Five billion people in the world lack access to quality surgical care. Surgeon skill varies dramatically, and many surgical patients suffer complications and avoidable harm. Improving surgical training and feedback would help to reduce the rate of complications-half of which have been shown to be preventable. To do this, it is essential to assess operative skill, a process that currently requires experts and is manual, time consuming, and subjective. In this work, we introduce an approach to automatically assess surgeon performance by tracking and analyzing tool movements in surgical videos, leveraging region-based convolutional neural networks. In order to study this problem, we also introduce a new dataset, m2cai16-tool-locations, which extends the m2cai16-tool dataset with spatial bounds of tools. While previous methods have addressed tool presence detection, ours is the first to not only detect presence but also spatially localize surgical tools in real-world laparoscopic surgical videos. We show that our method both effectively detects the spatial bounds of tools as well as significantly outperforms existing methods on tool presence detection. We further demonstrate the ability of our method to assess surgical quality through analysis of tool usage patterns, movement range, and economy of motion.

No abstract

No abstract

The vast majority of marginal ulcers had a favorable outcome after medical treatment. However, 9 % of patients eventually required surgical revision. Therefore, endoscopic follow-up is essential. Diabetes, smoking, and long gastric pouches were significant risk factors for marginal ulcer formation, suggesting increased acid exposure and mucosal ischemia are both involved in marginal ulcer pathogenesis. Management of these factors may prove effective in managing marginal ulcers, and tailoring postoperative proton pump inhibitor therapy to patients with multiple risk factors could be effective.