Automated surgical OSATS prediction from videos

View/ Open
Date
2014-04Author
Sharma, Yachna
Plötz, Thomas
Hammerla, Nils
Mello, Sebastian
McNaney, Roisin
Olivier, Patrick
Deshmukh, Sandeep
McCaskie, Andrew
Essa, Irfan
Metadata
Show full item recordAbstract
The assessment of surgical skills is an essential part of medical training. The prevalent manual evaluations by expert surgeons are time consuming and often their outcomes vary substantially from one observer to another. We present a video-based framework for automated evaluation of surgical skills
based on the Objective Structured Assessment of Technical Skills (OSATS) criteria. We encode the motion dynamics via frame kernel matrices, and represent the motion granularity by texture features. Linear discriminant analysis is used to derive a reduced dimensionality feature space followed by
linear regression to predict OSATS skill scores. We achieve statistically significant correlation (p-value <0.01) between the ground-truth (given by domain experts) and the OSATS scores predicted by our framework.