An in vitro assessment of acoustic radiation force impulse imaging for visualizing cardiac radiofrequency ablation lesions

Abstract

Introduction: Lesion placement and transmurality are critical factors in the success of cardiac transcatheter radiofrequency ablation (RFA) treatments for supraventricular arrhythmias. This study investigated the capabilities of catheter transducer based acoustic radiation force impulse (ARFI) ultrasound imaging for quantifying ablation lesion dimensions.

Methods and results: RFA lesions were created in vitro in porcine ventricular myocardium and imaged with an intracardiac ultrasound catheter transducer capable of acquiring spatially registered B-mode and ARFI images. The myocardium was sliced along the imaging plane and photographed. The maximum ARFI-induced displacement images of the lesion were normalized and spatially registered with the photograph by matching the surfaces of the tissue in the B-mode and photographic images. The lesion dimensions determined by a manual segmentation of the photographed lesion based on the visible discoloration of the tissue were compared to automatic segmentations of the ARFI image using 2 different calculated thresholds. ARFI imaging accurately localized and sized the lesions within the myocardium. Differences in the maximum lateral and axial dimensions were statistically below 2 mm and 1 mm, respectively, for the 2 thresholding methods, with mean percent overlap of 68.7 +/- 5.21% and 66.3 +/- 8.4% for the 2 thresholds used.

Conclusion: ARFI imaging is capable of visualizing myocardial RFA lesion dimensions to within 2 mm in vitro. Visualizing lesions during transcatheter cardiac ablation procedures could improve the success of the treatment by imaging lesion line discontinuity and potentially reducing the required number of ablation lesions and procedure time.

Fig. 1

The in vitro experimental chamber. A myocardial (M) sample rests in front of a sound absorbing backing (B) on a vertical mount box. A lesion (L) was made using a radiofrequency ablation device (AD) connected to a foil ground electrode (GE) and an ablation catheter (AC) brought into contact with the myocardium though a guide sheath (GS). An ultrasound scanner (US) imaged the lesion with an AcuNav^™ transducer (AT). The imaging catheter was adjusted to the desired imaging plane (IP) using a translation stage (TS) and rotation dial (RD).

Fig. 2

Myocardial sample (M) was placed in a mount box with 30° slicing slits (SS) on the top and bottom edges. The RFA lesion (L) was created between these two slits and imaged by the AcuNav^™ transducer (AT), with the imaging plane (IP) positioned along the 30° plane. The myocardial sample was then cut in the imaging plane using the slits as guides.

Fig. 3

(a) B-mode image and (b) digital image of a RFA lesion sliced along the 30° imaging plane. Image of maximum ARFI-induced displacement overlaid onto: (c) the B-mode image and (d) the digital photograph of the lesion cross-section. Depth normalized maximum ARFI-induced displacement data overlaid onto: (e) the B-mode image and (f) the digital image of the lesion cross-section. The color bar units in (c) and (d) are μm displacement away from the transducer; in plates (e) and (f) the colors represent the fraction of the maximum displacement at a given depth.

Fig. 4

Examples of raw and normalized ARFI images and of the human and machine determined lesion boundaries. Each row contains images for a separate lesion. Column (a) is the maximum ARFI-induced displacement image overlaid onto the photograph of the lesion cross-section. Column (b) is the depth normalized ARFI image overlaid onto the cross-section photograph. Column (c) shows the lesion boundary traces as determined by a manual segmentation based on the digital image (black) and the automatic ARFI imaging segmentations based on the optimal (blue) and standardized (green) thresholds. Lesions 1 and 2 were imaged with the custom 128-element AcuNav^™, while lesion 3 was imaged with a commercially available 64-element AcuNav^™. The automatic threshold traces for lesion 3 are identical and overlap. The color bar units in column (a) are μm displacement away from transducer; in column (b) the colors represent the fraction of the maximum displacement at a given depth.