This letter proposes a novel video-based, contrastive regression architecture, Contra-Sformer, for automated surgical skill assessment in robot-assisted surgery. The proposed framework is structured to capture the differences in the surgical performance, between a test video and a reference video which represents optimal surgical execution. A feature extractor combining a spatial component (ResNet-18), supervised on frame-level with gesture labels, and a temporal component (TCN), generates spatio-temporal feature matrices of the test and reference videos. These are then fed into an action-aware Transformer with multi-head attention that produces inter-video contrastive features at frame level, representative of the skill similarity/deviation between the two videos. Moments of sub-optimal performance can be identified and temporally localized in the obtained feature vectors, which are ultimately used to regress the manually assigned skill scores. Validated on the JIGSAWS dataset, Contra-Sformer achieves competitive performance (Spearman 0.65–0.89), with a normalized mean absolute error between 5.8%-13.4% on all tasks and across validation setups.
Background: Manual objective assessment of skill and errors in minimally invasive surgery have been validated with correlation to surgical expertise and patient outcomes. However, assessment and error annotation can be subjective and are time-consuming processes, often precluding their use. Recent years have seen the development of artificial intelligence models to work towards automating the process to allow reduction of errors and truly objective assessment. This study aimed to validate surgical skill rating and error annotations in suturing gestures to inform the development and evaluation of AI models. Methods: SAR-RARP50 open data set was blindly, independently annotated at the gesture level in Robotic-Assisted Radical Prostatectomy (RARP) suturing. Manual objective assessment tools and error annotation methodology, Objective Clinical Human Reliability Analysis (OCHRA), were used as ground truth to train and test vision-based deep learning methods to estimate skill and errors. Analysis included descriptive statistics plus tool validity and reliability. Results: Fifty-four RARP videos (266 min) were analysed. Strong/excellent inter-rater reliability (range r = 0.70–0.89, p < 0.001) and very strong correlation (r = 0.92, p < 0.001) between objective assessment tools was demonstrated. Skill estimation of OSATS and M-GEARS had a Spearman’s Correlation Coefficient 0.37 and 0.36, respectively, with normalised mean absolute error representing a prediction error of 17.92% (inverted “accuracy” 82.08%) and 20.6% (inverted “accuracy” 79.4%) respectively. The best performing models in error prediction achieved mean absolute precision of 37.14%, area under the curve 65.10% and Macro-F1 58.97%. Conclusions: This is the first study to employ detailed error detection methodology and deep learning models within real robotic surgical video. This benchmark evaluation of AI models sets a foundation and promising approach for future advancements in automated technical skill assessment. Graphical
Microsurgery serves as the foundation for numerous operative procedures. Given its highly technical nature, the assessment of surgical skill becomes an essential component of clinical practice and microsurgery education. The interaction forces between surgical tools and tissues play a pivotal role in surgical success, making them a valuable indicator of surgical skill. In this study, we employ six distinct deep learning architectures (LSTM, GRU, Bi-LSTM, CLDNN, TCN, Transformer) specifically designed for the classification of surgical skill levels. We use force data obtained from a novel sensorized surgical glove utilized during a microsurgical task. To enhance the performance of our models, we propose six data augmentation techniques. The proposed frameworks are accompanied by a comprehensive analysis, both quantitative and qualitative, including experiments conducted with two cross-validation schemes and interpretable visualizations of the network’s decision-making process. Our experimental results show that CLDNN and TCN are the top-performing models, achieving impressive accuracy rates of 96.16% and 97.45%, respectively. This not only underscores the effectiveness of our proposed architectures, but also serves as compelling evidence that the force data obtained through the sensorized surgical glove contains valuable information regarding surgical skill.
Purpose: Accurate assessment of surgical complexity is essential in laparoscopic cholecystectomy (LC), where severe inflammation is associated with longer operative times and increased risk of postoperative complications. The Parkland Grading Scale (PGS) provides a clinically validated framework for stratifying inflammation severity; however, its automation in surgical videos remains largely unexplored, particularly in realistic scenarios where complete videos must be analyzed without prior manual curation. Methods: In this work, we introduce STC-Net, a novel framework for Single-Timestamp-based Complexity estimation in LC via the PGS, designed to operate under weak temporal supervision. Unlike prior methods limited to static images or manually trimmed clips, STC-Net operates directly on full videos. It jointly performs temporal localization and grading through a localization, window proposal, and grading module. We introduce a novel loss formulation combining hard and soft localization objectives and background-aware grading supervision. Results: Evaluated on a private dataset of 1859 LC videos, STC-Net achieves an accuracy of 60.18% and an F1-score of 59.68%, outperforming non-localized baselines by over 12% in both metrics and highlighting the effectiveness of weak supervision for surgical complexity assessment. Conclusion: STC-Net demonstrates a scalable and effective approach for automated PGS-based surgical complexity estimation from full LC videos, making it promising for postoperative analysis and surgical training.