A computer vision-based approach to grade simulated cataract surgeries

Abstract

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

Machine learning for technical skill assessment in surgery: a systematic review

“…Two studies employed the use of animal models in order to conduct procedures such as laparoscopic cholecystectomy. 20/66 studies assessed laparoscopic tasks, 26/66 studies assessed robotic tasks, and the remainder assessed a combination of open tasks such as hand tying or open suturing, or procedures such as arthroscopy 14 and capsulorhexis 15 . The use of simulators allowed the assessment of more complicated tasks including procedures such as discectomy 16 or hemilaminectomy 17 .…”

“…• Support vector clustering. • Semi supervised SVM 14 , 15 , 17 , 23 , 59 , 61 , 65 , 67 , 71 , 73 , 74 , 80 , 81 , 86 , 87 , 93 , 100 k-nearest neighbors (kNN) Supervised classification algorithm which groups the points of each class together. During inferencing, the Euclidean distances between the new observed data point and the training data points are calculated.…”

“…The SVM classifier relies on the multi-dimensional handcrafted features and metrics relevant to the tasks of interest derived from original signals, such as bio-signal 44 , video 45 , kinematic data 46 . Such features include energy-based metrics 14 (which include total work, the sum of the changes in potential energy, and the sum of the changes in kinetic energy when performing a specific task), computer vision-based features 15 (such as duration, size, centrality, circularity, and motion stability), and other measurable indexes (such as the position, angle, and force application of instruments and volume of simulated tissue removed 17 . These features vectors or matrix are often linearly inseparable.…”

An automated skills assessment framework for laparoscopic training tasks

“…Although this is a promising approach, an additional analysis step is required to conclude about the surgeon's level of expertise. In the field of eye surgery, a vision‐based approach was recently proposed for evaluating the performance of a cataract surgery task on a wet‐lab simulator …”

“…In the field of eye surgery, a vision-based approach was recently proposed for evaluating the performance of a cataract surgery task on a wet-lab simulator. 29 The proposed framework focuses on the automated assessment of trainee competency for basic tasks such as peg transfer and knot tying even without a priori knowledge of the task type. The developed framework utilizes robust techniques for tracking both graspers throughout the scene without a priori assumptions on their placement or utilization of specific markers.…”