Deep learning-based framework for motion-compensated image fusion in catheterization procedures

Vernikouskaya, Ina; Bertsche, Dagmar; Rottbauer, Wolfgang; Rasche, Volker

doi:10.1016/j.compmedimag.2022.102069

Cited by 4 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the results presented might be considered as indication of the relevance of motioncompensation with further validation in larger cohorts still needed. The co-registration as well as identification of the respiratory phase was done manually and using automated approaches such as, e.g., proposed earlier [15,34,35] might further increase the resulting accuracy. Further, the nonavailability of XR runs in two angulations for the motion impact analysis and hence the projection of the marker displacement on the view axis might impact the absolute value of the differences between the analyzed data.…”

Section: Discussionmentioning

confidence: 99%

“…Improved co-registration techniques have been presented for 3D-3D as well as for 2D-3D co-registration [12][13][14], and motion compensation approaches have been introduced mainly focusing on the compensation of respiratory motion [15][16][17]. As desired accuracy of an IGI system, a minimum of 5 mm has been reported for endovascular and cardiac procedures [18,19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Impact of cardiac and respiratory motion on the 3D accuracy of image-guided interventions on monoplane systems

et al. 2023

Self Cite

View full text Add to dashboard Cite

Purpose Image-guided intervention (IGI) systems have the potential to increase the efficiency in interventional cardiology but face limitations from motion. Even though motion compensation approaches have been proposed, the resulting accuracy has rarely been quantified using in vivo data. The purpose of this study is to investigate the potential benefit of motion-compensation in IGS systems. Methods Patients scheduled for left atrial appendage closure (LAAc) underwent pre- and postprocedural non-contrast-enhanced cardiac magnetic resonance imaging (CMR). According to the clinical standard, the final position of the occluder device was routinely documented using x-ray fluoroscopy (XR). The accuracy of the IGI system was assessed retrospectively based on the distance of the 3D device marker location derived from the periprocedural XR data and the respective location as identified in the postprocedural CMR data. Results The assessment of the motion-compensation depending accuracy was possible based on the patient data. With motion synchronization, the measured accuracy of the IGI system resulted similar to the estimated accuracy, with almost negligible distances of the device marker positions identified in CMR and XR. Neglection of the cardiac and/or respiratory phase significantly increased the mean distances, with respiratory motion mainly reducing the accuracy with rather low impact on the precision, whereas cardiac motion decreased the accuracy and the precision of the image guidance. Conclusions In the presented work, the accuracy of the IGI system could be assessed based on in vivo data. Motion consideration clearly showed the potential to increase the accuracy in IGI systems. Where the general decrease in accuracy in non-motion-synchronized data did not come unexpected, a clear difference between cardiac and respiratory motion-induced errors was observed for LAAc data. Since sedation and intervention location close to the large vessels likely impacts the respiratory motion contribution, an intervention-specific accuracy analysis may be useful for other interventions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Impact of cardiac and respiratory motion on the 3D accuracy of image-guided interventions on monoplane systems

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…In terms of catheter or guidewire tracking for fluoroscopy images [5,[8][9][10][11][12][13][14], Vernikouskaya et al designed a convolutional neural network (CNN) with two channels, utilized to track the pacing of the catheter tip and considered a single-point tracking method [13]. Motion was identified based on the template matching of 2D fluoroscopic images.…”

Section: Introductionmentioning

confidence: 99%

“…Motion was identified based on the template matching of 2D fluoroscopic images. The training data were generated by tracing a rapid-pace catheter tip; however, heatmap plots indicated that the catheter tip was not of interest, spreading the attention of the CNN on the diaphragm [13]. In another study, researchers estimated an external force applied on the tip of a planar catheter through image processing algorithms based on cropping and edge detection, followed by a mathematical catheter representation.…”

Section: Introductionmentioning

confidence: 99%

Use of Yolo Detection for 3D Pose Tracking of Cardiac Catheters Using Bi-Plane Fluoroscopy

Hashemi,

Annabestani,

Aghasizade

et al. 2024

View full text Add to dashboard Cite

The increasing rate of minimally invasive procedures and the growing prevalence of cardiovascular disease have led to a demand for higher-quality guidance systems for catheter tracking. Traditional methods for catheter tracking, such as detection based on single points and applying masking techniques, have been limited in their ability to provide accurate pose information. In this paper, we propose a novel deep learning-based method for catheter tracking and pose detection. Our method uses a Yolov5 bounding box neural network with postprocessing to perform landmark detection in four regions of the catheter: the tip, radio-opaque marker, bend, and entry point. This allows us to track the catheter’s position and orientation in real time, without the need for additional masking or segmentation techniques. We evaluated our method on a dataset of fluoroscopic images from two distinct datasets and achieved state-of-the-art results in terms of accuracy and robustness. Our model was able to detect all four landmark features (tip, marker, bend, and entry) used to generate a pose for a catheter with 0.285 ± 0.143 mm, 0.261 ± 0.138 mm, 0.424 ± 0.361 mm, and 0.235 ± 0.085 mm accuracy. We believe that our method has the potential to significantly improve the accuracy and efficiency of catheter tracking in medical procedures that utilize bi-plane fluoroscopy guidance.

show abstract

“…In another work, researchers utilized a CNN to explore the possibility to detect motion between two fluoroscopic frames in catheterization procedures [69]. They were able to compare their CNN-based catheter tip detection with normalized cross correlation (CC) and found a mean absolute error (MAE) of 8.7 ± 2.5 pixels or 3.0 ± 0.9 mm between methods, with the CNN outperforming CC.…”

Section: Introductionmentioning

confidence: 99%

A Coordinate-Regression-Based Deep Learning Model for Catheter Detection during Structural Heart Interventions

Aghasizade,

Kiyoumarsioskouei,

Hashemi

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

With a growing geriatric population estimated to triple by 2050, minimally invasive procedures that are image-guided are becoming both more popular and necessary for treating a variety of diseases. To lower the learning curve for new procedures, it is necessary to develop better guidance systems and methods to analyze procedure performance. Since fluoroscopy remains the primary mode of visualizations, the ability to perform catheter tracking from fluoroscopic images is an important part of this endeavor. This paper explores the use of deep learning to perform the landmark detection of a catheter from fluoroscopic images in 3D-printed heart models. We show that a two-stage deep-convolutional-neural-network-based model architecture can provide improved performance by initially locating a region of interest before determining the coordinates of the catheter tip within the image. This model has an average error of less than 2% of the image resolution and can be performed within 4 milliseconds, allowing for its potential use for real-time intraprocedural tracking. Coordinate regression models have the advantage of directly outputting values that can be used for quantitative tracking in future applications and are easier to create ground truth values (~50× faster), as compared to semantic segmentation models that require entire masks to be made. Therefore, we believe this work has better long-term potential to be used for a broader class of cardiac devices, catheters, and guidewires.

show abstract

Deep learning-based framework for motion-compensated image fusion in catheterization procedures

Cited by 4 publications

References 24 publications

Impact of cardiac and respiratory motion on the 3D accuracy of image-guided interventions on monoplane systems

Impact of cardiac and respiratory motion on the 3D accuracy of image-guided interventions on monoplane systems

Use of Yolo Detection for 3D Pose Tracking of Cardiac Catheters Using Bi-Plane Fluoroscopy

A Coordinate-Regression-Based Deep Learning Model for Catheter Detection during Structural Heart Interventions

Contact Info

Product

Resources

About