Cryo-balloon catheter localization in X-Ray fluoroscopy using U-net

Vernikouskaya, Ina; Bertsche, Dagmar; Dahme, Tillman; Rasche, Volker

doi:10.1007/s11548-021-02366-5

Cited by 7 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…) calculated using the wellknown camera models as previously described [27,28]. In detail, the Nadir points on the projection lines of the identified marker at the smallest distance between these lines was determined.…”

Section: Motion-synchronized 3d Accuracymentioning

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

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: Motion-synchronized 3d Accuracymentioning

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

“…Chabi et al [6] detected potential markers based on adaptive threshold and refined detections by excluding non-mask area using various machine learning classifiers, including k-nearest neighbor, naive Bayesian classifier, support vector machine and linear discriminant analysis. Vernikouskaya et al [23] employed U-Net, a popular encoder-decoder like CNN designed specifically for medical images, to segment markers and catheter shafts during pulmonary vein isolation as binary masks. The maker segmentation performances from the above methods are still limited by the super imbalance between foreground and background areas.…”

Section: Balloon Marker Detectionmentioning

confidence: 99%

“…. The first step is to detect landmarks from each frame using a U-Net [23]. In contrast to conventional object detection, the major challenge of landmark detection is the highly unbalanced foreground/background ratio, as landmarks are commonly tiny dots of few pixels compared to the frame size.…”

Section: Landmark Detectionmentioning

confidence: 99%

“…Therefore, we propose an end-to-end trainable deep learning framework that consists of three hierarchical modules: a landmark detection module, which is a U-Net [23] trained with small patches to detect potential balloon markers with local features; a stent proposal and feature extraction module, which is a ResNet [12] trained with larger stent patches to extract high-level features located between detected marker pairs; and a stent tracking module, which is a graph convolutional neural network (GCN) to associate marker pairs across frames using the combination of extracted features and spatial information. Our ablation study demonstrated that end-to-end learning of the whole framework can greatly benefit the performance of final stent tracking.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Landmark-based Stent Tracking in X-ray Fluoroscopy

Huang¹,

Liu²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

In clinical procedures of angioplasty (i.e., open clogged coronary arteries), devices such as balloons and stents need to be placed and expanded in arteries under the guidance of X-ray fluoroscopy. Due to the limitation of X-ray dose, the resulting images are often noisy. To check the correct placement of these devices, typically multiple motioncompensated frames are averaged to enhance the view. Therefore, device tracking is a necessary procedure for this purpose. Even though angioplasty devices are designed to have radiopaque markers for the ease of tracking, current methods struggle to deliver satisfactory results due to the small marker size and complex scenes in angioplasty. In this paper, we propose an end-to-end deep learning framework for single stent tracking, which consists of three hierarchical modules: a U-Net for landmark detection, a ResNet for stent proposal and feature extraction, and a graph convolutional neural network for stent tracking that temporally aggregates both spatial information and appearance features. The experiments show that our method performs significantly better in detection compared with the state-of-the-art point-based tracking models. In addition, its fast inference speed satisfies clinical requirements.

show abstract

“…Therefore, the automatic tracking of an initial marker was exemplified, resulting in successful tracking of the device position in 2D and subsequent 3D localization in real-time. Even though the tracking was exemplified applying cross-correlation, the localization method is applicable in general and could be combined with other automatization methods as previously suggested [37][38][39][40].…”

mentioning

confidence: 99%

3D localization from 2D X-ray projection

et al. 2022

Self Cite

View full text Add to dashboard Cite

Purpose Most cardiology procedures are guided using X-ray (XR) fluoroscopy. However, the projective nature of the XR fluoroscopy does not allow for true depth perception as required for safe and efficient intervention guidance in structural heart diseases. For improving guidance, different methods have been proposed often being radiation-intensive, time-consuming, or expensive. We propose a simple 3D localization method based on a single monoplane XR projection using a co-registered centerline model. Methods The method is based on 3D anatomic surface models and corresponding centerlines generated from preprocedural imaging. After initial co-registration, 2D working points identified in monoplane XR projections are localized in 3D by minimizing the angle between the projection lines of the centerline points and the working points. The accuracy and reliability of the located 3D positions were assessed in 3D using phantom data and in patient data projected to 2D obtained during placement of embolic protection system in interventional procedures. Results With the proposed methods, 2D working points identified in monoplane XR could be successfully located in the 3D phantom and in the patient-specific 3D anatomy. Accuracy in the phantom (3D) resulted in 1.6 mm (± 0.8 mm) on average, and 2.7 mm (± 1.3 mm) on average in the patient data (2D). Conclusion The use of co-registered centerline models allows reliable and accurate 3D localization of devices from a single monoplane XR projection during placement of the embolic protection system in TAVR. The extension to different vascular interventions and combination with automatic methods for device detection and registration might be promising.

show abstract

Cryo-balloon catheter localization in X-Ray fluoroscopy using U-net

Cited by 7 publications

References 14 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

Robust Landmark-based Stent Tracking in X-ray Fluoroscopy

3D localization from 2D X-ray projection

Contact Info

Product

Resources

About