Large-scale Self-supervised Video Foundation Model for Intelligent Surgery

TL;DR

This paper introduces SurgVISTA, a large-scale self-supervised video pre-training framework for surgical scene understanding, capturing spatiotemporal features from extensive surgical videos to improve AI-assisted surgery.

Contribution

The work presents the first joint spatiotemporal surgical pre-training method using a large-scale dataset and a reconstruction-based approach with knowledge distillation, advancing surgical AI capabilities.

Findings

SurgVISTA outperforms existing models on multiple surgical video benchmarks.

The large-scale dataset enables robust spatiotemporal feature learning.

Knowledge distillation enhances fine-grained anatomical understanding.

Abstract

Computer-Assisted Intervention (CAI) has the potential to revolutionize modern surgery, with surgical scene understanding serving as a critical component in supporting decision-making, improving procedural efficacy, and ensuring intraoperative safety. While existing AI-driven approaches alleviate annotation burdens via self-supervised spatial representation learning, their lack of explicit temporal modeling during pre-training fundamentally restricts the capture of dynamic surgical contexts, resulting in incomplete spatiotemporal understanding. In this work, we introduce the first video-level surgical pre-training framework that enables joint spatiotemporal representation learning from large-scale surgical video data. To achieve this, we constructed a large-scale surgical video dataset comprising 3,650 videos and approximately 3.55 million frames, spanning more than 20 surgical procedures and over 10 anatomical structures. Building upon this dataset, we propose SurgVISTA (Surgical Video-level Spatial-Temporal Architecture), a reconstruction-based pre-training method that captures intricate spatial structures and temporal dynamics through joint spatiotemporal modeling. Additionally, SurgVISTA incorporates image-level knowledge distillation guided by a surgery-specific expert to enhance the learning of fine-grained anatomical and semantic features. To validate its effectiveness, we established a comprehensive benchmark comprising 13 video-level datasets spanning six surgical procedures across four tasks. Extensive experiments demonstrate that SurgVISTA consistently outperforms both natural- and surgical-domain pre-trained models, demonstrating strong potential to advance intelligent surgical systems in clinically meaningful scenarios.