Multi-mode information fusion navigation system for robot-assisted vascular interventional surgery.

BACKGROUND: Minimally invasive vascular intervention (MIVI) is a powerful technique for the treatment of cardiovascular diseases, such as abdominal aortic aneurysm (AAA), thoracic aortic aneurysm (TAA) and aortic dissection (AD). Navigation of traditional MIVI surgery mainly relies only on 2D digital subtraction angiography (DSA) images, which is hard to observe the 3D morphology of blood vessels and position the interventional instruments. The multi-mode information fusion navigation system (MIFNS) proposed in this paper combines preoperative CT images and intraoperative DSA images together to increase the visualization information during operations. RESULTS: The main functions of MIFNS were evaluated by real clinical data and a vascular model. The registration accuracy of preoperative CTA images and intraoperative DSA images were less than 1 mm. The positioning accuracy of surgical instruments was quantitatively assessed using a vascular model and was also less than 1 mm. Real clinical data used to assess the navigation results of MIFNS on AAA, TAA and AD. CONCLUSIONS: A comprehensive and effective navigation system was developed to facilitate the operation of surgeon during MIVI. The registration accuracy and positioning accuracy of the proposed navigation system were both less than 1 mm, which met the accuracy requirements of robot assisted MIVI.

Transfer Learning for Nonrigid 2D/3D Cardiovascular Images Registration.

Cardiovascular image registration is an essential approach to combine the advantages of preoperative 3D computed tomography angiograph (CTA) images and intraoperative 2D X-ray/digital subtraction angiography (DSA) images together in minimally invasive vascular interventional surgery (MIVI). Recent studies have shown that convolutional neural network (CNN) regression model can be used to register these two modality vascular images with fast speed and satisfactory accuracy. However, CNN regression model trained by tens of thousands of images of one patient is often unable to be applied to another patient due to the large difference and deformation of vascular structure in different patients. To overcome this challenge, we evaluate the ability of transfer learning (TL) for the registration of 2D/3D deformable cardiovascular images. Frozen weights in the convolutional layers were optimized to find the best common feature extractors for TL. After TL, the training data set size was reduced to 200 for a randomly selected patient to get accurate registration results. We compared the effectiveness of our proposed nonrigid registration model after TL with not only that without TL but also some traditional intensity-based methods to evaluate that our nonrigid model after TL performs better on deformable cardiovascular image registration.