Double speed-of-sound photoacoustic image reconstruction at ten frames-per-second with automatic segmentation

Abstract

Photoacoustic computed tomography (PACT), also known as optoacoustic or thermoacoustic tomography, is a rapidly emerging hybrid imaging modality that combines optical image contrast with ultrasound detection. Most currently available PACT image reconstruction algorithms are based on idealized imaging models that assume a lossless and acoustically homogeneous medium. However, in many applications of PACT, if the non-uniform acoustic properties of objects are not considered in the reconstruction algorithm, the reconstructed images may contain significant distortions and artifacts. This paper proposes a fully automatic double-SoS (Speed-of-sound) reconstruction algorithm which runs at 10Hzfortwo-dimensional images of (512)(512) pixels. The algorithm uses a deep learning model to segment the animal’s outer profile from the water background. We adaptively calculate the most appropriate sound speed and assign different sound speeds to the two regions for PA image reconstruction. The reconstructed images were compared to those reconstructed using a uniform SoS quantitatively.

Challenges and advances in two-dimensional photoacoustic computed tomography: a review

“…Panel (c) is reproduced with permission from Ref. 114. (d)(i) Illustrations of the system hardware setup of the ADS-USPACT.…”

“…Reference 114 utilized a U-Net 123 model to identify the object PA surface signal in raw data and reconstruct the object shape [shown in Fig. 7(c)(i–iii)].…”