Image reconstruction algorithm from compressed sensing measurements by dictionary learning

Multi-domain integrative Swin transformer network for sparse-view tomographic reconstruction

Decreasing projection views to a lower X-ray radiation dose usually leads to severe streak artifacts. To improve image quality from sparse-view data, a multi-domain integrative Swin transformer network (MIST-net) was developed and is reported in this article. First, MIST-net incorporated lavish domain features from data, residual data, image, and residual image using flexible network architectures, where a residual data and residual image sub-network was considered as a data consistency module to eliminate interpolation and reconstruction errors. Second, a trainable edge enhancement filter was incorporated to detect and protect image edges. Third, a high-quality reconstruction Swin transformer (i.e., Recformer) was designed to capture image global features. The experimental results on numerical and real cardiac clinical datasets with 48 views demonstrated that our proposed MIST-net provided better image quality with more small features and sharp edges than other competitors.

Hand gesture classification using a novel CNN-crow search algorithm

Human–computer interaction (HCI) and related technologies focus on the implementation of interactive computational systems. The studies in HCI emphasize on system use, creation of new techniques that support user activities, access to information, and ensures seamless communication. The use of artificial intelligence and deep learning-based models has been extensive across various domains yielding state-of-the-art results. In the present study, a crow search-based convolution neural networks model has been implemented in gesture recognition pertaining to the HCI domain. The hand gesture dataset used in the study is a publicly available one, downloaded from Kaggle. In this work, a one-hot encoding technique is used to convert the categorical data values to binary form. This is followed by the implementation of a crow search algorithm (CSA) for selecting optimal hyper-parameters for training of dataset using the convolution neural networks. The irrelevant parameters are eliminated from consideration, which contributes towards enhancement of accuracy in classifying the hand gestures. The model generates 100 percent training and testing accuracy that justifies the superiority of the model against traditional state-of-the-art models.

Sparse angle CT reconstruction with weighted dictionary learning algorithm based on adaptive group-sparsity regularization

OBJECTIVE

In order to solve the blurred structural details and over-smoothing effects in sparse representation dictionary learning reconstruction algorithm, this study aims to test sparse angle CT reconstruction with weighted dictionary learning algorithm based on adaptive Group-Sparsity Regularization (AGSR-SART).

METHODS

First, a new similarity measure is defined in which Covariance is introduced into Euclidean distance, Non-local image patches are adaptively divided into groups of different sizes as the basic unit of sparse representation. Second, the weight factor of the regular constraint terms is designed through the residuals represented by the dictionary, so that the algorithm takes different smoothing effects on different regions of the image during the iterative process. The sparse reconstructed image is modified according to the difference between the estimated value and the intermediate image. Last, The SBI (Split Bregman Iteration) iterative algorithm is used to solve the objective function. An abdominal image, a pelvic image and a thoracic image are employed to evaluate performance of the proposed method.

RESULTS

In terms of quantitative evaluations, experimental results show that new algorithm yields PSNR of 48.20, the maximum SSIM of 99.06% and the minimum MAE of 0.0028.

CONCLUSIONS

This study demonstrates that new algorithm can better preserve structural details in reconstructed CT images. It eliminates the effect of excessive smoothing in sparse angle reconstruction, enhances the sparseness and non-local self-similarity of the image, and thus it is superior to several existing reconstruction algorithms.

SLRL4D: Joint Restoration of Subspace Low-Rank Learning and Non-Local 4-D Transform Filtering for Hyperspectral Image

During the process of signal sampling and digital imaging, hyperspectral images (HSI) inevitably suffer from the contamination of mixed noises. The fidelity and efficiency of subsequent applications are considerably reduced along with this degradation. Recently, as a formidable implement for image processing, low-rank regularization has been widely extended to the restoration of HSI. Meanwhile, further exploration of the non-local self-similarity of low-rank images are proven useful in exploiting the spatial redundancy of HSI. Better preservation of spatial-spectral features is achieved under both low-rank and non-local regularizations. However, existing methods generally regularize the original space of HSI, the exploration of the intrinsic properties in subspace, which leads to better denoising performance, is relatively rare. To address these challenges, a joint method of subspace low-rank learning and non-local 4-d transform filtering, named SLRL4D, is put forward for HSI restoration. Technically, the original HSI is projected into a low-dimensional subspace. Then, both spectral and spatial correlations are explored simultaneously by imposing low-rank learning and non-local 4-d transform filtering on the subspace. The alternating direction method of multipliers-based algorithm is designed to solve the formulated convex signal-noise isolation problem. Finally, experiments on multiple datasets are conducted to illustrate the accuracy and efficiency of SLRL4D.

New reconstruction method for few-view grating-based phase-contrast imaging via dictionary learning

Grating-based phase-contrast is a hot topic in recent years owing to its excellent imaging contrast capability on soft tissues. Although it is compatible with conventional X-ray tubes and applicable in many fields, long scanning time, and high radiation dose obstruct its wider use in clinical and medical fields, especially for computed tomography applications. In this study, we solve this challenge by reducing the projection views and compensating the loss of reconstruction quality through dual-dictionary learning algorithm. The algorithm is implemented in two steps. First, estimated high-quality absorption images are obtained from the first dual-quality dictionary learning, which uses the correspondence between high-quality images and low-quality ones reconstructed from highly under-sampled data. Then, the second absorption-phase dual-modality dictionary learning is adopted to yield both estimated phase and absorption images, resulting in complementary information for both modality images. Afterwards the absorption and phase images are gradually improved in iterative reconstructions. By using SSIM RMSE measurements and visual assessment for enlarged regions of interest, our proposed method can improve the resolution of these two modality images and recover smaller structures, as compared to conventional methods.

Optshrink LR + S: accelerated fMRI reconstruction using non-convex optimal singular value shrinkage

This paper presents a new accelerated fMRI reconstruction method, namely, OptShrink LR + S method that reconstructs undersampled fMRI data using a linear combination of low-rank and sparse components. The low-rank component has been estimated using non-convex optimal singular value shrinkage algorithm, while the sparse component has been estimated using convex l¹ minimization. The performance of the proposed method is compared with the existing state-of-the-art algorithms on real fMRI dataset. The proposed OptShrink LR + S method yields good qualitative and quantitative results.