Computer vision based method and system for evaluating and grading surgical procedures

摘要

To increase the timeliness, objectivity, and efficiency in evaluating surgical procedures such as those performed by ophthalmology residents' learning of cataract surgery, an automatic analysis system for surgeries such as cataract surgery is provided to assess performance, particularly in the capsulorrhexis step on the Kitaro simulator. Computer vision technologies are employed to measure performance of this critical step including duration, centrality, circularity, size, as well as motion stability during the capsulorrhexis procedure. Consequently, a grading mechanism is established based on either linear regression or non-linear classification via Support Vector Machine (SVM) of those computed measures. Comparisons of expert graders to the computer vision based approach have demonstrated the accuracy and consistency of the computerized technique.

主权项

1. A computer-based method for evaluating cataract surgical procedures by medical personnel, the method comprising the steps of:
providing surgical procedure video data on a computer having a processor, memory and computer readable media and storing said surgical procedure video data on the computer readable media; identifying with a transform stored on the computer readable media a pupil area of an eye in the surgical procedure video data; segmenting the surgical procedure video data based on changes in the pupil area location; identifying in the surgical procedure video data each segment as an independent surgical procedure; determining time duration of each independent surgical procedure by the time duration of each segment; assigning a time duration value to the each independent surgical procedure; identifying with the transform stored on the computer readable media key images that indicate completion of a capsulorrhexis procedure; within the identified key images, measuring spatial features of a hole made in an anterior capsule of a cataract of the eye or simulated eye during capsulorrhexis; assigning a value to the measured spatial features of the hole; applying optical flow and resulting optical flow values to compute motion during the capsulorrhexis procedure; calculating a stability of the surgical procedure from the computed motion; assigning a value to the calculated stability of the surgical procedure; and outputting said assigned values for evaluation of the surgical procedure.