% 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{Wagner:274184,
      author       = {M. Wagner and B.-P. Müller-Stich and A. Kisilenko and D.
                      Tran and P. Heger and L. Mündermann and D. M. Lubotsky and
                      B. Müller and T. Davitashvili and M. Capek and A.
                      Reinke$^*$ and C. Reid$^*$ and T. Yu and A. Vardazaryan and
                      C. I. Nwoye and N. Padoy and X. Liu and E.-J. Lee and C.
                      Disch and H. Meine and T. Xia and F. Jia and S. Kondo and W.
                      Reiter and Y. Jin and Y. Long and M. Jiang and Q. Dou and P.
                      A. Heng and I. Twick and K. Kirtac and E. Hosgor and J. L.
                      Bolmgren and M. Stenzel and B. von Siemens and L. Zhao and
                      Z. Ge and H. Sun and D. Xie and M. Guo and D. Liu and H. G.
                      Kenngott and F. Nickel and M. v. Frankenberg and F.
                      Mathis-Ullrich and A. Kopp-Schneider$^*$ and L.
                      Maier-Hein$^*$ and S. Speidel and S. Bodenstedt},
      title        = {{C}omparative validation of machine learning algorithms for
                      surgical workflow and skill analysis with the {H}ei{C}hole
                      benchmark.},
      journal      = {Medical image analysis},
      volume       = {86},
      issn         = {1361-8415},
      address      = {Amsterdam [u.a.]},
      publisher    = {Elsevier Science},
      reportid     = {DKFZ-2023-00479},
      pages        = {102770},
      year         = {2023},
      abstract     = {Surgical workflow and skill analysis are key technologies
                      for the next generation of cognitive surgical assistance
                      systems. These systems could increase the safety of the
                      operation through context-sensitive warnings and
                      semi-autonomous robotic assistance or improve training of
                      surgeons via data-driven feedback. In surgical workflow
                      analysis up to $91\%$ average precision has been reported
                      for phase recognition on an open data single-center video
                      dataset. In this work we investigated the generalizability
                      of phase recognition algorithms in a multicenter setting
                      including more difficult recognition tasks such as surgical
                      action and surgical skill.To achieve this goal, a dataset
                      with 33 laparoscopic cholecystectomy videos from three
                      surgical centers with a total operation time of 22 h was
                      created. Labels included framewise annotation of seven
                      surgical phases with 250 phase transitions, 5514 occurences
                      of four surgical actions, 6980 occurences of 21 surgical
                      instruments from seven instrument categories and 495 skill
                      classifications in five skill dimensions. The dataset was
                      used in the 2019 international Endoscopic Vision challenge,
                      sub-challenge for surgical workflow and skill analysis.
                      Here, 12 research teams trained and submitted their machine
                      learning algorithms for recognition of phase, action,
                      instrument and/or skill assessment.F1-scores were achieved
                      for phase recognition between $23.9\%$ and $67.7\%$ (n = 9
                      teams), for instrument presence detection between $38.5\%$
                      and $63.8\%$ (n = 8 teams), but for action recognition only
                      between $21.8\%$ and $23.3\%$ (n = 5 teams). The average
                      absolute error for skill assessment was 0.78 (n = 1
                      team).Surgical workflow and skill analysis are promising
                      technologies to support the surgical team, but there is
                      still room for improvement, as shown by our comparison of
                      machine learning algorithms. This novel HeiChole benchmark
                      can be used for comparable evaluation and validation of
                      future work. In future studies, it is of utmost importance
                      to create more open, high-quality datasets in order to allow
                      the development of artificial intelligence and cognitive
                      robotics in surgery.},
      keywords     = {Endoscopic vision (Other) / Laparoscopic cholecystectomy
                      (Other) / Surgical data science (Other) / Surgical workflow
                      analysis (Other)},
      cin          = {E130 / C060},
      ddc          = {610},
      cid          = {I:(DE-He78)E130-20160331 / 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:36889206},
      doi          = {10.1016/j.media.2023.102770},
      url          = {https://inrepo02.dkfz.de/record/274184},
}