IEEE TCI Article

Recently, deep-learning based methods have been widely used for computed tomography (CT) reconstruction. However, most of these methods need extra steps to convert the sinogrmas into CT images and so their networks are not end-to-end. In this paper, we propose an end-to-end deep network for CT image reconstruction, which directly maps sparse sinogramss to CT images. Our network has three cascaded blocks, where the first block is used to denoise and interpolate the sinograms, the second to map the sinograms to CT images and the last to denoise the CT images.

The use of microwave tomography (MWT) in an industrial drying process is demonstrated in this feasibility study with synthetic measurement data. The studied imaging modality is applied to estimate the moisture content distribution in a polymer foam during the microwave drying process. Such moisture information is crucial in developing control strategies for controlling the microwave power for selective heating.

Perfusion computed tomography (PCT) is critical in detecting cerebral ischemic lesions. PCT examination with lowdose scans can effectively reduce radiation exposure to patients at the cost of degraded images with severe noise, and artifacts. Tensor total variation (TTV) models are powerful tools that can encode the regional continuous structures underlying a PCT object.

The modeling of phenomenological structure is a crucial aspect in inverse imaging problems. One emerging modeling tool in computer vision is the optimal transport framework. Its ability to model geometric displacements across an image's support gives it attractive qualities similar to optical flow methods that are effective at capturing visual motion, but are restricted to operate in significantly smaller state-spaces. 

Fusion based hyperspectral image (HSI) super-resolution method, which obtains a spatially high-resolution (HR) HSI by fusing a low-resolution (LR) HSI and an HR conventional image, has been a prevalent method for HSI super-resolution. One effective fusion based method is to cast HSI super-resolution into a unified optimization problem, where handcrafted priors such as sparse prior or low rank prior are always adopted to regularize the latent HR HSI to be optimized. 

The coded aperture snapshot spectral imager (CASSI) is a computational imaging system that acquires a three dimensional (3D) spectral data cube by a single or a few two dimensional (2D) measurements. The 3D data cube is reconstructed computationally. Binary on-off random coded apertures with square pixels are primarily implemented in CASSI systems to modulate the spectral images in the image plane.

Users of X-ray (micro-)CT in research environments often study many different types of objects, with many different research questions. For each new scan, the settings of the scan (number of angles, dose, cone angle) are chosen by the user, often based on how much time is available, the dose sensitivity of the sample, and geometrical characteristics of the particular CT-scanner that is used.

Sparsity and low-rank models have been popular for reconstructing images and videos from limited or corrupted measurements. Dictionary or transform learning methods are useful in applications such as denoising, inpainting, and medical image reconstruction.

Good temporal representations are crucial for video understanding, and the state-of-the-art video recognition framework is based on two-stream networks. In such framework, besides the regular ConvNets responsible for RGB frame inputs, a second network is introduced to handle the temporal representation, usually the optical flow (OF). 

Three-dimensional (3-D) radar imaging can provide additional information along elevation dimension about the target with respect to the conventional 2-D radar imaging, but usually requires a huge amount of data collected over 3-D frequency-azimuth-elevation space, which motivates us to perform 3-D imaging by using sparsely sampled data. Traditional compressive sensing (CS) based 3-D imaging methods with sparse data convert the 3-D data into a long vector, and then complete the sensing and recovery steps.