Rapid Image Registration of Three-Dimensional Transesophageal Echocardiography and X-ray Fluoroscopy for the Guidance of Cardiac Interventions

Gao, Gang; Penney, Graeme P.; Gogin, Nicolas; Cathier, Pascal; Arujuna, Aruna; Wright, Matthew; Caulfield, Dennis; Rinaldi, Christopher Aldo; Razavi, Reza; Rhode, Kawal

doi:10.1007/978-3-642-13711-2_12

Cited by 13 publications

(15 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A 3D/2D registration between a 3D TEE probe model and its projection onto 2D X-ray images is performed to acquire the transformation [10] between the two modalities. Through this transformation, each key point on the tracked curve in the X-ray images can be related to a ray in the US volume, and a curve on X-ray will correspond to a curved surface in US.…”

Section: Features and Clusters On A Curved Surfacementioning

confidence: 99%

Catheter tracking in 3D echocardiographic sequences based on tracking in 2D X-ray sequences for cardiac catheterization interventions

Housden

Varma

et al. 2013

2013 IEEE 10th International Symposium on Biomedical Imaging

Self Cite

View full text Add to dashboard Cite

Although X-ray imaging has played a dominant role in cardiac catheter-based interventions, sometimes 3D soft tissue information, which X-ray images cannot provide, may be required. In contrast, 3D echocardiographic imaging is able to visualise soft tissue. In this paper, we propose a real-time catheter tracking strategy in echocardiographic sequences based on catheter tracking in 2D X-ray images and registration between these two modalities. The catheter tracking in X-ray images can be divided into catheter initialization and tracking. For initialization, an extraction algorithm based on SURF features, patch analysis and Kalman filtering is used to locate the catheter in the first X-ray image. Following this, a tracking algorithm based on patch analysis and Fast-PD optimization is used to track the catheter in the following images. The tracking result of each X-ray frame, as well as the transformation between X-ray and ultrasound images obtained from registration, is used to reduce the search space in the echo volume to only a curved surface. Using a graphical model and shortest path optimization, the position of the catheters in each echo frame can be estimated. Based on 10 pairs of X-ray and US sequences, comprising more than 800 frames, our experimental results show that the tracking system can track catheters with an average error of less than 1mm in X-ray images and less than 2mm in US. Also, our strategy for tracking in X-ray outperforms previous methods using only Fast-PD. The speed in total can reach 1.5 fps.

show abstract

Section: Features and Clusters On A Curved Surfacementioning

confidence: 99%

Catheter tracking in 3D echocardiographic sequences based on tracking in 2D X-ray sequences for cardiac catheterization interventions

Housden

Varma

et al. 2013

2013 IEEE 10th International Symposium on Biomedical Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…The main problems were that extra hardware and modifications to the TEE probe were required, and that the system was prone to inaccuracies due to electromagnetic fields generated by the XRF system. Image based methods were first presented in Gao et al (2010), where the feasibility of using GPU accelerated raycasting techniques to register the TEE probe to XRF images was demonstrated. The initial results indicated that the method was accurate (mean projection distance = 1.8 ± 1.13 mm), and fast enough for clinical applications that required sub-real-time registrations (1.8 ± 0.6 seconds per registration).…”

Section: Previous Workmentioning

confidence: 99%

Real-time pose estimation of devices from x-ray images: Application to x-ray/echo registration for cardiac interventions

Hatt

Speidel

Raval

2016

Medical Image Analysis

View full text Add to dashboard Cite

In recent years, registration between x-ray fluoroscopy (XRF) and transesophageal echocardiography (TEE) has been rapidly developed, validated, and translated to the clinic as a tool for advanced image guidance of structural heart interventions. This technology relies on accurate pose-estimation of the TEE probe via standard 2D/3D registration methods. It has been shown that latencies caused by slow registrations can result in errors during untracked frames, and a real-time (> 15 hz) tracking algorithm is needed to minimize these errors. This paper presents two novel similarity metrics designed for accurate, robust, and extremely fast pose-estimation of devices from XRF images: Direct Splat Correlation (DSC) and Patch Gradient Correlation (PGC). Both metrics were implemented in CUDA C, and validated on simulated and clinical datasets against prior methods presented in the literature. It was shown that by combining DSC and PGC in a hybrid method (HYB), target registration errors comparable to previously reported methods were achieved, but at much higher speeds and lower failure rates. In simulated datasets, the proposed HYB method achieved a median projected target registration error (pTRE) of 0.33 mm and a mean registration frame-rate of 12.1 hz, while previously published methods produced median pTREs greater than 1.5 mm and mean registration frame-rates less than 4 hz. In clinical datasets, the HYB method achieved a median pTRE of 1.1 mm and a mean registration frame-rate of 20.5 hz, while previously published methods produced median pTREs greater than 1.3 mm and mean registration frame-rates less than 12 hz. The proposed hybrid method also had much lower failure rates than previously published methods.

show abstract

“…Although the final purpose of catheter tracking is often to localize the catheter tip, it is important that the entire catheters are segmented so that the tip localization is constrained. Recently, several methods have been developed that register the X-ray images to ultrasound images [2], [18]- [21]. Thus, the information from the corresponding X-ray images can assist in detecting or segmenting structures in ultrasound.…”

Section: A Related Workmentioning

confidence: 99%

“…This Kalman filter allows for tangential movement of the catheter, which would not be detected by Fast-PD. The X-ray and ultrasound images are registered by mapping a previously obtained 3-D TEE probe model to its projection image in the X-ray frame [18](Section II-D). This registration is only required at the beginning of the tracking.…”

Section: A Pipeline Overviewmentioning

confidence: 99%

Fast Catheter Segmentation From Echocardiographic Sequences Based on Segmentation From Corresponding X-Ray Fluoroscopy for Cardiac Catheterization Interventions

Housden

et al. 2015

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

Echocardiography is a potential alternative to X-ray fluoroscopy in cardiac catheterization given its richness in soft tissue information and its lack of ionizing radiation. However, its small field of view and acoustic artifacts make direct automatic segmentation of the catheters very challenging. In this study, a fast catheter segmentation framework for echocardiographic imaging guided by the segmentation of corresponding X-ray fluoroscopic imaging is proposed. The complete framework consists of: 1) catheter initialization in the first X-ray frame; 2) catheter tracking in the rest of the X-ray sequence; 3) fast registration of corresponding X-ray and ultrasound frames; and 4) catheter segmentation in ultrasound images guided by the results of both X-ray tracking and fast registration. The main contributions include: 1) a Kalman filter-based growing strategy with more clinical data evalution; 2) a SURF detector applied in a constrained search space for catheter segmentation in ultrasound images; 3) a two layer hierarchical graph model to integrate and smooth catheter fragments into a complete catheter; and 4) the integration of these components into a system for clinical applications. This framework is evaluated on five sequences of porcine data and four sequences of patient data comprising more than 3000 X-ray frames and more than 1000 ultrasound frames. The results show that our algorithm is able to track the catheter in ultrasound images at 1.3 s per frame, with an error of less than 2 mm. However, although this may satisfy the accuracy for visualization purposes and is also fast, the algorithm still needs to be further accelerated for real-time clinical applications.

show abstract

Rapid Image Registration of Three-Dimensional Transesophageal Echocardiography and X-ray Fluoroscopy for the Guidance of Cardiac Interventions

Cited by 13 publications

References 10 publications

Catheter tracking in 3D echocardiographic sequences based on tracking in 2D X-ray sequences for cardiac catheterization interventions

Catheter tracking in 3D echocardiographic sequences based on tracking in 2D X-ray sequences for cardiac catheterization interventions

Real-time pose estimation of devices from x-ray images: Application to x-ray/echo registration for cardiac interventions

Fast Catheter Segmentation From Echocardiographic Sequences Based on Segmentation From Corresponding X-Ray Fluoroscopy for Cardiac Catheterization Interventions

Contact Info

Product

Resources

About