Purpose Automatic identification of interventional devices in X-ray (XR) fluoroscopy offers the potential of improved navigation during transcatheter endovascular procedures. This paper presents a prototype implementation of fully automatic 3D reconstruction of a cryo-balloon catheter during pulmonary vein isolation (PVI) procedures by deep learning approaches. Methods We employ convolutional neural networks (CNN) to automatically identify the cryo-balloon XR marker and catheter shaft in 2D fluoroscopy during PVI. Training data are generated exploiting established semiautomatic techniques, including template-matching and analytical graph building. A first network of U-net architecture uses a single grayscale XR image as input and yields the mask of the XR marker. A second network of the similar architecture is trained using the mask of the XR marker as additional input to the grayscale XR image for the segmentation of the cryo-balloon catheter shaft mask. The structures automatically identified in two 2D images with different angulations are then used to reconstruct the cryo-balloon in 3D. Results Automatic identification of the XR marker was successful in 78% of test cases and in 100% for the catheter shaft. Training of the model for prediction of the XR marker mask was successful with 3426 training samples. Incorporation of the XR marker mask as additional input for the model predicting the catheter shaft allowed to achieve good training result with only 805 training samples. The average prediction time per frame was 14.47 ms for the XR marker and 78.22 ms for the catheter shaft. Localization accuracy for the XR marker yielded on average 1.52 pixels or 0.56 mm. Conclusions In this paper, we report a novel method for automatic detection and 3D reconstruction of the cryo-balloon catheter shaft and marker from 2D fluoroscopic images. Initial evaluation yields promising results thus indicating the high potential of CNNs as alternatives to the current state-of-the-art solutions.
Purpose With the growing availability and variety of imaging modalities, new methods of intraoperative support have become available for all kinds of interventions. The basic principles of image fusion and image guidance have been widely adopted and are commercialized through a number of platforms. Although multimodal systems have been found to be useful for guiding interventional procedures, they all have their limitations. The integration of more advanced guidance techniques into the product functionality is, however, not easy due to the proprietary solutions of the vendors. Therefore, the purpose of this work is to introduce a software system for image fusion, real-time navigation, and working points documentation during transcatheter interventions performed under X-ray (XR) guidance. Methods An interactive software system for cross-modal registration and image fusion of XR fluoroscopy with CT or MRI-derived anatomic 3D models is implemented using Qt application framework and VTK visualization pipeline. DICOM data can be imported in retrospective mode. Live XR data input is realized by a video capture card application interface. Results The actual software release offers a graphical user interface with basic functionality including data import and handling, calculation of projection geometry and transformations between related coordinate systems, rigid 3D-3D registration, and template matching-based tracking and motion compensation algorithms in 2D and 3D. The link to the actual software release on GitHub including source code and executable is provided to support independent research and development in the field of intervention guidance. Conclusion The introduced system provides a common foundation for the rapid prototyping of new approaches in the field of XR fluoroscopic guidance. As a pure software solution, the developed system is potentially vendor-independent and can be easily extended to be used with the XR systems of different manufacturers.
Purpose Percutaneous closure of the left atrial appendage (LAA) reduces the risk of embolic stroke in patients with atrial fibrillation. Thereby, the optimal transseptal puncture (TSP) site differs due to the highly variable anatomical shape of the LAA, which is rarely considered in existing training models. Based on non-contrast-enhanced magnetic resonance imaging (MRI) volumes, we propose a training model for LAA closure with interchangeable and patient-specific LAA enabling LAA-specific identification of the TSP site best suited. Methods Based on patient-specific MRI data, silicone models of the LAAs were produced using a 3D-printed cast model. In addition, an MRI-derived 3D-printed base model was set up, including the right and left atrium with predefined passages in the septum, mimicking multiple TSP sites. The various silicone models and a tube mimicking venous access were connected to the base model. Empirical use of the model allowed the demonstration of its usability. Results Patient-specific silicone models of the LAA could be generated from all LAA patient MRI datasets. The influence of various combinations regarding TSP sites and LAA shapes could be demonstrated as well as the technical functionality of the occluder system. Via the attached tube mimicking the venous access, the correct handling of the deployment catheter even in case of not optimal puncture site could be practiced. Conclusion The proposed contrast-agent and radiation-free MRI-based training model for percutaneous LAA closure enables the pre-interventional assessment of the influence of the TSP site on the access of patient-specific LAA shapes. A straightforward replication of this work is measured by using clinically available imaging protocols and a widespread 3D printer technique to build the model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.