Siyu Liu

Photoacoustic imaging provides optical-absorption contrast through ultrasonic detection. However, image reconstruction remains affected by acquisition geometry, detector response, acoustic noise, and the attenuation of high-frequency components during analytic inversion. Although deep post-processing methods have shown effectiveness in artifact reduction, purely image-domain restoration lacks a direct mechanism for incorporating complementary information contained in the raw measurement data. This work proposes OGRR-Net, an observation-guided residual refinement network for photoacoustic imaging. The network takes an initial reconstruction as the spatial reference and encodes the corresponding raw sinogram into an observation-guidance map, which conditions a gated residual correction pathway for image refinement. Evaluated on an in vivo mouse dataset and the OADAT optoacoustic dataset against representative image-domain and hybrid reconstruction methods, the proposed observation-guided strategy improves reconstruction fidelity, reduces artifacts, and enhances the preservation of structural details.

To address the ill-posedness inherent in photoacoustic tomography reconstruction, we propose ZS-PSNN, a zero-shot physics-supervised neural network framework that eliminates the reliance on external paired training data. By explicitly constructing a discretized acoustic system matrix and embedding it as a differentiable forward operator within the loss function, the proposed method enforces acoustic measurement consistency to supervise the neural network optimization directly from a single scan. Results on simulated vascular data and experimental mouse data demonstrate that ZS-PSNN achieves competitive reconstruction performance compared with FBP, TR, model-based TV regularization, plug-and-play TV, and implicit neural representation methods. This work establishes a single-measurement physics-supervised neural optimization strategy for zero-shot photoacoustic reconstruction applicable to scenarios where high-quality paired training data are challenging to obtain.

Ultrasonic Non-Destructive Testing (NDT) technology

Photoacoustic tomography has developed rapidly in recent years and holds great potential for applications in the biomedical field. In photoacoustic tomography, the quality of the final reconstructed image mainly depends on the choice of reconstruction algorithm. However, traditional filtered back projection algorithms may introduce negative artifacts into the final reconstructed images due to the finite bandwidth of ultrasound transducers. To address the issue of negative artifacts, we propose a photoacoustic imaging method based on the virtual orthogonal wave field. This method converts the original photoacoustic signals into pairs of virtual orthogonal signals, constructs the real and imaginary parts of the photoacoustic complex signal from them and extracts the virtual photoacoustic envelope, thereby obtaining a reconstruction image without negative artifacts. In this work, we propose the theory of the virtual orthogonal wave field. By combining the point spread function based on spherical harmonics with the theory of the virtual orthogonal wave field, the point spread function of the virtual orthogonal wave field method is derived, we explain the theoretical basis for non-negative imaging using this method. The result of simulations and experiments demonstrates that this method can effectively eliminate negative artifacts and improve image fidelity.

Medium heterogeneity poses a severe challenge to image reconstruction in transcranial photoacoustic tomography, which cannot be fully addressed by the homogeneous phase shift migration method. Although the existing methods can enhancethe imaging quality to a certain extent, they are limited by the large approximation errors and low computational efficiency. To further improve imaging performance and calculation speed, this paper proposes full matrix wavefield migration, which takes into account both lateral and longitudinal variations of speed of sound (SOS). Unlike the PSM method which relies on a layer-by-layer migration framework, the proposed approach reformulates the SOS map across the propagation medium into a spatial matrix of SOS. By means of extrapolating wavefield data in the wavenumber domain and correcting phase deviations in the spatial domain, this method reduces the image distortion caused by SOS irregularity and suppresses artifacts in reconstructed images. Moreover, the calculation process is further optimized to eliminate redundancy. Simulation and experimental results demonstrate that full matrix wavefield migration method improves lateral resolution (up to 21.24%) and computational efficiency (about 19.84%) compared to the previous methods.

To address the issue of low imaging quality in compressed sensing photoacoustic imaging methods under high undersampling, a three-stage compressed sensing method is proposed. This method effectively increases the sampling rate while maintaining the same number of sensors, thereby enhancing reconstruction quality. Initially, in the fully sampled scenario, spatial and temporal operators are created, transforming the target recovery signal from complete photoacoustic data into a signal that is compressed in both spatial and temporal domains through these operators. Random undersampling is then performed in the spatial domain, and the compressed signal is recovered using the observation signal and curvelet domain compressed sensing. Subsequently, the inverse operator is applied to restore the compressed signal to complete photoacoustic data. Finally, traditional photoacoustic reconstruction methods are combined for imaging. Simulation and experimental results indicate that the three-stage compressed sensing photoacoustic imaging method not only retains the low cost and high-speed advantages of the two-stage method but also significantly improves the quality of photoacoustic imaging.

The miniaturization and real time imaging capability have always been the desired properties of photoacoustic imaging (PAI) system, which unlocked vast potential for personalized healthcare and diagnostics. While the imaging quality and resolution in such systems are inferior due to physics and system volume constraints, which limited its wide deployment and application. This paper proposes a novel platform to enhance the imaging quality of handheld PAI system in real time, integrating MultiResU-Net imaging enhancement algorithm with Ferroelectric random-access memory (FeRAM) crossbar array. The FeRAM crossbar array enables in memory computing, which is highly suitable for accelerating deep neural network where extensive matrix multiplications are involved. The hardware implementation of the algorithm is optimized for low-power operation on edge devices, a specifically designed algorithmic strategy is further introduced to accurately simulate the impact of hardware variation on the computation in the array with time complexity of O(mn). The feasibility and effectiveness of this method are demonstrated through simulation data (synthesized through physical model) and in vivo data, the experimental results demonstrate more than 10 times of imaging resolution improvement. The execution of neural network inference has been significantly accelerated and can be completed within a few microseconds, fully covering the imaging speed in handheld PAI system and satisfying the real time imaging capability. The whole platform can be integrated into a compact size of 25×25×20 cm³, which is a portable system with real time and high resolution imaging capability.

To facilitate photoacoustic imaging in heterogeneous media such as transcranial imaging and breast imaging, an increasing number of heterogeneous photoacoustic methods have been proposed. Nonetheless, prevailing reconstruction methods require prior knowledge of the speed of sound (SOS) distribution, which is often impractical in industrial applications. To mitigate the dependency on prior knowledge of the SOS distribution, this paper introduces the blind autofocus method. This method employs passive ultrasound technique to obtain the temporal matrix of SOS and stratified traversal of SOS values to determine the optimized spatial matrix of SOS. The feasibility of this approach in reconstructing the initial pressure in heterogeneous media is evaluated through simulation and experiments. The results demonstrate the capability of the blind autofocus method in achieving high-quality reconstruction in 3D stratified medium.

Photoacoustic imaging (PAI) is a rapidly developing emerging non-invasive biomedical imaging technique that combines the strong contrast from optical absorption imaging and the high resolution from acoustic imaging. Abnormal biological tissues (such as tumors and inflammation) generate different levels of thermal expansion after absorbing optical energy, producing distinct acoustic signals from normal tissues. This technique can detect small tissue lesions in biological tissues and has demonstrated significant potential for applications in tumor research, melanoma detection, and cardiovascular disease diagnosis. During the process of collecting photoacoustic signals in a PAI system, various factors can influence the signals, such as absorption, scattering, and attenuation in biological tissues. A single ultrasound transducer cannot provide sufficient information to reconstruct high-precision photoacoustic images. To obtain more accurate and clear image reconstruction results, PAI systems typically use a large number of ultrasound transducers to collect multi-channel signals from different angles and positions, thereby acquiring more information about the photoacoustic signals. Therefore, to reconstruct high-quality photoacoustic images, PAI systems require a significant number of measurement signals, which can result in substantial hardware and time costs. Compressed sensing is an algorithm that breaks through the Nyquist sampling theorem and can reconstruct the original signal with a small number of measurement signals. PAI based on compressed sensing has made breakthroughs over the past decade, enabling the reconstruction of low artifacts and high-quality images with a small number of photoacoustic measurement signals, improving time efficiency, and reducing hardware costs. This article provides a detailed introduction to PAI based on compressed sensing, such as the physical transmission model-based compressed sensing method, two-stage reconstruction-based compressed sensing method, and single-pixel camera-based compressed sensing method. Challenges and future perspectives of compressed sensing-based PAI are also discussed.