Background Artificial Intelligence (AI) holds tremendous potential to reduce surgical risks and improve surgical assessment. Machine Learning, a subfield of AI, relies on video and image data, where annotations provide veracity about the desired target features. Yet, methodological annotation explorations are limited to date. Here, we provide an exploratory analysis of the requirements and methods of instrument annotation in a multi-institutional team from two specialized AI centers and compile a structured manual for future AI projects focusing on instrument detection. Methods We developed a bottom-up approach for team annotation of robotic instruments in robotassisted partial nephrectomy (RAPN), after which it was validated in robot-assisted minimally invasive esophagectomy (RAMIE). Furthermore, instrument annotation methods were evaluated for their use in Machine Learning algorithms. Overall, we evaluated the efficiency and transferability of the proposed team approach and quantified performance metrics (e.g. time per frame required for each annotation modality) between RAPN and RAMIE.
ResultsThe proposed annotation methodology was transferrable between both RAPN and RAMIE. The bottom-up approach of annotation management and training resulted in accurate annotations and demonstrated efficiency in annotating large datasets and diverse annotator groups. The average annotation time for RAPN for pixel annotation ranged from 4.49 to 12.6 minutes per image; for vector annotation this was decreased to 2.92 minutes. Similar ranges of pixel annotation times were denoted for RAMIE. Lastly, we elaborate on common pitfalls encountered throughout the annotation process. Conclusions We propose a successful bottom-up approach for annotator team composition, applicable to any annotation project. Our results set the foundation to start AI projects for instrument detection, segmentation and pose estimation. Due to the immense annotation burden resulting from spatial instrumental annotation, further analysis into sampling frequency and annotation detail needs to be conducted.
Background: Retzius-sparing robot-assisted radical prostatectomy (RS-RARP) has been shown to lead to better outcomes regarding early continence compared to standard anterior RARP (SA-RARP). The goal of this study was to assess the feasibility and safety of implementing RS-RARP in a tertiary center with experience in SA-RARP. Methods: From February 2020, all newly diagnosed non-metastatic prostate cancer patients for whom RARP was indicated were evaluated for RS-RARP. Data from the first 100 RS-RARP patients were prospectively collected and compared with data from the last 100 SA-RARP patients. Patients were evaluated for Clavien Dindo grade ≥3a complications, urinary continence after 2 and 6 weeks, 3, 6 and 12 months, erectile function, positive surgical margins (PSMs) and biochemical recurrence (BCR). Results: There was no significant difference in postoperative complications at Clavien-Dindo grade ≥3a (SA-RARP: 6, RS-RARP: 4; p = 0.292). At all time points, significantly higher proportions of RS-RARP patients were continent (p < 0.001). No significant differences in postoperative potency were observed (52% vs. 59%, respectively, p = 0.608). PSMs were more frequent in the RS-RARP group (43% vs. 29%, p = 0.034), especially in locally advanced tumors (pT3: 64.6% vs. 43.8%, p = 0.041—pT2: 23.5% vs. 15.4%, p = 0.329). The one-year BCR-free survival was 82.6% vs. 81.6% in the SA-RARP and RS-RARP groups, respectively (p = 0.567). The median follow-up was 22 [18–27] vs. 24.5 [17–35] months in the RS-RARP and SA-RARP groups, respectively (p = 0.008). Conclusions: The transition from SA-RARP to RS-RARP can be safely performed by surgeons proficient in SA-RARP. Continence results after RS-RARP were significantly better at any time point. A higher proportion of PSMs was observed, although it did not result in a worse BCR-free survival.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.