Computed tomography (CT) is a widely used imaging technique in both medical and industrial applications. However, accurate CT reconstruction requires complete projection data, while incomplete data can result in significant artifacts in the reconstructed images, compromising their reliability for subsequent detection and diagnosis. As a result, accurate CT reconstruction from incomplete projection data remains a challenging research area in radiology. With the rapid development of deep learning (DL) techniques, many DL-based methods have been proposed for CT reconstruction from incomplete projection data. However, there are limited comprehensive surveys that summarize recent advances in this field. This paper provides a comprehensive overview of the current state-of-the-art DL-based CT reconstruction from incomplete projection data, including sparse-view reconstruction, limited-angle reconstruction, metal artifact reduction, interior tomography, and ring artifact reduction. This survey covers various DL-based solutions to the five problems, potential limitations of existing methods, and future research directions.

Ultrafast ultrasound imaging remains an active area of interest in the ultrasound community due to its ultrahigh frame rates. Recently, a wide variety of studies based on deep learning have sought to improve ultrafast ultrasound imaging. Most of these approaches have been performed on radio frequency (RF) signals. However, in- phase/quadrature (I/Q) digital beamformers are now widely used as low-cost strategies. In this work, we used complex convolutional neural networks for reconstruction of ultrasound images from I/Q signals. We recently described a convolutional neural network architecture called ID-Net, which exploited an inception layer designed for reconstruction of RF diverging-wave ultrasound images. In the present study, we derive the complex equivalent of this network, i.e., complex-valued inception for diverging-wave network (CID-Net) that operates on I/Q data. We provide experimental evidence that CID-Net provides the same image quality as that obtained from RF-trained convolutional neural networks, i.e., using only three I/Q images, CID-Net produces high-quality images that can compete with those obtained by coherently compounding 31 RF images. Moreover, we show that CID-Net outperforms the straightforward architecture that consists of processing real and imaginary parts of the I/Q signal separately, which thereby indicates the importance of consistently processing the I/Q signals using a network that exploits the complex nature of such signals.

In recent years, diverging wave (DW) ultrasound imaging has become a very promising methodology for cardiovascular imaging due to its high temporal resolution. However, if they are limited in number, DW transmits provide lower image quality compared with classical focused schemes. A conventional reconstruction approach consists in summing series of ultrasound signals coherently, at the expense of frame rate, data volume, and computation time. To deal with this limitation, we propose a convolutional neural networks (CNN) architecture, IDNet, for high-quality reconstruction of DW ultrasound images using a small number of transmissions. In order to cope with the specificities induced by the sectorial geometry associated to DW imaging, we adopted the inception model composed of the concatenation of multi-scale convolution kernels. Incorporating inception modules aims at capturing different image features with multi-scale receptive fields. A mapping between low-quality images and corresponding high-quality compounded reconstruction was learned by training the network using in vitro and in vivo samples. The performance of the proposed approach was evaluated in terms of contrast ratio (CR), contrast-to-noise ratio (CNR) and lateral resolution (LR), and compared with standard compounding method and conventional CNN methods. The results demonstrated that our method could produce highquality images using only 3 DWs, yielding an image quality equivalent to that obtained with compounding of 31 DWs and outperforming more conventional CNN architectures in terms of complexity, inference time and image quality.

Metal artifacts lead to CT imaging quality degradation. With the success of deep learning (DL) in medical imaging, a number of DL-based supervised methods have been developed for metal artifact reduction (MAR). Nonetheless, fully-supervised MAR methods based on simulated data do not perform well on clinical data due to the domain gap. Although this problem can be avoided in an unsupervised way to a certain degree, severe artifacts cannot be well suppressed in clinical practice. Recently, semi-supervised metal artifact reduction (MAR) methods have gained wide attention due to their ability in narrowing the domain gap and improving MAR performance in clinical data. However, these methods typically require large model sizes, posing challenges for optimization. To address this issue, we propose a novel semi-supervised MAR framework. In our framework, only the artifact-free parts are learned, and the artifacts are inferred by subtracting these clean parts from the metal-corrupted CT images. Our approach leverages a single generator to execute all complex transformations, thereby reducing the model's scale and preventing overlap between clean part and artifacts. To recover more tissue details, we distill the knowledge from the advanced dual-domain MAR network into our model in both image domain and latent feature space. The latent space constraint is achieved via contrastive learning. We also evaluate the impact of different generator architectures by investigating several mainstream deep learning-based MAR backbones. Our experiments demonstrate that the proposed method competes favorably with several state-of-the-art semi-supervised MAR techniques in both qualitative and quantitative aspects.

Ultrasound Imaging is one of the most widely used imaging modalities for clinic diagnosis, but suffers from a low resolution due to the intrinsic physical flaws. In this paper, we present a novel unsupervised super-resolution (USSR) framework to solve the single image super-resolution (SR) problem in ultrasound images which lack of training examples. Our method utilizes the powerful nonlinear mapping ability of convolutional neural networks (CNNs), without relying on prior training or any external data. We exploit the multi-scale contextual information extracted from the test image itself to train an image-specific network at test time. We utilize several techniques to improve the convergence and accuracy, including dilated convolution and residual learning. To capture valuable internal information, dilated convolution is employed to increase the receptive field without increasing the network parameters. To speed up the convergence of the training, residual learning is used to directly learn the difference between the high-resolution and low-resolution images. Quantitative and qualitative evaluations on real ultrasound images demonstrate that the proposed method outperforms the state-of-the-art unsupervised method.

High-quality ultrafast ultrasound imaging is based on coherent compounding from multiple transmissions of plane waves (PW) or diverging waves (DW). However, compounding results in reduced frame rate, as well as destructive interferences from high-velocity tissue motion if motion compensation (MoCo) is not considered. While many studies have recently shown the interest of deep learning for the reconstruction of high-quality static images from PW or DW, its ability to achieve such performance while maintaining the capability of tracking cardiac motion has yet to be assessed. In this paper, we addressed such issue by deploying a complex-weighted convolutional neural network (CNN) for image reconstruction and a state-of-the-art speckle tracking method. The evaluation of this approach was first performed by designing an adapted simulation framework, which provides specific reference data, i.e. high quality, motion artifact-free cardiac images. The obtained results showed that, while using only three DWs as input, the CNN-based approach yielded an image quality and a motion accuracy equivalent to those obtained by compounding 31 DWs free of motion artifacts. The performance was then further evaluated on non-simulated, experimental in vitro data, using a spinning disk phantom. This experiment demonstrated that our approach yielded high-quality image reconstruction and motion estimation, under a large range of velocities and outperforms a state-of-the-art MoCo-based approach at high velocities. Our method was finally assessed on in vivo datasets and showed consistent improvement in image quality and motion estimation compared to standard compounding. This demonstrates the feasibility and effectiveness of deep learning reconstruction for ultrafast speckle-tracking echocardiography.