Synergistic Bleeding Region and Point Detection in Surgical Videos

2025-03-28

AI Summary

Intraoperative bleeding during laparoscopic surgery frequently obscures the surgical field, necessitating real-time, precise, and synergistic detection of both bleeding regions and bleeding points. To address this, we introduce SurgBlood—the first real-world surgical bleeding detection dataset—and propose BlooDet, a dual-task collaborative online detector. BlooDet features a novel dual-branch bidirectional guidance architecture that integrates adaptive edge/point prompt embeddings, mask-based memory modeling, and optical-flow-driven estimation of bleeding point motion direction, enabling spatiotemporally consistent bleeding state inference. Built upon SAM 2, it unifies prompt learning, memory-augmented representation, optical flow estimation, and multi-task joint optimization. On SurgBlood, BlooDet achieves 64.88% IoU for region detection and 83.69% PCK-10% for point localization—substantially outperforming existing methods—and establishes a new paradigm for intelligent intraoperative hemostasis.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Intraoperative bleeding in laparoscopic surgery causes rapid obscuration of the operative field to hinder the surgical process. Intelligent detection of bleeding regions can quantify the blood loss to assist decision-making, while locating the bleeding point helps surgeons quickly identify the source of bleeding and achieve hemostasis in time. In this study, we first construct a real-world surgical bleeding detection dataset, named SurgBlood, comprising 5,330 frames from 95 surgical video clips with bleeding region and point annotations. Accordingly, we develop a dual-task synergistic online detector called BlooDet, designed to perform simultaneous detection of bleeding regions and points in surgical videos. Our framework embraces a dual-branch bidirectional guidance design based on Segment Anything Model 2 (SAM 2). The mask branch detects bleeding regions through adaptive edge and point prompt embeddings, while the point branch leverages mask memory to induce bleeding point memory modeling and captures the direction of bleed point movement through inter-frame optical flow. By interactive guidance and prompts, the two branches explore potential spatial-temporal relationships while leveraging memory modeling from previous frames to infer the current bleeding condition. Extensive experiments demonstrate that our approach outperforms other counterparts on SurgBlood in both bleeding region and point detection tasks, e.g., achieving 64.88% IoU for bleeding region detection and 83.69% PCK-10% for bleeding point detection.

Problem

• Detect bleeding regions in laparoscopic surgery videos
• Locate bleeding points to identify source quickly
• Quantify blood loss for better surgical decision-making

Innovation

• Dual-task synergistic online detector for bleeding
• SAM 2-based dual-branch bidirectional guidance design
• Memory modeling and optical flow for spatiotemporal analysis