Agentic Surgical AI: Surgeon Style Fingerprinting and Privacy Risk Quantification via Discrete Diffusion in a Vision-Language-Action Framework
This work addresses the need for personalized surgical AI systems while highlighting privacy trade-offs, representing an incremental advance in domain-specific modeling.
The paper tackles the problem of predicting surgeon-specific behavior in robotic surgery by proposing an agentic modeling approach that combines discrete diffusion with a vision-language-action pipeline, achieving accurate gesture sequence reconstruction on the JIGSAWS dataset while learning unique motion fingerprints for each surgeon. It also quantifies privacy risks, finding that more expressive embeddings improve performance but increase susceptibility to identity leakage through membership inference attacks.
Surgeons exhibit distinct operating styles shaped by training, experience, and motor behavior-yet most surgical AI systems overlook this personalization signal. We propose a novel agentic modeling approach for surgeon-specific behavior prediction in robotic surgery, combining a discrete diffusion framework with a vision-language-action (VLA) pipeline. Gesture prediction is framed as a structured sequence denoising task, conditioned on multimodal inputs including surgical video, intent language, and personalized embeddings of surgeon identity and skill. These embeddings are encoded through natural language prompts using third-party language models, allowing the model to retain individual behavioral style without exposing explicit identity. We evaluate our method on the JIGSAWS dataset and demonstrate that it accurately reconstructs gesture sequences while learning meaningful motion fingerprints unique to each surgeon. To quantify the privacy implications of personalization, we perform membership inference attacks and find that more expressive embeddings improve task performance but simultaneously increase susceptibility to identity leakage. These findings demonstrate that while personalized embeddings improve performance, they also increase vulnerability to identity leakage, revealing the importance of balancing personalization with privacy risk in surgical modeling. Code is available at: https://github.com/huixin-zhan-ai/Surgeon_style_fingerprinting.