This was an experimental study for development and validation using a multi-institutional data set consisting of 337 laparoscopic colorectal surgical videos, which aimed to verify an automatic surgical instrument recognition model with broad applicability to multiple types of instruments, and pixel-level high recognition accuracy was feasible.
The developed convolutional neural network–based instance segmentation model can be used to recognize multiple types of instruments with high accuracy simultaneously, and the mean average precisions of the instance segmentation for surgical instruments were 90.9% for 3 instruments, 90.3% for 4 instruments, 91.6% for 6 instruments, and 91.8% for 8 instruments.
The recognition results of instance segmentation for 8 types of surgical instruments in the representative case of laparoscopic sigmoid colon resection are shown in this Video.
Click the Related Article link for full details.
JN Learning™ is the home for CME and MOC from the JAMA Network. Search by specialty or US state and earn AMA PRA Category 1 Credit(s)™ from articles, audio, Clinical Challenges and more. Learn more about CME/MOC
You currently have no searches saved.
You currently have no courses saved.