% 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{Carstens:307300,
      author       = {M. Carstens and S. Vasisht and Z. Zhang and I. Barbur and
                      A. Reinke$^*$ and L. Maier-Hein$^*$ and D. A. Hashimoto and
                      F. R. Kolbinger},
      title        = {{A}rtificial intelligence for surgical scene understanding:
                      a systematic review and reporting quality meta-analysis.},
      journal      = {npj digital medicine},
      volume       = {9},
      issn         = {2398-6352},
      address      = {[Basingstoke]},
      publisher    = {Macmillan Publishers Limited},
      reportid     = {DKFZ-2025-02986},
      pages        = {59},
      year         = {2026},
      note         = {volume 9, Article number: 59 (2026)},
      abstract     = {Surgical scene understanding (SSU) uses artificial
                      intelligence (AI) to interpret visual data from surgeries,
                      such as laparoscopic videos. Despite promising foundational
                      research on instrument and anatomy recognition, clinical
                      adoption remains minimal. This systematic review and
                      meta-analysis (PROSPERO: CRD420251005301) evaluates current
                      SSU research in minimally invasive abdominal surgery,
                      focusing on data curation, model design, validation,
                      reporting standards, and clinical relevance. A total of 188
                      studies were reviewed. Most relied on small, single-center
                      datasets $(70.7\%),$ primarily laparoscopic
                      cholecystectomies $(59.0\%),$ reflecting an overall narrow
                      topical breadth. Validation practices were often weak,
                      rarely involving external datasets $(10.1\%)$ or clinical
                      experts. Few studies addressed clinical translation
                      $(5.9\%),$ model performance variability estimation
                      $(38.3\%),$ or made code available $(29.8\%).$ Overall,
                      limited progress toward clinical integration has been made
                      over the past decade. Our findings highlight the need for
                      diverse, multi-institutional datasets, robust validation
                      practices, and clinically driven development to unlock the
                      full potential of SSU in surgical practice.},
      cin          = {E130},
      ddc          = {610},
      cid          = {I:(DE-He78)E130-20160331},
      pnm          = {315 - Bildgebung und Radioonkologie (POF4-315)},
      pid          = {G:(DE-HGF)POF4-315},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:41407878},
      doi          = {10.1038/s41746-025-02227-4},
      url          = {https://inrepo02.dkfz.de/record/307300},
}