Browsing by Author "Speidel, Stefanie"

Filter results by typing the first few letters
Now showing 1 - 3 of 3
  • ItemOpen Access
    Appendix300: Surgical video and patient metadata of 330 laparoscopic appendectomy cases from five institutions
    (Technische Universität Dresden, 2026-04-29) Kolbinger, Fiona R; Kirchner, Max; Pfeiffer, Kevin; Bodenstedt, Sebastian; Jenke, Alexander C; Barthel, Julia; Carstens, Matthias; Dehlke, Karolin; Dietz, Sophia; Emmanouilidis, Sotirios; Fitze, Guido; Freitag, Martin; Holderried, Fabian; Jacobi, Thorsten; Kanjo, Weam; Leitermann, Linda; Mees, Sören Torge; Pistorius, Steffen; Prudlo, Conrad; Seiberth, Astrid; Schultz, Jurek; Thiel, Karolin; Ziehn, Daniel; Speidel, Stefanie; Kather, Jakob Nikolas; Distler, Marius; Saldanha, Oliver Lester
    The limited availability of diverse and representative training data poses a critical barrier to the development of clinically relevant computational tools for intraoperative surgical decision support. Surgical procedures are not routinely recorded, and data annotation requires domain expertise, resulting in a scarcity of open-access surgical video datasets with high-quality annotations. Existing datasets are typically limited to single institutions and specific procedures, such as cholecystectomy, and rarely comprise patient-level metadata like demographic characteristics, disease history, or laboratory parameters. The Appendix300 dataset comprises 330 laparoscopic surgery recordings, including 325 full-length laparoscopic appendectomies and 5 control recordings from non-appendectomy procedures in pediatric and adult patients treated at five German centers. The dataset includes patient-level clinical metadata (demographics, medical history, clinical symptoms, preoperative laboratory parameters, and histopathological findings, as well as standardized expert annotations of the laparoscopic grade of appendicitis. This dataset enables novel validation tasks for computer vision in laparoscopic surgery and facilitates simulation of decentralized learning approaches, overall enhancing the breadth and translational relevance of AI-based surgical video analysis.
  • ItemOpen Access
    LASANA: Laparoscopic Skill Analysis and Assessment video dataset
    (Technische Universität Dresden, 2025-12-26) Funke, Isabel; Bodenstedt, Sebastian; von Bechtolsheim, Felix; Oehme, Florian; Maruschke, Michael; Petzsch, Stefanie; Weitz, Jürgen; Distler, Marius; Mees, Sören Torge; Speidel, Stefanie
    The LASANA video dataset comprises 1270 trimmed and synchronized stereo video recordings of four basic laparoscopic training tasks (peg transfer, circle cutting, balloon resection, and suture & knot). Per task, there are at least 311 recordings in the dataset. Each recording is annotated with a structured skill rating, aggregated across three independent raters, as well as binary labels indicating the presence or absence of task-specific errors (for example, dropping an object during the peg transfer task, or puncturing the inner balloon during the balloon resection task). The LASANA video dataset is intended to support the development and evaluation of methods for automatic video-based laparoscopic skill analysis. For benchmarking, a fixed datasplit into training, validation, and test videos is provided for each task.
  • ItemOpen Access
    The Dresden Dataset for 4D Reconstruction of Non-Rigid Abdominal Surgical Scenes
    (Technische Universität Dresden, 2025-12-10) Docea, Reuben; Younis, Rayan; Long, Yonghao; Fleury, Maxime; Xu, Jinjing; Li, Chenyang; Schulze, André; Wierick, Ann; Bender, Johannes; Pfeiffer, Micha; Dou, Qi; Wagner, Martin; Speidel, Stefanie
    The D4D Dataset provides paired endoscopic video and high-quality structured-light geometry for evaluating 3D reconstruction of deforming abdominal soft tissue in realistic surgical conditions. Data were acquired from six porcine cadaver sessions using a da Vinci Xi stereo endoscope and a Zivid structured-light camera, registered via optical tracking and manually curated iterative alignment methods. Three sequence types - whole deformations, incremental deformations, and moved-camera clips - probe algorithm robustness to non-rigid motion, deformation magnitude, and out-of-view updates. Each clip provides rectified stereo images, per-frame instrument masks, stereo depth, start/end structured-light point clouds, curated camera poses and camera intrinsics. In postprocessing, ICP and semi-automatic registration techniques are used to register data, and instrument masks are created. The dataset enables quantitative geometric evaluation in both visible and occluded regions, alongside photometric view-synthesis baselines. Comprising over 300,000 frames and 369 point clouds across 98 curated recordings, this resource can serve as a comprehensive benchmark for developing and evaluating non-rigid SLAM, 4D reconstruction, and depth estimation methods.