Suvranu De

Objective skill assessment in high-stakes procedural environments requires models that not only decode underlying cognitive and motor processes but also generalize across tasks, individuals, and experimental contexts. While prior work has demonstrated the potential of functional near-infrared spectroscopy (fNIRS) for evaluating cognitive-motor performance, existing approaches are often task-specific, rely on extensive preprocessing, and lack robustness to new procedures or conditions. Here, we introduce an interpretable transformer-based foundation model trained on minimally processed fNIRS signals for cross-procedural skill assessment. Pretrained using self-supervised learning on data from laparoscopic surgical tasks and endotracheal intubation (ETI), the model achieves >88% classification accuracy on all tasks, with Matthews Correlation Coefficient exceeding 0.91 on ETI. It generalizes to a novel emergency airway procedure—cricothyrotomy—using as few as 24 labeled samples and a lightweight (<3k parameter) adapter module, attaining an AUC greater than 85%. Interpretability is achieved via a novel channel attention mechanism—developed specifically for fNIRS—that identifies functionally coherent prefrontal sub-networks validated through ablation studies. Temporal attention patterns align with task-critical phases and capture stress-induced changes in neural variability, offering insight into dynamic cognitive states.

Transoral robotic surgery (TORS) has become a well-established surgical technique for the treatment of oropharyngeal cancer, but the significant learning curve and lack of standardized credentialing have resulted in wide variability in surgical outcomes. This study aims to define procedure-specific competence standards for TORS and test whether a hierarchical task analysis (HTA)-derived procedure-based assessment (PBA) distinguishes experience levels. We examined the ability of PBA and Global Evaluative Assessment of Robotic Skills (GEARS) scores to discriminate between novice and experienced surgeons and to assess their association with operative efficiency and margin quality. We built an HTA by deconstructing the TORS lateral oropharyngectomy into tasks and subtasks. Then, PBA metrics for mucosal incision and deep dissection were developed. Two independent raters scored 40 porcine tongue TORS videos (20 novice, 20 experienced) using PBA and GEARS and recorded global and phase times. Experienced surgeons scored higher on total PBA (39.98 vs 35.35, p = 0.0055) and GEARS (22.60 vs 19.63, p = 0.0009) and showed less score variability. The largest gaps were lateral tasks: lateral mucosal incision 4.65 vs 3.60 (p = 0.0015) and lateral deep dissection 4.58 vs 3.85 (p = 0.0115). Margin scores were higher in experienced surgeons (4.38 vs 3.80, p = 0.0149). Procedures were faster overall (298.47 s vs 466.43 s, p = 0.0003) with shorter mucosal incision and deep dissection times. An HTA-derived PBA reliably differentiates TORS expertise, aligns with speed and margin quality, and identifies lateral tasks as high-yield training targets. These metrics support standardized training, assessment, and integration into VR simulation for competency-based credentialing.

This study presents a novel approach using graph neural networks to predict the risk of internal bleeding using vessel maps derived from patient CT and MRI scans, aimed at enhancing the realism of surgical simulators for emergency scenarios such as trauma, where rapid detection of internal bleeding can be lifesaving. First, medical images are segmented and converted into graph representations of the vasculature, where nodes represent vessel branching points with spatial coordinates and edges encode vessel features such as length and radius. Due to no existing dataset directly labeling bleeding risks, we calculate the bleeding probability for each vessel node using a physics-based heuristic, peripheral vascular resistance via the Hagen-Poiseuille equation. A graph attention network is then trained to regress these probabilities, effectively learning to predict hemorrhage risk from the graph-structured imaging data. The model is trained using a tenfold cross-validation on a combined dataset of 1708 vessel graphs extracted from four public image datasets (MSD, KiTS, AbdomenCT, CT-ORG) with optimization via the Adam optimizer, mean squared error loss, early stopping, and L2 regularization. Our model achieves a mean R-squared of 0.86, reaching up to 0.9188 in optimal configurations and low mean training and validation losses of 0.0069 and 0.0074, respectively, in predicting bleeding risk, with higher performance on well-connected vascular graphs. Finally, we integrate the trained model into an immersive virtual reality environment to simulate intra-abdominal bleeding scenarios for immersive surgical training. The model demonstrates robust predictive performance despite the inherent sparsity of real-life datasets.

Virtual Bariatric Endoscopy (ViBE) simulator is designed for Endoscopic Sleeve Gastroplasty (ESG), a minimally invasive bariatric procedure. While virtual simulators exist for bariatric surgeries, there has been a lack of ESG-specific tools. The ViBE simulator fills this gap by providing a cost-effective alternative to physical models and enhancing ESG training. The simulator consists of three main components: software simulation, hardware, and a hardware interface linking the two. The software focuses on ESG techniques like marking, suturing, and tissue-pulling, with an algorithm for suturing and soft-body physics simulations. The simulator features two human-computer interfaces: one using USB-HID protocol with optical encoders and ARM Cortex M7 devices, and another using computer vision for delicate instruments. The computer vision interface simplifies mechanical design. Performance tests showed an average of 55 FPS, with render times between 2ms and 4ms and solver times between 16ms and 18ms. The end-to-end delay was under 75ms, and haptic feedback forces updated every 1ms. The ViBE simulator aims to improve ESG training and suturing techniques, demonstrating its potential as an effective learning tool with efficient software performance and minimal hardware latency.

Laparoscopic cholecystectomy (LC) is the standard procedure for gallbladder removal, but improper identification of anatomical structures can lead to biliary duct injury (BDI). The critical view of safety (CVS) is a standardized technique designed to mitigate this risk. However, existing surgical training systems primarily emphasize haptic feedback and physical skill development, making them expensive and less accessible. This paper presents the next-generation Portable Camera-Aided Surgical Simulator (PortCAS), a cost-effective, portable, vision-based surgical training simulator designed to enhance cognitive skill acquisition in LC. The system consists of an enclosed physical module equipped with a vision system, a single-board computer for real-time instrument tracking, and a virtual simulation interface that runs on a user-provided computer. Unlike traditional simulators, PortCAS prioritizes cognitive training over force-based interactions, eliminating the need for costly haptic components. The system was evaluated through user studies assessing accuracy, usability, and training effectiveness. Results demonstrate that PortCAS provides a sufficiently accurate tracking performance for training surgical skills such as CVS, offering a scalable and accessible solution for surgical education.

Purpose Current training methods for surgical trainees are inadequate because they are costly, low-fidelity, or have a low skill ceiling. This work aims to expand available virtual reality training options by developing a VR trainer for straight coloanal anastomosis (SCA), one of the Colorectal Objective Structured Assessment of Technical Skills (COSATS) tasks. Methods We developed a VR-based SCA simulator to evaluate trainees based on their performance. To increase the immersiveness, alongside the VR headset, we used haptics as the primary method of interaction with the simulation. We also implemented objective performance metrics to evaluate trainee performance throughout the simulation. Results We presented our performance metrics to 27 participants for an Expert Consensus Survey (5-point Likert scale) and created weights for our metrics. The weighted average scores for the 24 task-specific metrics ranged from 3.5 to 5. Additionally, for the general metrics, the scores spanned from 3.3 to 4.6. In the second phase of our study, we conducted a study with 16 participants (novice n = 9, expert n = 7). Based on the performance, experts outperformed novices by 8.56% when referring to the total score (p = 0.0041). Three of the measurable metrics, purse suture (p = 0.0797), retracting the anvil (p = 0.0738), and inserting the colonoscope (p = 0.0738) showed a significant difference between experts and novices. Experts were smoother with their hand motions by 3.67% per second and took 70.77% longer paths to complete the same tasks. Conclusion We created a high-fidelity coloanal anastomosis VR simulator. The simulator runs in real-time while allowing high immersion with a VR headset, deformable bodies, and a haptic device while providing objective feedback through performance metrics. Experts obtained higher scores throughout the simulation, including the quiz to demonstrate procedural knowledge, the metrics to demonstrate experience in steps/procedure, and control of their basic surgical skills and hand movements.

As trainees practice fundamental surgical skills, they typically rely on performance measures, such as time and errors, to determine improvement. For example, each manual skill of the fundamentals of laparoscopic surgery (FLS) curriculum, the standard for basic surgical skills training of US-based surgeons, is evaluated based on a score combining the completion time and task-specific errors. However, these measures may be limited in their sensitivity and utility for providing feedback to trainees to improve performance. In addition, there is often a mismatch between these measures that are the focus of simulation training and the expectations of experienced surgeons in the clinical environment.¹ As a result, a recent survey determined that many still require additional training in laparoscopic suturing, including needle positioning and bimanual coordination, after completing residency.² Thus, there has been a push in surgical skills training to support the development of objective metrics to improve assessment and training.

To ensure satisfactory clinical outcomes, surgical skill assessment must be objective, time-efficient, and preferentially automated—none of which is currently achievable. Video-based assessment (VBA) is being deployed in intraoperative and simulation settings to evaluate technical skill execution. However, VBA is manual, time-intensive, and prone to subjective interpretation and poor inter-rater reliability. Herein, we propose a deep learning (DL) model that can automatically and objectively provide a high-stakes summative assessment of surgical skill execution based on video feeds and low-stakes formative assessment to guide surgical skill acquisition. Formative assessment is generated using heatmaps of visual features that correlate with surgical performance. Hence, the DL model paves the way for the quantitative and reproducible evaluation of surgical tasks from videos with the potential for broad dissemination in surgical training, certification, and credentialing.

The ability to provide realistic haptic feedback is indispensable for virtual-reality (VR) based endoscopic colorectal surgery simulators. Despite its importance, force feedback is commonly simulated by simplified approximations with parameters manually tuned in preliminary evaluations due to the complexity of the dynamics of haptic interaction in colonoscopy interventions. Endoscopic submucosal dissection (ESD) is a particularly challenging intervention that requires advanced manual skills for endoscopic control. This work proposes a mechanical impedance model for haptic interactions in ESD formulated via an experimental methodology applied to endoscopic colorectal interventions in general. The developed model is shown to capture the variations in the interaction force during two operations performed at distinct locations on a porcine sample. Salient cues in the recorded haptic interaction data are presented, and changes in the impedance characteristics of the tool-tissue interaction between the steps of the operation are analyzed.