Tool Detection in Laparoscopic Datasets for Surgical Training in Low-Resource Settings

In low-resource settings, there is a critical need for skilled surgeons. Alternative training processes that include computer-assisted surgical skill evaluation are essential to address this gap. Using tool detection, surgical videos can be leveraged to derive insights into surgical skill assessment. This study implements and tests multiple anchor-based and anchor-free deep learning state-of-the-art models with various hardware configurations on a newly curated in-house laparoscopic box-trainer dataset, emphasising real-time performance on low-cost embedded devices. Overall, the best model achieved 99.5% mAP50 and 94.5% mAP50:95 at 3.1ms (~322.6 FPS) on an edge computing device, comparable to resources in low-resource settings. The results highlight the models' potential for effective real-time surgical tool detection, even in resource-constrained environments, which can help set the backbones for further surgical skill methods.