News & Events

The Accreditation Council for Graduate Medical Education (ACGME) requires that each ophthalmology residency training program provides a wet laboratory for residents to prepare intraocular surgery prior to live human surgery. Training residents in cataract surgery has been a challenge for residency programs as a result of several factors: 1. Surgery is usually performed on an awake patient. 2. Wet lab facilities are underfunded. 3. Faculties are not funded for teaching. 4. Lack of high-fidelity, low-cost simulation models.

To increase the timeliness, objectivity, and efficiency in evaluating ophthalmology residents’ learning of cataract surgery, an automatic analysis system for cataract surgery videos has been developed by researchers at the University of Rochester to assess the surgical performance, particularly in the capsulorhexis step on the widely used Kitaro simulator. Professor Jiebo Luo and his medical colleagues utilize computer vision technologies to measure the 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 Machines of those computed measures. Comparisons of expert graders to the computer vision-based approach have demonstrated the accuracy and consistency of the computerized technique.

This work is documented in the following publication: Junhuan Zhu, Jiebo Luo, Yousuf Khalifar, "A computer vision-based approach to grade simulated cataract surgeries," Machine Vision and Applications, 26(1): 115-125, 2015. The related intellectual property is covered by US Patent No. 9,424,656, “Computer Vision Based Method and System for Evaluating and Grading Surgical Procedures” issued on August 23rd, 2016 to the University of Rochester.