% 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{Rueckert:308544,
      author       = {T. Rueckert and D. Rauber and R. Maerkl and L. Klausmann
                      and S. R. Yildiran and M. Gutbrod and D. W. Nunes and A. F.
                      Moreno and I. Luengo and D. Stoyanov and N. Toussaint and E.
                      Cho and H. B. Kim and O. S. Choo and K. Y. Kim and S. T. Kim
                      and G. Arantes and K. Song and J. Zhu and J. Xiong and T.
                      Lin and S. Kikuchi and H. Matsuzaki and A. Kouno and J. R.
                      R. Manesco and J. P. Papa and T.-M. Choi and T. K. Jeong and
                      J. Park and O. Alabi and M. Wei and T. Vercauteren and R. Wu
                      and M. Xu and A. Wang and L. Bai and H. Ren and A.
                      Yamlahi$^*$ and J. Hennighausen$^*$ and L. Maier-Hein$^*$
                      and S. Kondo and S. Kasai and K. Hirasawa and S. Yang and Y.
                      Wang and H. Chen and S. Rodríguez and N. Aparicio and L.
                      Manrique and J. C. Lyons and O. Hosie and N. Ayobi and P.
                      Arbeláez and Y. Li and Y. Al Khalil and S. Nasirihaghighi
                      and S. Speidel$^*$ and D. Rueckert and H. Feussner and D.
                      Wilhelm and C. Palm},
      title        = {{C}omparative validation of surgical phase recognition,
                      instrument keypoint estimation, and instrument instance
                      segmentation in endoscopy: {R}esults of the {P}ha{KIR} 2024
                      challenge.},
      journal      = {Medical image analysis},
      volume       = {109},
      issn         = {1361-8415},
      address      = {Amsterdam [u.a.]},
      publisher    = {Elsevier Science},
      reportid     = {DKFZ-2026-00170},
      pages        = {103945},
      year         = {2026},
      note         = {#NCTZFB26#},
      abstract     = {Reliable recognition and localization of surgical
                      instruments in endoscopic video recordings are foundational
                      for a wide range of applications in computer- and
                      robot-assisted minimally invasive surgery (RAMIS), including
                      surgical training, skill assessment, and autonomous
                      assistance. However, robust performance under real-world
                      conditions remains a significant challenge. Incorporating
                      surgical context - such as the current procedural phase -
                      has emerged as a promising strategy to improve robustness
                      and interpretability. To address these challenges, we
                      organized the Surgical Procedure Phase, Keypoint, and
                      Instrument Recognition (PhaKIR) sub-challenge as part of the
                      Endoscopic Vision (EndoVis) challenge at MICCAI 2024. We
                      introduced a novel, multi-center dataset comprising thirteen
                      full-length laparoscopic cholecystectomy videos collected
                      from three distinct medical institutions, with unified
                      annotations for three interrelated tasks: surgical phase
                      recognition, instrument keypoint estimation, and instrument
                      instance segmentation. Unlike existing datasets, ours
                      enables joint investigation of instrument localization and
                      procedural context within the same data while supporting the
                      integration of temporal information across entire
                      procedures. We report results and findings in accordance
                      with the BIAS guidelines for biomedical image analysis
                      challenges. The PhaKIR sub-challenge advances the field by
                      providing a unique benchmark for developing temporally
                      aware, context-driven methods in RAMIS and offers a
                      high-quality resource to support future research in surgical
                      scene understanding.},
      keywords     = {Instrument instance segmentation (Other) / Instrument
                      keypoint estimation (Other) / Robot-assisted surgery (Other)
                      / Surgical phase recognition (Other)},
      cin          = {E130 / DD04 / DD06},
      ddc          = {610},
      cid          = {I:(DE-He78)E130-20160331 / I:(DE-He78)DD04-20160331 /
                      I:(DE-He78)DD06-20160331},
      pnm          = {315 - Bildgebung und Radioonkologie (POF4-315)},
      pid          = {G:(DE-HGF)POF4-315},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:41564633},
      doi          = {10.1016/j.media.2026.103945},
      url          = {https://inrepo02.dkfz.de/record/308544},
}