Deep-Learning Image Reconstruction for Real-Time Photoacoustic System

Deep learning for biomedical photoacoustic imaging: A review

Photoacoustic imaging (PAI) is a promising emerging imaging modality that enables spatially resolved imaging of optical tissue properties up to several centimeters deep in tissue, creating the potential for numerous exciting clinical applications. However, extraction of relevant tissue parameters from the raw data requires the solving of inverse image reconstruction problems, which have proven extremely difficult to solve. The application of deep learning methods has recently exploded in popularity, leading to impressive successes in the context of medical imaging and also finding first use in the field of PAI. Deep learning methods possess unique advantages that can facilitate the clinical translation of PAI, such as extremely fast computation times and the fact that they can be adapted to any given problem. In this review, we examine the current state of the art regarding deep learning in PAI and identify potential directions of research that will help to reach the goal of clinical applicability.

Enhancement of in vivo cardiac photoacoustic signal specificity using spatiotemporal singular value decomposition

SIGNIFICANCE

Photoacoustic imaging (PAI) can be used to infer molecular information about myocardial health non-invasively in vivo using optical excitation at ultrasonic spatial resolution. For clinical and preclinical linear array imaging systems, conventional delay-and-sum (DAS) beamforming is typically used. However, DAS cardiac PA images are prone to artifacts such as diffuse quasi-static clutter with temporally varying noise-reducing myocardial signal specificity. Typically, multiple frame averaging schemes are utilized to improve the quality of cardiac PAI, which affects the spatial and temporal resolution and reduces sensitivity to subtle PA signal variation. Furthermore, frame averaging might corrupt myocardial oxygen saturation quantification due to the presence of natural cardiac wall motion. In this paper, a spatiotemporal singular value decomposition (SVD) processing algorithm is proposed to reduce DAS PAI artifacts and subsequent enhancement of myocardial signal specificity.

AIM

Demonstrate enhancement of PA signals from myocardial tissue compared to surrounding tissues and blood inside the left-ventricular (LV) chamber using spatiotemporal SVD processing with electrocardiogram (ECG) and respiratory signal (ECG-R) gated in vivo murine cardiac PAI.

APPROACH

In vivo murine cardiac PAI was performed by collecting single wavelength (850 nm) photoacoustic channel data on eight healthy mice. A three-dimensional (3D) volume of complex PAI data over a cardiac cycle was reconstructed using a custom ECG-R gating algorithm and DAS beamforming. Spatiotemporal SVD was applied on a two-dimensional Casorati matrix generated using the 3D volume of PAI data. The singular value spectrum (SVS) was then filtered to remove contributions from diffuse quasi-static clutter and random noise. Finally, SVD processed beamformed images were derived using filtered SVS and inverse SVD computations.

RESULTS

Qualitative comparison with DAS and minimum variance (MV) beamforming shows that SVD processed images had better myocardial signal specificity, contrast, and target detectability. DAS, MV, and SVD images were quantitatively evaluated by calculating contrast ratio (CR), generalized contrast-to-noise ratio (gCNR), and signal-to-noise ratio (SNR). Quantitative evaluations were done at three cardiac time points (during systole, at end-systole (ES), and during diastole) identified from co-registered ultrasound M-Mode image. Mean CR, gCNR, and SNR values of SVD images at ES were 245, 115.15, and 258.17 times higher than DAS images with statistical significance evaluated with one-way analysis of variance.

CONCLUSIONS

Our results suggest that significantly better-quality images can be realized using spatiotemporal SVD processing for in vivo murine cardiac PAI.

Deep learning in photoacoustic imaging: a review

SIGNIFICANCE

Photoacoustic (PA) imaging can provide structural, functional, and molecular information for preclinical and clinical studies. For PA imaging (PAI), non-ideal signal detection deteriorates image quality, and quantitative PAI (QPAI) remains challenging due to the unknown light fluence spectra in deep tissue. In recent years, deep learning (DL) has shown outstanding performance when implemented in PAI, with applications in image reconstruction, quantification, and understanding.

AIM

We provide (i) a comprehensive overview of the DL techniques that have been applied in PAI, (ii) references for designing DL models for various PAI tasks, and (iii) a summary of the future challenges and opportunities.

APPROACH

Papers published before November 2020 in the area of applying DL in PAI were reviewed. We categorized them into three types: image understanding, reconstruction of the initial pressure distribution, and QPAI.

RESULTS

When applied in PAI, DL can effectively process images, improve reconstruction quality, fuse information, and assist quantitative analysis.

CONCLUSION

DL has become a powerful tool in PAI. With the development of DL theory and technology, it will continue to boost the performance and facilitate the clinical translation of PAI.

Review of deep learning for photoacoustic imaging

Machine learning has been developed dramatically and witnessed a lot of applications in various fields over the past few years. This boom originated in 2009, when a new model emerged, that is, the deep artificial neural network, which began to surpass other established mature models on some important benchmarks. Later, it was widely used in academia and industry. Ranging from image analysis to natural language processing, it fully exerted its magic and now become the state-of-the-art machine learning models. Deep neural networks have great potential in medical imaging technology, medical data analysis, medical diagnosis and other healthcare issues, and is promoted in both pre-clinical and even clinical stages. In this review, we performed an overview of some new developments and challenges in the application of machine learning to medical image analysis, with a special focus on deep learning in photoacoustic imaging. The aim of this review is threefold: (i) introducing deep learning with some important basics, (ii) reviewing recent works that apply deep learning in the entire ecological chain of photoacoustic imaging, from image reconstruction to disease diagnosis, (iii) providing some open source materials and other resources for researchers interested in applying deep learning to photoacoustic imaging.

Compensating for visibility artefacts in photoacoustic imaging with a deep learning approach providing prediction uncertainties

Conventional photoacoustic imaging may suffer from the limited view and bandwidth of ultrasound transducers. A deep learning approach is proposed to handle these problems and is demonstrated both in simulations and in experiments on a multi-scale model of leaf skeleton. We employed an experimental approach to build the training and the test sets using photographs of the samples as ground truth images. Reconstructions produced by the neural network show a greatly improved image quality as compared to conventional approaches. In addition, this work aimed at quantifying the reliability of the neural network predictions. To achieve this, the dropout Monte-Carlo procedure is applied to estimate a pixel-wise degree of confidence on each predicted picture. Last, we address the possibility to use transfer learning with simulated data in order to drastically limit the size of the experimental dataset.

Real-time interleaved spectroscopic photoacoustic and ultrasound (PAUS) scanning with simultaneous fluence compensation and motion correction

For over two decades photoacoustic imaging has been tested clinically, but successful human trials have been limited. To enable quantitative clinical spectroscopy, the fundamental issues of wavelength-dependent fluence variations and inter-wavelength motion must be overcome. Here we propose a real-time, spectroscopic photoacoustic/ultrasound (PAUS) imaging approach using a compact, 1-kHz rate wavelength-tunable laser. Instead of illuminating tissue over a large area, the fiber-optic delivery system surrounding an US array sequentially scans a narrow laser beam, with partial PA image reconstruction for each laser pulse. The final image is then formed by coherently summing partial images. This scheme enables (i) automatic compensation for wavelength-dependent fluence variations in spectroscopic PA imaging and (ii) motion correction of spectroscopic PA frames using US speckle tracking in real-time systems. The 50-Hz video rate PAUS system is demonstrated in vivo using a murine model of labelled drug delivery.

Another decade of photoacoustic imaging

Photoacoustic imaging - a hybrid biomedical imaging modality finding its way to clinical practices. Although the photoacoustic phenomenon was known more than a century back, only in the last two decades it has been widely researched and used for biomedical imaging applications. In this review we focus on the development and progress of the technology in the last decade (2010-2020). From becoming more and more user friendly, cheaper in cost, portable in size, photoacoustic imaging promises a wide range of applications, if translated to clinic. The growth of photoacoustic community is steady, and with several new directions researchers are exploring, it is inevitable that photoacoustic imaging will one day establish itself as a regular imaging system in the clinical practices.

Convolutional neural network for resolution enhancement and noise reduction in acoustic resolution photoacoustic microscopy

In acoustic resolution photoacoustic microscopy (AR-PAM), a high numerical aperture focused ultrasound transducer (UST) is used for deep tissue high resolution photoacoustic imaging. There is a significant degradation of lateral resolution in the out-of-focus region. Improvement in out-of-focus resolution without degrading the image quality remains a challenge. In this work, we propose a deep learning-based method to improve the resolution of AR-PAM images, especially at the out of focus plane. A modified fully dense U-Net based architecture was trained on simulated AR-PAM images. Applying the trained model on experimental images showed that the variation in resolution is ∼10% across the entire imaging depth (∼4 mm) in the deep learning-based method, compared to ∼180% variation in the original PAM images. Performance of the trained network on in vivo rat vasculature imaging further validated that noise-free, high resolution images can be obtained using this method.

End-to-end Res-Unet based reconstruction algorithm for photoacoustic imaging

Recently, deep neural networks have attracted great attention in photoacoustic imaging (PAI). In PAI, reconstructing the initial pressure distribution from acquired photoacoustic (PA) signals is a typically inverse problem. In this paper, an end-to-end Unet with residual blocks (Res-Unet) is designed and trained to solve the inverse problem in PAI. The performance of the proposed algorithm is explored and analyzed by comparing a recent model-resolution-based regularization algorithm (MRR) with numerical and physical phantom experiments. The improvement obtained in the reconstructed images was more than 95% in pearson correlation and 39% in peak signal-to-noise ratio in comparison to the MRR. The Res-Unet also achieved superior performance over the state-of-the-art Unet++ architecture by more than 18% in PSNR in simulation experiments.

Correction of wavelength-dependent laser fluence in swept-beam spectroscopic photoacoustic imaging with a hand-held probe

Recently, we demonstrated an integrated photoacoustic (PA) and ultrasound (PAUS) system using a kHz-rate wavelength-tunable laser and a swept-beam delivery approach. It irradiates a medium using a narrow laser beam swept at high repetition rate (∼1 kHz) over the desired imaging area, in contrast to the conventional PA approach using broad-beam illumination at a low repetition rate (10-50 Hz). Here, we present a method to correct the wavelength-dependent fluence distribution and demonstrate its performance in phantom studies using a conventional limited view/bandwidth hand-held US probe. We adopted analytic fluence models, extending diffusion theory for the case of a pencil beam obliquely incident on an optically homogenous turbid medium, and developed a robust method to estimate fluence attenuation in the medium using PA measurements acquired from multiple fiber-irradiation positions swept at a kHz rate. We conducted comprehensive simulation tests and phantom studies using well-known contrast-agents to validate the reliability of the fluence model and its spectral corrections.