BLFM-Net: An Efficient Regional Feature Matching Method for Bronchoscopic Surgery Based on Deep Learning Object Detection

Accurate and robust navigation in complex surgical environments is crucial for bronchoscopic surgeries. This study purposes a bronchoscopic lumen feature matching network (BLFM-Net) based on deep learning to address the challenges of image noise, anatomical complexity, and the stringent real-time requirements. The BLFM-Net enhances bronchoscopic image processing by integrating several functional modules. The FFA-Net preprocessing module mitigates image fogging and improves visual clarity for subsequent processing. The feature extraction module derives multi-dimensional features, such as centroids, area, and shape descriptors, from dehazed images. The Faster R-CNN Object detection module detects bronchial regions of interest and generates bounding boxes to localize key areas. The feature matching module accelerates the process by combining detection boxes, extracted features, and a KD-Tree (K-Dimensional Tree)-based algorithm, ensuring efficient and accurate regional feature associations. The BLFM-Net was evaluated on 5212 bronchoscopic images, demonstrating superior performance compared to traditional and other deep learning-based image matching methods. It achieved real-time matching with an average frame time of 6 ms, with a matching accuracy of over 96%. The method remained robust under challenging conditions including frame dropping (0, 5, 10, 20), shadowed regions, and variable lighting, maintaining accuracy of above 94% even with the frame dropping of 20. This study presents BLFM-Net, a deep learning-based matching network designed to enhance and match bronchial features in bronchoscopic images. The BLFM-Net shows improved accuracy, real-time performance, and reliability, making a valuable tool for bronchoscopic surgeries.