy
                      concerns, we trained the model in a federated manner across
                      three clinical centers, reaching AUROC = 0.82 across all
                      cohorts, with image-based risk scores achieving hazard
                      ratios up to 7.42 (p < 0.01) in multivariable analyses.
                      Through interpretability analysis, we identified spatial and
                      morphological features predictive of progression, suggesting
                      that tumor boundary information and tissue heterogeneity
                      characterize progressive cSCCs. Trained exclusively on
                      routine diagnostic slides and offering biological insights,
                      our model can improve secondary prevention and understanding
                      of cSCC while enabling deployment across clinical centers
                      without administrative overheads or privacy concerns.},
      cin          = {HD01},
      ddc          = {610},
      cid          = {I:(DE-He78)HD01-20160331},
      pnm          = {899 - ohne Topic (POF4-899)},
      pid          = {G:(DE-HGF)POF4-899},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:40581685},
      pmc          = {pmc:PMC12206231},
      doi          = {10.1038/s41698-025-00997-4},
      url          = {https://inrepo02.dkfz.de/record/302792},
}