% 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{DAlmeida:292112,
      author       = {S. D Almeida$^*$ and T. Norajitra$^*$ and C. T. Lüth$^*$
                      and T. Wald$^*$ and V. Weru$^*$ and M. Nolden$^*$ and P. F.
                      Jäger$^*$ and O. von Stackelberg and C. P. Heußel and O.
                      Weinheimer and J. Biederer and H.-U. Kauczor and K.
                      Maier-Hein$^*$},
      title        = {{H}ow do deep-learning models generalize across
                      populations? {C}ross-ethnicity generalization of {COPD}
                      detection.},
      journal      = {Insights into imaging},
      volume       = {15},
      number       = {1},
      issn         = {1869-4101},
      address      = {Heidelberg},
      publisher    = {Springer},
      reportid     = {DKFZ-2024-01611},
      pages        = {198},
      year         = {2024},
      note         = {#EA:E230#LA:E230#},
      abstract     = {To evaluate the performance and potential biases of
                      deep-learning models in detecting chronic obstructive
                      pulmonary disease (COPD) on chest CT scans across different
                      ethnic groups, specifically non-Hispanic White (NHW) and
                      African American (AA) populations.Inspiratory chest CT and
                      clinical data from 7549 Genetic epidemiology of COPD
                      individuals (mean age 62 years old, 56-69 interquartile
                      range), including 5240 NHW and 2309 AA individuals, were
                      retrospectively analyzed. Several factors influencing COPD
                      binary classification performance on different ethnic
                      populations were examined: (1) effects of training
                      population: NHW-only, AA-only, balanced set (half NHW, half
                      AA) and the entire set (NHW + AA all); (2) learning
                      strategy: three supervised learning (SL) vs. three
                      self-supervised learning (SSL) methods. Distribution shifts
                      across ethnicity were further assessed for the
                      top-performing methods.The learning strategy significantly
                      influenced model performance, with SSL methods achieving
                      higher performances compared to SL methods (p < 0.001),
                      across all training configurations. Training on balanced
                      datasets containing NHW and AA individuals resulted in
                      improved model performance compared to population-specific
                      datasets. Distribution shifts were found between ethnicities
                      for the same health status, particularly when models were
                      trained on nearest-neighbor contrastive SSL. Training on a
                      balanced dataset resulted in fewer distribution shifts
                      across ethnicity and health status, highlighting its
                      efficacy in reducing biases.Our findings demonstrate that
                      utilizing SSL methods and training on large and balanced
                      datasets can enhance COPD detection model performance and
                      reduce biases across diverse ethnic populations. These
                      findings emphasize the importance of equitable AI-driven
                      healthcare solutions for COPD diagnosis.Self-supervised
                      learning coupled with balanced datasets significantly
                      improves COPD detection model performance, addressing biases
                      across diverse ethnic populations and emphasizing the
                      crucial role of equitable AI-driven healthcare
                      solutions.Self-supervised learning methods outperform
                      supervised learning methods, showing higher AUC values (p <
                      0.001). Balanced datasets with non-Hispanic White and
                      African American individuals improve model performance.
                      Training on diverse datasets enhances COPD detection
                      accuracy. Ethnically diverse datasets reduce bias in COPD
                      detection models. SimCLR models mitigate biases in COPD
                      detection across ethnicities.},
      keywords     = {Artificial intelligence (Other) / Chronic obstructive
                      pulmonary disease (Other) / Computed tomography (Other) /
                      Deep learning (Other) / Ethnicity (Other)},
      cin          = {E230 / E290 / C060},
      ddc          = {610},
      cid          = {I:(DE-He78)E230-20160331 / I:(DE-He78)E290-20160331 /
                      I:(DE-He78)C060-20160331},
      pnm          = {315 - Bildgebung und Radioonkologie (POF4-315)},
      pid          = {G:(DE-HGF)POF4-315},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:39112910},
      doi          = {10.1186/s13244-024-01781-x},
      url          = {https://inrepo02.dkfz.de/record/292112},
}