Simulated outcomes for durotomy repair in minimally invasive spine surgery

Abstract

Minimally invasive spine surgery (MISS) is increasingly performed using endoscopic and microscopic visualization, and the captured video can be used for surgical education and development of predictive artificial intelligence (AI) models. Video datasets depicting adverse event management are also valuable, as predictive models not exposed to adverse events may exhibit poor performance when these occur. Given that no dedicated spine surgery video datasets for AI model development are publicly available, we introduce Simulated Outcomes for Durotomy Repair in Minimally Invasive Spine Surgery (SOSpine). A validated MISS cadaveric dural repair simulator was used to educate neurosurgery residents, and surgical microscope video recordings were paired with outcome data. Objects including durotomy, needle, grasper, needle driver, and nerve hook were then annotated. Altogether, SOSpine contains 15,698 frames with 53,238 annotations and associated durotomy repair outcomes. For validation, an AI model was fine-tuned on SOSpine video and detected surgical instruments with a mean average precision of 0.77. In summary, SOSpine depicts spine surgeons managing a common complication, providing opportunities to develop surgical AI models.

Fig. 1

Sample tooltip and bounding box instrument annotations.

Fig. 2

Tool presence comparison between ground-truth and CV detections for a selected SOSpine trial. Surgical actions are highlighted in red, blue, and grey.

Fig. 3

YOLOv4 deep learning instrument detection precision recall curves and average precision. AP, average precision.

Fig. 4

Tool presence comparison between ground-truth and detections for all SOSpine test set trials.