EUVIMEDОткрийте EUVIMED
Systematische ÜbersichtOpen access · CC BY 4.0

Artificial intelligence in the operating room: A systematic review of AI models for surgical phase, instruments and anatomical structure identification

Künstliche Intelligenz im Operationssaal: systematische Übersicht zu KI-Modellen für die Erkennung von Operationsphasen, Instrumenten und anatomischen Strukturen

Sara Paracchini, Cristina Taliento iD, Giulia Pellecchia iD, Veronica Tius iD, Madalena Tavares, Chiara Borghi iD, Alessandro Antonio Buda iD, Adrien Bartoli, Nicolas Bourdel, Giuseppe Vizzielli iD

Acta Obstetricia et Gynecologica Scandinavica · 2025-11 · 104 (11) · 2054-2064

DOI: 10.1111/aogs.70045 ↗

Auf einen Blick

21 Studien zeigen für KI-Modelle in intraoperativen Videos vielversprechende Ergebnisse bei der Erkennung von Operationsphasen und anatomischen Strukturen.

Fragestellung

Wie gut eignen sich KI-Modelle zur Erkennung von Operationsphasen, anatomischen Strukturen und chirurgischen Instrumenten in intraoperativen Videos?

Methode

Systematische Übersicht; Literaturrecherche in PubMed, Web of Science und EBSCO bis März 2024; eingeschlossen waren Studien zu Machine Learning/Deep Learning für chirurgische Videoanalyse.

Ergebnisse

21 Studien. Für die Erkennung von Operationsphasen lag die Genauigkeit bei 81 % bis 93,2 %. Für anatomische Strukturen lag die Genauigkeit bei 71,4 % bis 98,1 %.

Einschränkungen

Weitere Forschung nötig zu Datensatzgrenzen, Standardisierung der Annotationen und Bias.

Schlussfolgerung der Autor:innen

Künstliche Intelligenz kann die chirurgische Präzision und den Workflow verbessern; weitere Forschung ist nötig, um Datenprobleme, Annotationen und Bias zu adressieren.

Kernaussagen

  • 21 Studien zu KI in der intraoperativen Videoanalyse
  • Operationsphasen: Genauigkeit 81 % bis 93,2 %
  • Anatomische Strukturen: Genauigkeit 71,4 % bis 98,1 %

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Systematische Übersicht in Acta Obstetricia et Gynecologica Scandinavica, published online on 2025-08-27. Written by Sara Paracchini and 9 co-authors. Institution: Gynecology Oncology Surgical Unit, Department of Obstetrics and Gynecology, Ospedale Michele e Pietro Ferrero, Verduno, Italy. Major MEDLINE topics: Operating Rooms, Artificial Intelligence, Deep Learning. Cited 23 times so far (Crossref); 39 references. The full text is freely available (open access, CC BY 4.0).

Auf einen BlickРезюмеSubjectsБиблиографски данниCiteRelated studies

Abstract (original language)

Introduction

This systematic review examines the application of multiple deep learning algorithms in the analysis of intraoperative videos to enable feature extraction and pattern recognition of surgical phases, anatomical structures, and surgical instruments. Material and Methods A comprehensive literature search was conducted across PubMed, Web of Science, and EBSCO, covering studies published until March 2024. This review includes studies that applied AI models in the operating room for surgical‐phase recognition and/or anatomical structures and instruments. Only studies utilizing machine learning or deep learning for surgical video analysis were considered. The primary outcome measures were accuracy, precision, recall, and F1 score.

Results

A total of 21 studies were included. Multilayer architecture of interconnected neural networks was predominantly used. The deep learning models demonstrated promising results, with accuracy ranging from 81% to 93.2% for surgical‐phase recognition. Anatomical structure recognition models achieved accuracy between 71.4% and 98.1%.

Conclusions

Artificial intelligence has the potential to significantly improve surgical precision and workflow, with demonstrated success in phase recognition and anatomical structure identification. However, further research is needed to address dataset limitations, standardize annotation protocols, and minimize biases.

Subjects

MeSH terms (MEDLINE)

Operating RoomsArtificial IntelligenceDeep LearningHumansVideo RecordingNeural Networks, ComputerSurgical Instruments

Author keywords

artificial intelligenceinstrument recognitionminimally invasive surgerysurgical step recognition

Authors and institutions

  • Gynecology Oncology Surgical Unit, Department of Obstetrics and Gynecology, Ospedale Michele e Pietro Ferrero, Verduno, Italy.
  • Department of Medicine (DMED), University of Udine, Udine, Italy.
  • Department of Medical Sciences, University of Ferrara, Ferrara, Italy.
  • Clinic of Obstetrics and Gynecology, "S. Maria Della Misericordia" University Hospital, Azienda Sanitaria Universitaria Friuli Centrale (ASUFC), Udine, Italy.
  • Department of Gynecology, Hospital Da Luz, Lisbon, Portugal.
  • EnCoV, Institut Pascal, UMR 6602, CNRS/UCA, Clermont-Ferrand, France.

ORCID profiles: Cristina Taliento, Giulia Pellecchia, Veronica Tius, Chiara Borghi, Alessandro Antonio Buda, Giuseppe Vizzielli

Cite

APA

Paracchini, S., Taliento, C., Pellecchia, G., Tius, V., Tavares, M., Borghi, C., Buda, A. A., Bartoli, A., Bourdel, N., & Vizzielli, G. (2025). Artificial intelligence in the operating room: A systematic review of AI models for surgical phase, instruments and anatomical structure identification. Acta Obstetricia et Gynecologica Scandinavica, 104(11), 2054-2064. https://doi.org/10.1111/aogs.70045

Vancouver

Paracchini S, Taliento C, Pellecchia G, Tius V, Tavares M, Borghi C, et al. Artificial intelligence in the operating room: A systematic review of AI models for surgical phase, instruments and anatomical structure identification. Acta Obstetricia et Gynecologica Scandinavica. 2025;104(11):2054-2064. doi:10.1111/aogs.70045

BibTeX
@article{Paracchini2025,
  author = {Paracchini, Sara and Taliento, Cristina and Pellecchia, Giulia and Tius, Veronica and Tavares, Madalena and Borghi, Chiara and Buda, Alessandro Antonio and Bartoli, Adrien and Bourdel, Nicolas and Vizzielli, Giuseppe},
  title = {Artificial intelligence in the operating room: A systematic review of AI models for surgical phase, instruments and anatomical structure identification},
  journal = {Acta Obstetricia et Gynecologica Scandinavica},
  year = {2025},
  volume = {104},
  number = {11},
  pages = {2054--2064},
  doi = {10.1111/aogs.70045}
}
Start for free →