Conventional photoacoustic (PA) imaging suffers from visibility artefacts due to limitations in ultrasound transducer bandwidth, viewing angles, and the use of sparse arrays. PA fluctuation imaging (PAFI), exploiting the signal changes due to blood flow, compensates for these artefacts, at the cost of temporal resolution.
Our study addresses this limitation employing a deep learning approach in which PAFI images serve as ground truths for training a 3D neural network to obtain real-time single-shot artefact-free images.
Following a pre-training with simulated examples, a 3D-ResUnet network was trained with 90 PA chicken embryo vasculature volumes as input and corresponding PAFI as ground truths. Notably, inclusion of experimental data significantly improves predictions over simulation-only training, even accounting for transducer angular filtering.
Furthermore, applying the same network exclusively trained in-ovo to predict the femoral artery in mice demonstrates the potential of this method for real-time, full-visibility multispectral PA imaging in vivo using sparse arrays.
Photoacoustic imaging (PAI) provides optical contrast at depth beyond the optical transport mean free path. From the generation of ultrasound by light absorption, images can be reconstructed at the acoustic resolution ( 100 μm) with a penetration of a few cm. The design of imaging systems often leads to limited view artifacts, where a part of the information needed for a complete reconstruction of the objects is missing. We theoretically show that a dynamic approach based on the analysis of fluctuations induced by blood flow can suppress visibility artefacts. We demonstrate the performance of 3D Photoacoustic Fluctuation imaging (PAFI) using a spherical array with limited number of channels (256
elements, 8 MHz) in the chicken embryo model. Due to the low number of channels, standard PAI reconstructions additionally suffer from a poor contrast, which is enhanced by 2 to 3-fold using PAFI. We present an implementation of simultaneous PAFI and Ultrasound Power Doppler and present some results with coupled flow direction evaluations and optical contrast. Photoacoustic fluctuation imaging overcomes many limitations of conventional imaging and will be further evaluated for in-vivo imaging.
KEYWORDS: Monte Carlo methods, Simulation of CCA and DLA aggregates, Photography, Data modeling, Visibility, Image quality, Computer simulations, Photoacoustic imaging, Veins, Transducers
In conventional photoacoustics (PA) imaging, the finite size and limited-bandwidth of ultrasound transducers often lead to visibility artifacts resulting in a degraded image quality. We propose a reconstruction algorithm based on deep learning to address theses issues. An in vitro vasculature mimicking model has been used in order to show the capability of a conventional neural network to remove these artefacts in an experimental configuration. The deep learning algorithm is trained using couples of PA images and ground truth photographs. The uncertainty of the model prediction is estimated through the Monte Carlo dropout method allowing the display of a pixel-wise degree of confidence. Finally, the interest of using simulation data through transfer learning in order to reduce the size of the experimental dataset is investigated.
We investigate the use of a 256-channel spherically focused sparse array for volumic real-time ultrasound (US) and photoacoustic (PA) imaging of chicken embryo in vivo. Reconstructions were performed offline and signal processing techniques exploiting spatial and temporal dynamics of the blood flow were applied to visualize the vasculature. The resulting reduction of the clutter enhances the contrast by up to a factor of 2, providing an enhanced visualization of vascular networks.
This methodology has a potential for in vivo 3D real time visualization of the vasculature and other features using complementary information provided by US and PA imaging.
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.