- Titel
- Anatomy segmentation in laparoscopic surgery
- Untertitel
- Comparison of machine learning and human expertise
- An experimental study
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:14-qucosa2-956334
- Quellenangabe
- International Journal of Surgery
Erscheinungsjahr: 2023
Jahrgang: 109
Heft: 10
Seiten: 2962-2974
E-ISSN: 1743-9159 - Erstveröffentlichung
- 2023
- Abstract (EN)
- Background: Lack of anatomy recognition represents a clinically relevant risk in abdominal surgery. Machine learning (ML) methods can help identify visible patterns and risk structures; however, their practical value remains largely unclear. Materials and methods: Based on a novel dataset of 13 195 laparoscopic images with pixel-wise segmentations of 11 anatomical structures, we developed specialized segmentation models for each structure and combined models for all anatomical structures using two state-of-the-art model architectures (DeepLabv3 and SegFormer) and compared segmentation performance of algorithms to a cohort of 28 physicians, medical students, and medical laypersons using the example of pancreas segmentation. Results: Mean Intersection-over-Union for semantic segmentation of intra-abdominal structures ranged from 0.28 to 0.83 and from 0.23 to 0.77 for the DeepLabv3-based structure-specific and combined models, and from 0.31 to 0.85 and from 0.26 to 0.67 for the SegFormer-based structure-specific and combined models, respectively. Both the structure-specific and the combined DeepLabv3-based models are capable of near-real-time operation, while the SegFormer-based models are not. All four models outperformed at least 26 out of 28 human participants in pancreas segmentation. Conclusions: These results demonstrate that ML methods have the potential to provide relevant assistance in anatomy recognition in minimally invasive surgery in near-real-time. Future research should investigate the educational value and subsequent clinical impact of the respective assistance systems.
- Andere Ausgabe
- Link zum Artikel, der zuerst in der Zeitschrift „International Journal of Surgery” im Verlag Wolters Kluwer erschienen ist.
DOI: 10.1097/JS9.0000000000000595 - Freie Schlagwörter (EN)
- artificial intelligence, laparoscopy, minimally invasive surgery, surgical anatomy, surgical data science
- Klassifikation (DDC)
- 610
- Verlag
- Wolters Kluwer, [Alphen aan den Rijn, Niederlande]
- Förder- / Projektangaben
- Else Kröner Fresenius Center for Digital Health (EKFZ)
CoBot - Deutsche Forschungsgemeinschaft (DFG)
EXC 2050
Centre for Tactile Internet with Human-in-the-Loop
(CeTI)
ID: 390696704 - Bundesministerium für Gesundheit (BMG)
Personalisierte Prädiktion lebensbedrohlicher Komplikationen in der Chirurgie durch maschinelles Lernen aus multimodalen Prozessdaten
(Surgomics)
ID: BMG 2520DAT82 - Technische Universität Dresden, Medizinische Fakultät Carl Gustav Carus MedDrive Start program
ID: 60487 - Joachim Herz Foundation Add-on Fellowship for Interdisciplinary Life Science
- Version / Begutachtungsstatus
- publizierte Version / Verlagsversion
- URN Qucosa
- urn:nbn:de:bsz:14-qucosa2-956334
- Veröffentlichungsdatum Qucosa
- 03.11.2025
- Dokumenttyp
- Artikel
- Sprache des Dokumentes
- Englisch
- Lizenz / Rechtehinweis
CC BY-NC-ND 4.0