Single-view 2D/3D registation for X-ray guided bronchoscopy

X-ray guided bronchoscopy is commonly used for targeting peripheral lesions in the lungs which cannot be visualized directly by the bronchoscope. The airways and lesions are normally not visible in X-ray images, and as a result, transbronchial biopsy of peripheral lesions is often carried out blindly, lowering the diagnostic yield of bronchoscopy. In response to this problem, we propose to superimpose the lesions and airways segmented from preoperative 3D CT images onto 2D fluoroscopic images. A feature-based 2D/3D registration method is used for image fusion between the two datasets. The algorithm extracts features of the bony structures from both CT and X-ray images to compute the registration. Phantom and clinical studies were carried out to validate the algorithm´s performance, showing an accuracy of 3.48±1.38mm. The convergence range and speed of the algorithm were also evaluated to investigate the feasibility of using the algorithm clinically. The results are presented.