Deep-learning-based tomographic imaging is an important application of artificial intelligence and a new frontier of machine learning. Deep learning has been widely used in computer vision and image analysis, which deal with existing images, improve these images, and produce features from them. Since 2016, deep learning techniques have been actively researched for tomographic imaging, especially in the context of biomedicine, with impressive results and great potential. Tomographic reconstruction produces images of multi-dimensional structures from externally measured ‘encoded’ data in the form of various tomographic transforms (integrals, harmonics, echoes and so on). In this Review, we provide a general background, highlight representative results with an emphasis on medical imaging, and discuss key issues that need to be addressed in this emerging field. In particular, tomographic imaging is an integral part of modern medicine, and will play a key role in personalized, preventive and precision medicine and make it intelligent, inexpensive and indiscriminate. The popularity of deep learning is leading to new areas in biomedical applications. Wang and colleagues summarize in this Review the recent development and future directions of deep neural networks for superior image quality in the tomographic imaging field.

Deep learning for tomographic image reconstruction

Photoacoustic tomography (PAT) is a non-ionizing imaging modality capable of acquiring high contrast and resolution images of optical absorption at depths greater than traditional optical imaging techniques. Practical considerations with instrumentation and geometry limit the number of available acoustic sensors and their “view” of the imaging target, which result in image reconstruction artifacts degrading image quality. Iterative reconstruction methods can be used to reduce artifacts but are computationally expensive. In this work, we propose a novel deep learning approach termed pixel-wise deep learning (Pixel-DL) that first employs pixel-wise interpolation governed by the physics of photoacoustic wave propagation and then uses a convolution neural network to reconstruct an image. Simulated photoacoustic data from synthetic, mouse-brain, lung, and fundus vasculature phantoms were used for training and testing. Results demonstrated that Pixel-DL achieved comparable or better performance to iterative methods and consistently outperformed other CNN-based approaches for correcting artifacts. Pixel-DL is a computationally efficient approach that enables for real-time PAT rendering and improved image reconstruction quality for limited-view and sparse PAT.

/pdf/limited-view-and-sparse-photoacoustic-tomography-for-4167ot1bry.pdf

Limited-View and Sparse Photoacoustic Tomography for Neuroimaging with Deep Learning.

Biomedical photoacoustic tomography, which can provide high-resolution 3D soft tissue images based on optical absorption, has advanced to the stage at which translation from the laboratory to clinical settings is becoming possible. The need for rapid image formation and the practical restrictions on data acquisition that arise from the constraints of a clinical workflow are presenting new image reconstruction challenges. There are many classical approaches to image reconstruction, but ameliorating the effects of incomplete or imperfect data through the incorporation of accurate priors is challenging and leads to slow algorithms. Recently, the application of deep learning (DL), or deep neural networks, to this problem has received a great deal of attention. We review the literature on learned image reconstruction, summarizing the current trends and explain how these approaches fit within, and to some extent have arisen from, a framework that encompasses classical reconstruction methods. In particular, it shows how these techniques can be understood from a Bayesian perspective, providing useful insights. We also provide a concise tutorial demonstration of three prototypical approaches to learned image reconstruction. The code and data sets for these demonstrations are available to researchers. It is anticipated that it is in in vivo applications—where data may be sparse, fast imaging critical, and priors difficult to construct by hand—that DL will have the most impact. With this in mind, we conclude with some indications of possible future research directions.

https://www.spiedigitallibrary.org/journals/journal-of-biomedical-optics/volume-25/issue-11/112903/Deep-learning-in-photoacoustic-tomography--current-approaches-and-future/10.1117/1.JBO.25.11.112903.pdf

Deep learning in photoacoustic tomography: current approaches and future directions

Deep learning for biomedical photoacoustic imaging: A review.

One primary technical challenge in photoacoustic microscopy (PAM) is the necessary compromise between spatial resolution and imaging speed. In this study, we propose a novel application of deep learning principles to reconstruct undersampled PAM images and transcend the trade-off between spatial resolution and imaging speed. We compared various convolutional neural network (CNN) architectures, and selected a Fully Dense U-net (FD U-net) model that produced the best results. To mimic various undersampling conditions in practice, we artificially downsampled fully-sampled PAM images of mouse brain vasculature at different ratios. This allowed us to not only definitively establish the ground truth, but also train and test our deep learning model at various imaging conditions. Our results and numerical analysis have collectively demonstrated the robust performance of our model to reconstruct PAM images with as few as 2% of the original pixels, which can effectively shorten the imaging time without substantially sacrificing the image quality.

Reconstructing Undersampled Photoacoustic Microscopy Images Using Deep Learning

The rapidly evolving field of optoacoustic (photoacoustic) imaging and tomography is driven by a constant need for better imaging performance in terms of resolution, speed, sensitivity, depth and contrast. In practice, data acquisition strategies commonly involve sub-optimal sampling of the tomographic data, resulting in inevitable performance trade-offs and diminished image quality. We propose a new framework for efficient recovery of image quality from sparse optoacoustic data based on a deep convolutional neural network and demonstrate its performance with whole body mouse imaging in vivo. To generate accurate high-resolution reference images for optimal training, a full-view tomographic scanner capable of attaining superior cross-sectional image quality from living mice was devised. When provided with images reconstructed from substantially undersampled data or limited-view scans, the trained network was capable of enhancing the visibility of arbitrarily oriented structures and restoring the expected image quality. Notably, the network also eliminated some reconstruction artefacts present in reference images rendered from densely sampled data. No comparable gains were achieved when the training was performed with synthetic or phantom data, underlining the importance of training with high-quality in vivo images acquired by full-view scanners. The new method can benefit numerous optoacoustic imaging applications by mitigating common image artefacts, enhancing anatomical contrast and image quantification capacities, accelerating data acquisition and image reconstruction approaches, while also facilitating the development of practical and affordable imaging systems. The suggested approach operates solely on image-domain data and thus can be seamlessly applied to artefactual images reconstructed with other modalities. Optoacoustic imaging can achieve high spatial and temporal resolution but image quality is often compromised by suboptimal data acquisition. A new method employing deep learning to recover high-quality images from sparse or limited-view optoacoustic scans has been developed and demonstrated for whole-body mouse imaging in vivo.

Deep learning optoacoustic tomography with sparse data

Respiratory motion in living organisms is known to result in image blurring and loss of resolution, chiefly due to the lengthy acquisition times of the corresponding image acquisition methods Optoacoustic tomography can effectively eliminate in vivo motion artifacts due to its inherent capacity for collecting image data from the entire imaged region following a single nanoseconds-duration laser pulse However, multi-frame image analysis is often essential in applications relying on spectroscopic data acquisition or for scanning-based systems Thereby, efficient methods to correct for image distortions due to motion are imperative Herein, we demonstrate that efficient motion rejection in optoacoustic tomography can readily be accomplished by frame clustering during image acquisition, thus averting excessive data acquisition and post-processing The algorithm’s efficiency for two- and three-dimensional imaging was validated with experimental whole-body mouse data acquired by spiral volumetric optoacoustic tomography (SVOT) and full-ring cross-sectional imaging scanners

https://www.zora.uzh.ch/id/eprint/176184/1/applsci-09-02737.pdf

Self-Gated Respiratory Motion Rejection for Optoacoustic Tomography

Images rendered with common optoacoustic system implementations are often afflicted with distortions and poor visibility of structures, hindering reliable image interpretation and quantification of bio-chrome distribution. Among the practical limitations contributing to artifactual reconstructions are insufficient tomographic detection coverage and suboptimal illumination geometry, as well as inability to accurately account for acoustic reflections and speed of sound heterogeneities in the imaged tissues. Here we developed a convolutional neural network (CNN) approach for enhancement of optoacoustic image quality which combines training on both time-resolved signals and tomographic reconstructions. Reference human finger data for training the CNN were recorded using a full-ring array system that provides optimal tomographic coverage around the imaged object. The reconstructions were further refined with a dedicated algorithm that minimizes acoustic reflection artifacts induced by acoustically mismatch structures, such as bones. The combined methodology is shown to outperform other learning-based methods solely operating on image-domain data.

Deep learning of image- and time-domain data enhances the visibility of structures in optoacoustic tomography.

Multi-spectral optoacoustic tomography (MSOT) relies on optical excitation of tissues with subsequent detection of the generated ultrasound waves. Optimal image quality in MSOT is achieved by detection of signals from a broad tomographic view. However, due to physical constraints and other cost-related considerations, most imaging systems are implemented with probes having limited tomographic coverage around the imaged object, such as linear array transducers often employed for clinical ultrasound (US) imaging. MSOT image reconstruction from limited-view data results in arc-shaped image artifacts and disrupted shape of the vascular structures. Deep learning methods have previously been used to recover MSOT images from incomplete tomographic data, albeit poor performance was at-tained when training with data from simulations or other imaging modalities. We propose a two-step method consisting of i) style transfer for domain adaptation between simulated and experimental MSOT signals

Neda Davoudi

Papers

Deep learning optoacoustic tomography with sparse data

Self-Gated Respiratory Motion Rejection for Optoacoustic Tomography

Deep learning of image- and time-domain data enhances the visibility of structures in optoacoustic tomography.

Signal Domain Learning Approach for Optoacoustic Image Reconstruction from Limited View Data

Biomedical data analysis from bidirectional optical-acoustic interface