Objective Analysis of Capsulorhexis Surgical Skills Using Video-Image Analysis
We explore the use of image analysis methods to quantitatively assess cataract surgical skills of residents from surgical video clips. The goal is to improve teaching methods by accurately measuring surgical technique. We studied the capsulorhexis part of the procedure.
Video clips of the capsulorhexis of 6 patients undergoing cataract surgery were analyzed. The clips represent varying degrees of surgeon skills, image illumination conditions, and cataract impairment. Normalized correlation was used to identify and track the limbus in the clips. Optical flow, frame subtraction, feature extraction, and edge detection methods were used to recognize needle, cannula and forceps, and count the number of insertions into the eye. The analysis algorithm was tested on clips done by surgeons ranging from a PGY 3 resident with 7 prior cases to an experienced surgeon with 10,000 prior cases.
The limbus was reliably identified and tracked through the entire video clip, even if the eye moved significantly or partly left the field of view. Inter-frame subtraction of the stabilized (registered) sequence identified moving objects (surgical instruments) within the eye. Line segment detection then outlined specific instruments. Further work to count the number of insertions and attempts at grasping the capsule is underway.
Video image analysis provides an objective way to measure proficiency in the capsulorhexis part of cataract surgery, and may provide new tools to understand the learning of surgical skills.