Catheter tail end attitude estimation method and system and medium

Abstract

The invention provides a catheter tail end attitude estimation method and system and a medium, and the method comprises the steps of obtaining the prior shape of the catheter tail end in a three-dimensional scanning or manual surveying and mapping mode before intubation, cutting a two-dimensional projection drawing of the catheter tail end in an XCA image in the intubation process, and recording the direction information of the two sides of a bent section of the catheter tail end; fusing the prior shape of the tail end of the catheter and the two-dimensional projection drawing information at the current moment in the front fusion stage, and fusing the direction information of the electromagnetic sensor at the current moment into the middle layer of the deep learning network and fusing with the middle layer features in the rear fusion stage; and inputting the pre-fusion result into an encoder of the deep learning network, inputting the post-fusion result into a decoder of the deep learning network, and finally outputting attitude estimation in a point sequence format by the deep learning network. According to the invention, the deep neural network is firstly used for estimating the catheter tail end posture, and the method has the advantages of being high in robustness, high in calculation efficiency, accurate in estimation and the like.

Description

technical field [0001] The present invention relates to the field of medicine, in particular, to a method, system and medium for estimating the pose of a catheter end, and more specifically, to a method for estimating the pose of a catheter end based on a two-step multi-source information fusion deep learning network. Background technique [0002] In PCI (Percutaneous Coronary Intervention) surgery, intraoperative XCA angiography images are usually used as a reference to observe the patient's vascular system and internal medical tools. It has the advantages of real-time rapid imaging and clear anatomical structures. However, due to the single-plane two-dimensional projection image, the spatial three-dimensional depth information is lost, so doctors need to rely on experience and operating feel to reconstruct the three-dimensional posture of the catheter end from the two-dimensional image information. The catheter end pose automatic estimation technology can be integrated in ...

AI Technical Summary

Problems solved by technology

At present, there is still no good way to improve the accuracy of 3D pose estimation by solving the above ambiguity

Images