Related Experiment Video
Updated: Jan 12, 2026
Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System
Published on: October 16, 2013
Objective Assessments and Annotation Frameworks in Microscopic Surgery: A Scoping Review
Prishae Wilson1, Madison M Doucette2, James R Dornhoffer3
1Department of Otolaryngology-Head and Neck Surgery, Mayo Clinic in Florida, Jacksonville, Florida, USA.
Objective:
Microscopic surgery assessment tools vary in objectivity and requirements for determining surgical proficiency. Artificial intelligence methods for objective microsurgical analysis have become more common, but their applications to mastoidectomy have not been reconciled with earlier efforts. This scoping review aimed to (1) compile and compare objective features and assessment targets of microscopic surgery analysis tools and (2) inform the development of a standardized annotation framework for mastoidectomy.
Data Sources:
Ovid MEDLINE®, Embase (Ovid), Cochrane Central Register of Controlled Trials (CENTRAL, Ovid), Cochrane Database of Systematic Reviews (Ovid), and Scopus.
Review Methods:
A scoping review of English-language, full-text articles describing any objective analysis tool for microscopic surgery performed by participants of any level. Extracted data included procedure type, evaluation modality, and classification into five domains: checklist/rating-based, instrument motion analysis, error identification, workflow modeling, and artificial intelligence-assisted feedback.
Results:
Of 2203 screened studies, 52 met the inclusion criteria across otolaryngology, ophthalmology, and neurological surgery. Manual assessments (n = 42, 80.8%) primarily used checklists, rating scales, or end-product evaluations. Automated assessments (n = 10, 19.2%) incorporated motion tracking and artificial intelligence-assisted feedback. Otolaryngology contributed 28 tools, 22 of which evaluated mastoidectomy, cochlear implantation, or temporal bone dissection. Virtual reality was the most commonly reported training platform (n = 13).
Conclusion:
Although instrument tracking and artificial intelligence-assisted feedback have been explored, evaluation of microscopic surgery remains largely manual and subjective, with limited adoption of automated assessment tools. The lack of a standardized framework for automated mastoidectomy assessment represents a potential area for future development.
