Action classification for endoscopic pituitary adenoma resection: a consensus-based study - Summary - MDSpire

Action classification for endoscopic pituitary adenoma resection: a consensus-based study

  • By

  • Joachim Starup-Hansen

  • Danyal Z. Khan

  • Adrito Das

  • Joao Paulo Almeida

  • Sophia Bano

  • Anouk Borg

  • Kevin Cleary

  • Neil Dorward

  • Juan C. Fernandez-Miranda

  • Eduardo Torres-Rodríguez

  • Danail Stoyanov

  • Recai Yilmaz

  • Peter Weir

  • Daniel A. Donoho

  • Hani J. Marcus

  • April 11, 2026

  • 0 min

Share

Objective:

To develop a reproducible and consensus-based action-level ontology for pituitary surgery, facilitating AI applications in surgical performance assessment, with a clear definition of 'action-level ontology'.

Key Findings:
  • The study established a universal classification ontology for actions in endoscopic pituitary adenoma surgery, which can enhance surgical education.
  • Action analysis can enhance surgical skill training and improve patient outcomes.
  • The framework allows for standardized data curation and AI model development, paving the way for future research.
Interpretation:

The development of a structured action classification framework is essential for advancing AI applications in surgical performance assessment, particularly in neurosurgery, by providing a clear methodology for evaluating surgical actions.

Limitations:
  • The study is limited to specific surgical videos from two institutions, which may not represent all surgical practices, potentially affecting the generalizability of the findings.
  • The effectiveness of the action classification system in predicting outcomes requires further validation, which is necessary to establish its reliability.
Conclusion:

This study lays the groundwork for future AI-driven analyses of surgical performance in pituitary adenoma resections, potentially improving surgical education and patient care.

Original Source(s)

Related Content