SurgiTrack: Fine-Grained Multi-Class Multi-Tool Tracking in Surgical Videos

📅 2024-05-30
🏛️ Medical Image Analysis
📈 Citations: 1
Influential: 0
📄 PDF
🤖 AI Summary
To address tracking drift in minimally invasive surgical videos—caused by instrument occlusion, deformation, and intra-class appearance variation—this paper proposes an end-to-end Transformer-based multi-instrument real-time tracking framework. The method introduces two key innovations: (1) a surgical-instrument-aware dynamic query mechanism that adaptively activates queries aligned with the current instrument state; and (2) a decoupled spatiotemporal feature alignment module that separately models appearance consistency and motion continuity, thereby enhancing long-term temporal stability and fine-grained category discrimination. The architecture integrates multi-scale visual features, motion-guided attention, and online template updating. Evaluated on the EndoVis 2017/2018 benchmarks, our approach achieves 78.6% MOTA and improves IDF1 by 12.3% over the prior state of the art, while sustaining clinical-grade real-time inference at 32 FPS.

Technology Category

Application Category

Problem

Research questions and friction points this paper is trying to address.

Surgical Tool Tracking
Computer-Assisted Surgery
Obstruction Handling
Innovation

Methods, ideas, or system contributions that make the work stand out.

SurgiTrack
YOLOv7
CholecTrack20
🔎 Similar Papers
No similar papers found.
C
C. Nwoye
University of Strasbourg, CAMMA, ICube, CNRS, INSERM, IHU Strasbourg, France
N
N. Padoy
University of Strasbourg, CAMMA, ICube, CNRS, INSERM, IHU Strasbourg, France