Real-Time Glottis Detection Framework via Spatial-decoupled Feature Learning for Nasal Transnasal Intubation

TL;DR

This paper introduces Mobile GlottisNet, a lightweight real-time glottis detection framework optimized for embedded devices, improving speed and robustness in nasal intubation procedures.

Contribution

The paper presents a novel, efficient glottis detection model with structural awareness and adaptive modules, enabling fast inference on resource-constrained devices.

Findings

Achieves over 62 FPS on devices and 33 FPS on edge platforms.

Model size is only 5MB, suitable for embedded deployment.

Demonstrates robustness under complex anatomical and visual conditions.

Abstract

Nasotracheal intubation (NTI) is a vital procedure in emergency airway management, where rapid and accurate glottis detection is essential to ensure patient safety. However, existing machine assisted visual detection systems often rely on high performance computational resources and suffer from significant inference delays, which limits their applicability in time critical and resource constrained scenarios. To overcome these limitations, we propose Mobile GlottisNet, a lightweight and efficient glottis detection framework designed for real time inference on embedded and edge devices. The model incorporates structural awareness and spatial alignment mechanisms, enabling robust glottis localization under complex anatomical and visual conditions. We implement a hierarchical dynamic thresholding strategy to enhance sample assignment, and introduce an adaptive feature decoupling module based on deformable convolution to support dynamic spatial reconstruction. A cross layer dynamic weighting scheme further facilitates the fusion of semantic and detail features across multiple scales. Experimental results demonstrate that the model, with a size of only 5MB on both our PID dataset and Clinical datasets, achieves inference speeds of over 62 FPS on devices and 33 FPS on edge platforms, showing great potential in the application of emergency NTI.