Student-developed machine-learning techniques make surgeries
Now open: Certificate Course in Management of Covid-19 by Govt. Of Gujarat and PlexusMDKnow more...Now open: Certificate Course in Management of Covid-19 by Govt. Of Gujarat and PlexusMDKnow more...
An interdisciplinary fellowship with the Data Science Institute has resulted in a promising machine-learning technology that can effectively track complex surgical activity, thus having the potential to improve patient outcomes, safety, and documentation.

Open surgery represents a dominant proportion of procedures performed but has lagged behind endoscopic surgery in video-based insights due to the difficulty obtaining the high-quality open surgical video. Automated detection of the open surgical wound would enhance tracking and stabilization of body-worn cameras to optimize video capture for these procedures.

Investigators present results using a mask R-CNN to identify the surgical wound (the “area of interest”, AOI) in image sets derived from 27 open neck procedures (a 2310-image training/validation set and an 1163-image testing set).

Bounding box application to the surgical wound was reliable in the testing sets with a <5% false-positive rate (recognizing non-wound areas as the AOI). Mask application to greater than 50% of the wound area also had good success under parameters set for high specificity. When applied to short video clips as proof-of-principle, the model performed well both with emerging AOI (i.e., identifying the wound as incisions were developed) and with the recapture of the AOI following obstruction. They identified image lighting quality and the presence of distractors (e.g., bloody sponges) as the primary sources of model errors on visual review.

These data serve as the first demonstration of open surgical wound detection using first-person video footage.

Medical Imaging 2021: Image-Guided Procedures, Robotic Interventions, and Modeling (2021)