Creating AI models with expert level understanding of surgery.
Using machine learning, deep neural networks, and multi-modal large language models, our group trains AI models to understand surgical video at an expert level. Such models are used to investigate perception of surgical video information, supplement surgical education and assist with prospective surgical action decision making (Skinner et al., 2024).
References
2024
NPJ Digit. Med.
Real-time near infrared artificial intelligence using scalable non-expert crowdsourcing in colorectal surgery
G. Skinner, T. Chen, G. Jentis, and 6 more authors
Surgical artificial intelligence (AI) has the potential to improve patient safety and clinical outcomes. To date, training such AI models to identify tissue anatomy requires annotations by expensive and ratelimiting surgical domain experts. Herein, we demonstrate and validate a methodology to obtain high quality surgical tissue annotations through crowdsourcing of non-experts, and real-time deployment of multimodal surgical anatomy AI model in colorectal surgery
@article{skinner2024digmed,title={Real-time near infrared artificial intelligence using scalable non-expert crowdsourcing in colorectal surgery},author={Skinner, G. and Chen, T. and Jentis, G. and Liu, Y. and McCulloh, C. and Harzman, A. and Huang, E. and Kalady, M. and Kim, P.},journal={npj Digital Medicine},volume={7},number={1},pages={99},year={2024},doi={10.1038/s41746-024-01095-8},url={https://doi.org/10.1038/s41746-024-01095-8},}