KEYWORDS: In vivo imaging, Heart, Histograms, Photoacoustic spectroscopy, Transducers, Computer simulations, Phased arrays, Data processing, Education and training, Deep learning
SignificanceInterventional cardiac procedures often require ionizing radiation to guide cardiac catheters to the heart. To reduce the associated risks of ionizing radiation, photoacoustic imaging can potentially be combined with robotic visual servoing, with initial demonstrations requiring segmentation of catheter tips. However, typical segmentation algorithms applied to conventional image formation methods are susceptible to problematic reflection artifacts, which compromise the required detectability and localization of the catheter tip.AimWe describe a convolutional neural network and the associated customizations required to successfully detect and localize in vivo photoacoustic signals from a catheter tip received by a phased array transducer, which is a common transducer for transthoracic cardiac imaging applications.ApproachWe trained a network with simulated photoacoustic channel data to identify point sources, which appropriately model photoacoustic signals from the tip of an optical fiber inserted in a cardiac catheter. The network was validated with an independent simulated dataset, then tested on data from the tips of cardiac catheters housing optical fibers and inserted into ex vivo and in vivo swine hearts.ResultsWhen validated with simulated data, the network achieved an F1 score of 98.3% and Euclidean errors (mean ± one standard deviation) of 1.02 ± 0.84 mm for target depths of 20 to 100 mm. When tested on ex vivo and in vivo data, the network achieved F1 scores as large as 100.0%. In addition, for target depths of 40 to 90 mm in the ex vivo and in vivo data, up to 86.7% of axial and 100.0% of lateral position errors were lower than the axial and lateral resolution, respectively, of the phased array transducer.ConclusionsThese results demonstrate the promise of the proposed method to identify photoacoustic sources in future interventional cardiology and cardiac electrophysiology applications.
Multiple image quality metrics are currently available to assess target detectability in photoacoustic images. Common metrics include contrast, contrast-to-noise ratio (CNR), and signal-to-noise ratio (SNR). The generalized contrast-to-noise ratio (gCNR) is a relatively new image quality metric to assess the probability of photoacoustic target detectability. This paper demonstrates the applicability of gCNR to assess photoacoustic image quality using simulated and experimental images created with delay-and-sum (DAS), short-lag spatial coherence (SLSC), generalized coherence factor weighting combined with DAS (GCF+DAS), and minimum variance (MV) beamforming. Images were created from data acquired with a fixed light source with output energy values increasing from 2 mJ to 35 mJ. The gCNR converged to 0.93, 0.98, 0.99, and 0.85 for DAS, SLSC, GCF+DAS, and MV beamforming, respectively, at energies of approximately 20, 10, 10, and 20 mJ, respectively. These results indicate that gCNR has the potential to determine the minimum laser energy needed to maximize the detectability of a photoacoustic target for any given image formation method.
Many cardiac interventional procedures (e.g., radiofrequency ablation) require fluoroscopy to navigate catheters in veins toward the heart. However, this image guidance method lacks depth information and increases the risks of radiation exposure for both patients and operators. To overcome these challenges, we developed a robotic visual servoing system that maintains visualization of segmented photoacoustic signals from a cardiac catheter tip. This system was tested in two in vivo cardiac catheterization procedures with ground truth position information provided by fluoroscopy and electromagnetic tracking. The 1D root mean square localization errors within the vein ranged 1.63 − 2.28 mm for the first experiment and 0.25 − 1.18 mm for the second experiment. The 3D root mean square localization error for the second experiment ranged 1.24 − 1.54 mm. The mean contrast of photoacoustic signals from the catheter tip ranged 29.8 − 48.8 dB when the catheter tip was visualized in the heart. Results indicate that robotic-photoacoustic imaging has promising potential as an alternative to fluoroscopic guidance. This alternative is advantageous because it provides depth information for cardiac interventions and enables enhanced visualization of the catheter tips within the beating heart.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.