KIT | KIT-Bibliothek | Impressum | Datenschutz

LapSeg3D: Weakly Supervised Semantic Segmentation of Point Clouds Representing Laparoscopic Scenes

Alt, Benjamin; Kunz, Christian ORCID iD icon 1; Katic, Darko; Younis, Rayan 1; Jäkel, Rainer; Müller-Stich, Beat; Wagner, Martin; Mathis-Ullrich, Franziska 1
1 Institut für Anthropomatik und Robotik (IAR), Karlsruher Institut für Technologie (KIT)


The semantic segmentation of surgical scenes is a prerequisite for task automation in robot assisted interventions. We propose LapSeg3D, a novel DNN-based approach for the voxel-wise annotation of point clouds representing surgical scenes. As the manual annotation of training data is highly time consuming, we introduce a semi-autonomous clustering-based pipeline for the annotation of the gallbladder, which is used to generate segmented labels for the DNN. When evaluated against manually annotated data, LapSeg3D achieves an F1 score of 0.94 for gallbladder segmentation on various datasets of ex-vivo porcine livers. We show LapSeg3D to generalize accurately across different gallbladders and datasets recorded with different RGB-D camera systems.

Volltext §
DOI: 10.5445/IR/1000155639
Veröffentlicht am 03.02.2023
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Forschungsbericht/Preprint
Publikationsjahr 2022
Sprache Englisch
Identifikator KITopen-ID: 1000155639
Umfang 6 S.
Vorab online veröffentlicht am 15.07.2022
Nachgewiesen in arXiv
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page