Paper Reading AI Learner

Image-based Intraluminal Contact Force Monitoring in Robotic Vascular Navigation

2020-12-19 19:22:06
Masoud Razban, Javad Dargahi, Benoit Boulet

Abstract

Embolization, stroke, ischaemic lesion, and perforation remain significant concerns in endovascular interventions. Sensing catheter interaction inside the artery is advantageous to minimize such complications and enhances navigation safety. Intraluminal information is currently limited due to the lack of intravascular contact sensing technologies. We present monitoring of the intraluminal catheter interaction with the arterial wall using an image-based estimation approach within vascular robotic navigation. The proposed image-based method employs continuous finite element simulation of the catheter motion using imaging data to estimate multi-point forces along catheter-vessel interaction. We implemented imaging algorithms to detect and track contacts and compute catheter pose measurements. The catheter model is constructed based on the nonlinear beam element and flexural rigidity distribution. During remote cannulation of aortic arteries, intraluminal monitoring achieved tracking local contact forces, building contour map of force on the arterial wall, and estimating structural stress of catheter. Shape estimation error was within 2% range. Results suggest that high-risk intraluminal forces may happen even in low insertion forces. The presented online monitoring tool delivers insight into the intraluminal behavior of catheters and is well-suited for intraoperative visual guidance of clinicians, robotic control vascular system, and optimizing interventional device design.

Abstract (translated)

URL

https://arxiv.org/abs/2012.10762

PDF

https://arxiv.org/pdf/2012.10762.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot