ABSTRACT
PURPOSE: Lumbar discectomy is among the most common spine procedures in the US, with 300,000 procedures performed each year. Like other surgical procedures, this procedure is not excluded from potential complications. This paper presents a video annotation methodology for microdiscectomy including the development of a surgical workflow. In future work, this methodology could be combined with computer vision and machine learning models to predict potential adverse events. These systems would monitor the intraoperative activities and possibly anticipate the outcomes. METHODS: A necessary step in supervised machine learning methods is video annotation, which involves labeling objects frame-by-frame to make them recognizable for machine learning applications. Microdiscectomy video recordings of spine surgeries were collected from a multi-center research collaborative. These videos were anonymized and stored in a cloud-based platform. Videos were uploaded to an online annotation platform. An annotation framework was developed based on literature review and surgical observations to ensure proper understanding of the instruments, anatomy, and steps. RESULTS: An annotated video of microdiscectomy was produced by a single surgeon. Multiple iterations allowed for the creation of an annotated video complete with labeled surgical tools, anatomy, and phases. In addition, a workflow was developed for the training of novice annotators, which provides information about the annotation software to assist in the production of standardized annotations. CONCLUSIONS: A standardized workflow for managing surgical video data is essential for surgical video annotation and machine learning applications. We developed a standard workflow for annotating surgical videos for microdiscectomy that may facilitate the quantitative analysis of videos using supervised machine learning applications. Future work will demonstrate the clinical relevance and impact of this workflow by developing process modeling and outcome predictors.
ABSTRACT
Objective: To compare the dusting vs fragmentation modes with thulium fiber laser (TFL) in retrograde intrarenal surgery (RIRS) for upper tract stones using the same fixed low-power settings in both the arms. The primary objective was to compare the stone-free rate (SFR) and secondary objectives were to compare mean operating times, hospital stay duration, complication rates, need for secondary procedures, and laser efficacy. Materials and Methods: A prospective randomized trial, with patients having proximal ureteral or renal stones of 10-20 mm and planned for RIRS was done at a single institute. A total of 60 consecutively admitted patients with signed consent were included for randomization with 30 patients in each arm of dusting and fragmentation modes. Results: Median age in dusting and fragmentation arms of 41.5 and 45.5 years, median stone size of 10.45 and 12.25 mm, median stone volume of 351.6 and 490.7 mm3, and median stone density of 1263.5 HU in both arms with comparable hospital stay of median of 2 days in both arms. Lasing time was significantly lesser in the fragmentation group (20.5 minutes; interquartile range [IQR] 15.12-31.62) than in the dusting group (34.25 minutes, IQR 26.62-38.62, p < 0.001). Higher ablation speed for fragmentation mode (0.405 mm3/sec, IQR 0.337-0.635) than for dusting mode (0.17 mm3/sec, IQR 0.135-0.325, p < 0.001). SFRs and complication rates were comparable in both the arms. Conclusion: TFL in fragmentation mode has shorter lasing times and better laser efficacy than dusting mode with comparable minimal complications, SFRs, and hospital stay duration. Clinical Trial Registration number: CTRI050827.