As the number of robotic surgery procedures has increased, so has the importance of evaluating surgical skills in these techniques. It is difficult, however, to automatically and quantitatively evaluate surgical skills during robotic surgery, as these skills are primarily associated with the movement of surgical instruments. This study proposes a deep learning-based surgical instrument tracking algorithm to evaluate surgeons’ skills in performing procedures by robotic surgery. This method overcame two main drawbacks: occlusion and maintenance of the identity of the surgical instruments. In addition, surgical skill prediction models were developed using motion metrics calculated from the motion of the instruments. The tracking method was applied to 54 video segments and evaluated by root mean squared error (RMSE), area under the curve (AUC), and Pearson correlation analysis. The RMSE was 3.52 mm, the AUC of 1 mm, 2 mm, and 5 mm were 0.7, 0.78, and 0.86, respectively, and Pearson’s correlation coefficients were 0.9 on the x-axis and 0.87 on the y-axis. The surgical skill prediction models showed an accuracy of 83% with Objective Structured Assessment of Technical Skill (OSATS) and Global Evaluative Assessment of Robotic Surgery (GEARS). The proposed method was able to track instruments during robotic surgery, suggesting that the current method of surgical skill assessment by surgeons can be replaced by the proposed automatic and quantitative evaluation method.

Background: Federated learning is a decentralized approach to machine learning; it is a training strategy that overcomes medical data privacy regulations and generalizes deep learning algorithms. Federated learning mitigates many systemic privacy risks by sharing only the model and parameters for training, without the need to export existing medical data sets. In this study, we performed ultrasound image analysis using federated learning to predict whether thyroid nodules were benign or malignant. Objective: The goal of this study was to evaluate whether the performance of federated learning was comparable with that of conventional deep learning. Methods: A total of 8457 (5375 malignant, 3082 benign) ultrasound images were collected from 6 institutions and used for federated learning and conventional deep learning. Five deep learning networks (VGG19, ResNet50, ResNext50, SE-ResNet50, and SE-ResNext50) were used. Using stratified random sampling, we selected 20% (1075 malignant, 616 benign) of the total images for internal validation. For external validation, we used 100 ultrasound images (50 malignant, 50 benign) from another institution. Results: For internal validation, the area under the receiver operating characteristic (AUROC) curve for federated learning was between 78.88% and 87.56%, and the AUROC for conventional deep learning was between 82.61% and 91.57%. For external validation, the AUROC for federated learning was between 75.20% and 86.72%, and the AUROC curve for conventional deep learning was between 73.04% and 91.04%. Conclusions: We demonstrated that the performance of federated learning using decentralized data was comparable to that of conventional deep learning using pooled data. Federated learning might be potentially useful for analyzing medical images while protecting patients’ personal information.

Background. Laparoscopic lateral transperitoneal adrenalectomy (LTA) has been the standard method for resecting benign adrenal gland tumors. Recently, however, laparoscopic posterior retroperitoneal adrenalectomy (PRA) has been more popular as an alternative method. This systematic review evaluates current evidence on adrenalectomy techniques, comparing laparoscopic LTA with PRA and laparoscopic adrenalectomy with robotic adrenalectomy.Methods. PubMed, Embase, and ISI Web of Knowledge databases were searched systematically for studies comparing surgical outcomes of laparoscopic LTA versus PRA and laparoscopic versus robotic adrenalectomy. The studies were evaluated according to the PRISMA statement.Results. Eight studies comparing laparoscopic PRA and LTA showed that laparoscopic PRA was superior or at least comparable to laparoscopic LTA in operation time, blood loss, pain score, hospital stay, and return to normal activity. Conversion rates and complication rates were similar. Six studies comparing robotic and laparoscopic adrenalectomy found that outcomes and complications were similar.Conclusion. Laparoscopic PRA was more effective than LTA, especially in reducing operation time and hospital stay, but there was no evidence showing that robotic adrenalectomy was superior to laparoscopic adrenalectomy. Cost reductions and further technical advances are needed for wider application of robotic adrenalectomy.

Context: The long-term quality of life (QoL) in patients with low-risk papillary thyroid microcarcinoma (PTMC) underwent active surveillance (AS) and immediate surgery is unclear. Objective: The aim of this study was to investigate the effect of initial treatment choice on 2-year QoL in patients with low-risk PTMC Design, Setting, and Participants: We analyzed 2652 QoL surveys from 1055 subjects enrolled in ongoing multicenter prospective cohort study on active surveillance of PTMC, in which the median follow-up duration was 24.4 months. Major Outcome Measure: We evaluated QoL of patients with low-risk PTMC according to their treatment modality using generalized estimating equation. Results: Six hundred and seventy-four subjects (male = 161; mean age = 48.8 ± 11.9 years) with low-risk PTMC chose AS while 381 subjects (male = 75; mean age = 45.7 ± 10.4 years) chose immediate surgery, including lobectomy/isthmusectomy (L/I) and total thyroidectomy (TT). Among the 817 subjects who completed baseline QoL surveys, 2-year QoL was good in order of AS (n = 500), L/I (n = 238), and TT (n = 79) groups after adjustment for age, sex, baseline tumor size, and baseline QoL scores. Among the 101 subjects who changed their treatment from AS to surgery during the follow-up period, 35 subjects who changed treatment due to disease progression had better QoL than 66 subjects who had no disease progression. Conclusions: This study identified QoL as a major issue in choosing an initial treatment of low-risk PTMC and highlighted the possibility of using AS as the primary treatment.

Chai YJ, et al. Ann Surg Treat Res. 2015 Dec;89(6):295-299. http://dx.doi.org/10.4174/astr.2015.89.6.295