Abstract Background To introduce an approach of employing segmentation-based Artificial Intelligence (AI) models to meticulously isolate the silicon-based Laparoscopic Cholecystectomy Simulation Model (LaChSi) model within the laparoscopic trainer box, thereby enhancing realism. To assess the effectiveness of the AI Model to track camera angles to seamlessly replace the background with a virtual environment reminiscent of authentic intra-operative intra-abdominal visuals. Method The proposed methodology integrates a sophisticated segmentation model that identifies and accurately delineates the LaChSi Model within the laparoscopic Trainer box. Simultaneously, the model exhibits the capability to segregate the background, while closely monitoring camera angles for real-time adjustment. Importantly, the model is trained to perform precise segmentation of surgical tools, ensuring a comprehensive and realistic representation of the laparoscopic environment. Results Implementation of the proposed method is thought to demonstrate a notable improvement in trainees’ adaptation to surgical scenarios. The visual transition experienced by trainees moving from simulation-based surgeries to actual surgical environments will significantly reduce disparities increasing the effectiveness of the Laparoscopic simulation training. This will further avoid the need to use sensors and wires on the LaChSi model to simulate the surgical settings. Conclusion As the visual representation in simulations often deviates substantially from the intricate nuances of actual surgical procedures. This study introduces an innovative AI-based model that will contribute to the augmentation of surgical realism within simulation-based training. By effectively integrating segmentation techniques, our approach will minimise visual discontinuities, providing trainees with a more authentic and immersive experience, and ultimately fostering a smoother transition to acute surgical settings.
Read full abstract