Surg$Σ$: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence

2026-03-17

AI Summary

Current surgical AI systems are often limited to narrow tasks, exhibit weak generalization, and lack support from large-scale, structured multimodal data. To address these limitations, this work proposes the SurgΣ framework and introduces SurgΣ-DB, the first large-scale, standardized multimodal surgical database spanning six specialties and 18 tasks. SurgΣ-DB integrates heterogeneous data from open-source, clinical, and web sources, comprising over 5.98 million annotated dialogues with hierarchical reasoning labels, all unified under a consistent semantic model. A foundational surgical model trained on this dataset demonstrates significantly enhanced cross-task generalization, contextual understanding, and interpretability across multiple benchmarks, thereby validating the critical role of structured multimodal data in advancing surgical intelligence.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Surgical intelligence has the potential to improve the safety and consistency of surgical care, yet most existing surgical AI frameworks remain task-specific and struggle to generalize across procedures and institutions. Although multimodal foundation models, particularly multimodal large language models, have demonstrated strong cross-task capabilities across various medical domains, their advancement in surgery remains constrained by the lack of large-scale, systematically curated multimodal data. To address this challenge, we introduce Surg$Σ$, a spectrum of large-scale multimodal data and foundation models for surgical intelligence. At the core of this framework lies Surg$Σ$-DB, a large-scale multimodal data foundation designed to support diverse surgical tasks. Surg$Σ$-DB consolidates heterogeneous surgical data sources (including open-source datasets, curated in-house clinical collections and web-source data) into a unified schema, aiming to improve label consistency and data standardization across heterogeneous datasets. Surg$Σ$-DB spans 6 clinical specialties and diverse surgical types, providing rich image- and video-level annotations across 18 practical surgical tasks covering understanding, reasoning, planning, and generation, at an unprecedented scale (over 5.98M conversations). Beyond conventional multimodal conversations, Surg$Σ$-DB incorporates hierarchical reasoning annotations, providing richer semantic cues to support deeper contextual understanding in complex surgical scenarios. We further provide empirical evidence through recently developed surgical foundation models built upon Surg$Σ$-DB, illustrating the practical benefits of large-scale multimodal annotations, unified semantic design, and structured reasoning annotations for improving cross-task generalization and interpretability.

Problem

• surgical intelligence
• multimodal data
• foundation models
• cross-task generalization
• data standardization

Innovation

• multimodal foundation models
• surgical intelligence
• large-scale multimodal data
• hierarchical reasoning annotations
• cross-task generalization