Sharif Digital Repository

This study proposes a new method for the detection of a weak scatterer among strong scatterers using prior-information ultrasound (US) imaging. A perfect application of this approach is in vivo cell detection in the bloodstream, where red blood cells (RBCs) serve as identifiable strong scatterers. In vivo cell detection can help diagnose cancer at its earliest stages, increasing the chances of survival for patients. This work combines time-domain US with frequency-domain compressive US imaging to detect a 20-μ MCF-7 circulating tumor cell (CTC) among a number of RBCs within a simulated venule inside the mouth. The 2D image reconstructed from the time-domain US is employed to simulate the... 

By generalising dictionary learning (DL) algorithms to multidimensional (MD) mode and using them in applications where signals are inherently multidimensional, such as in three-dimensional (3D) inverse synthetic aperture radar (ISAR) imaging, it is possible to achieve much higher speed and less computational complexity. In this study, the formulation of the multidimensional dictionary learning (MDDL) problem is expressed and two algorithms are proposed to solve it. The first one is based on the method of optimum directions (MOD) algorithm for 1D dictionary learning (1DDL), which uses alternating minimisation and gradient projection approach. As the MDDL problem is non-convex, the second... 

This communication addresses the focusing problem in the millimeter-wave imaging systems. We categorize the focusing problem into the frequency focusing for wideband systems and the range focusing for narrowband systems. In an out-of-focus wideband system, a shifted shadow of the object is present in the reconstruction, whereas for a range out of the focused system, the recovered images are blurred. To overcome these issues, first, we theoretically show that the defocusing variations for both categories are bounded. Then, we present a universal formulation for focusing problem, which covers both wideband and narrowband systems. As the true focused images are sharp at the boundaries of the... 

Few-view or sparse-view computed tomography has been recently introduced as a great potential to speed up data acquisition and alleviate the amount of patient radiation dose. This study aims to present a method for high-quality ultra-fast image reconstruction from sparsely sampled projections to overcome problems of previous methods, missing and blurring tissue boundaries, low-contrast objects, variations in shape and texture between the images of different individuals, and their outcomes. To this end, a new deep learning (DL) framework based on convolution neural network (CNN) models is proposed to solve the problem of CT reconstruction under sparsely sampled data, named the multi-receptive... 

Circular photoacoustic tomography (C-PAT) arrangements are widely used in PAT systems. Many algorithms are proposed for PAT to reconstruct images such as delay and sum (DAS), universal back-projection (UBP), etc., all suffering from their own disadvantages. In this paper, to overcome these limitations, we proposed a fast uniform adapted delay and sum (ADAS) and filtered adapted delay and sum (F-ADAS) for detectors with finite and infinite bandwidth, respectively. Moreover, the edge uniformity index (EUI) metric was proposed for quantitative evaluation. Two cases 1) infinite bandwidth and 25 dB SNR level and 2) 2.25 MHz, 80% bandwidth with the same SNR level were considered for numerical... 

Sparse-view computed tomography (CT) is recently proposed as a promising method to speed up data acquisition and alleviate the issue of CT high dose delivery to the patients. However, traditional reconstruction algorithms are time-consuming and suffer from image degradation when faced with sparse-view data. To address this problem, we propose a new framework based on deep learning (DL) that can quickly produce high-quality CT images from sparsely sampled projections and is able for clinical use. Our DL-based proposed model is based on the convolution, and residual neural networks in a parallel manner, named the parallel residual neural network (PARS-Net). Besides, our proposed PARS-Net model... 

Data science as a flourishing interdisciplinary domain of computer and mathematical sciences is playing an important role in guiding the porous material research streams. In the present narrative review, we have examined recent trends and issues in data-driven methods used in the image-based porous material research studies relevant to water resources researchers and scientists. Initially, the recent trends in porous material data-related issues have been investigated through search engine queries in terms of data source, data storage hub, programing languages, and software packages. Subsequent to a diligent analysis of the existing trends, a review of the common concepts of porous material... 

A state-of-the-art algorithm for perspective projection reconstruction of non-rigid surfaces from single-view and realistic videos is proposed. It overcomes the limitations arising from the usage of orthographic camera model and also the complexity and non-linearity issues of perspective projection equation. Unlike traditional non-rigid structure-from-motion (NRSfM) methods, which have been studied only on synthetic datasets and controlled lab environments that require some prior constraints (such as manually segmented objects, limited rotations and occlusions, and full-length trajectories); the proposed method can be used in realistic video sequences. In addition, contrary to previous... 

A coupled statistical and conditional generative adversarial neural network is used for 3D reconstruction of both homogeneous and heterogeneous porous media from a single two-dimensional image. A statistical approach feeds the deep network with conditional data, and then the reconstruction is trained on a deep generative network. The conditional nature of the generative model helps in network stability and convergence which has been optimized through a gradient-descent-based optimization method. Moreover, this coupled approach allows the reconstruction of heterogeneous samples, a critical and serious challenge in conventional reconstruction methods. The main contribution of this work is to... 

Recent years have seen an increasing trend in developing 3D action recognition methods. However, despite the advances, existing models still suffer from some major drawbacks including the lack of any provision for recognizing action sequences with some missing frames. This significantly hampers the applicability of these methods for online scenarios, where only an initial part of sequences are already provided. In this paper, we introduce a novel sequence-To-sequence representation-based algorithm in which a query sample is characterized using a collaborative frame representation of all the training sequences. This way, an optimal classifier is tailored for the existing frames of each query... 

A novel super-resolution volumetric photoacoustic microscopy, based on the theory of structured-illumination, is proposed in this paper. The structured-illumination will be introduced in order to surpass the diffraction limit in a photoacoustic microscopy (PAM) structure. Through optical excitation of the targeted object with a sinusoidal spatial fringe pattern, the object's frequency spectrum is forced to shift in the spatial frequency domain. The shifting in the desired direction leads to the passage of the high-frequency contents of the object through the passband of the acoustic diffraction frequency response. Finally, combining the low-frequency image with the high-frequency parts in... 

Recently, deep convolutional neural networks (DCNN) that leverage the adversarial training framework for image restoration and enhancement have significantly improved the processed images' sharpness. Surprisingly, although these DCNNs produced crispier images than other methods visually, they may get a lower quality score when popular measures are employed for evaluating them. Therefore it is necessary to develop a quantitative metric to reflect their performances, which is well-aligned with the perceived quality of an image. Famous quantitative metrics such as Peak signal-to-noise ratio (PSNR), The structural similarity index measure (SSIM), and Perceptual Index (PI) are not well-correlated... 

This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021. As a new type of image processing technology, perceptual image processing algorithms based on Generative Adversarial Networks (GAN) have produced images with more realistic textures. These output images have completely different characteristics from traditional distortions, thus pose a new challenge for IQA methods to evaluate their visual quality. In comparison with previous IQA challenges, the training and testing datasets in this challenge include the outputs of perceptual image... 

In this paper, the relationship between the position of ultrasound transducers from the photoacoustic source and the reconstructed image is investigated. Our studies have shown that the distance of the transducer and its location from the photoacoustic source specifically affects and is closely related to the quality of the reconstructed image of the source. Also, we introduce a concept called blind angle for photoacoustic computed tomography (PACT) that have planar or circular limited-view geometry. Complete and accurate equations of this relationship are presented in this paper for all different 2D photoacoustic geometries. The main source of these equations is the spherically of the... 

Background: The issue of medial image resolution enhancement is one of the most important topics for medical imaging that helps improve the performance of many post-processing aspects like classification and segmentation towards medical diagnosis. Objective: Our aim in this paper is to evaluate different types of pixel selection models in terms of pixel originality in medical image reconstruction problems. A previous investigation showed that selecting far original pixels has highly better performance than using near unoriginal/estimated pixels while magnifying some benchmarks in digital image processing. Material and Methods: In our technical study, we apply two classical inter-polators,... 

Sparse representation can be extended to high dimensions and can be used in many applications, including three-dimensional (3D) Inverse synthetic aperture radar (ISAR) imaging. In this study, the high-dimensional sparse representation problem and a recovery method called high-dimensional smoothed least zero-norm (HDSL0) are formulated. In this method, the theory and computation of tensors and approximating L0 norm using Gaussian functions are used for sparse recovery of high-dimensional data. To enhance the performance of HDSL0, modified regularised high-dimensional SL0 (MRe-HDSL0) algorithm, which benefits from the regularised form of SL0 and an additional hard thresholding step, is... 

Computed tomography (CT) simulators are versatile tools for scanning protocol evaluation, optimization of geometrical design parameters, assessment of image reconstruction algorithms, and evaluation of the impact of future innovations attempting to improve the performance of CT scanners. Computational human phantoms (CHPs) play a key role in simulators for the radiation dosimetry and assessment of image quality tasks in the medical x-ray systems. Since the construction of patient-specific CHPs can be both difficult and time-consuming, nominal standard/reference CHPs have been established, yielding significant discrepancies in the special design and optimization demands of patient dose and... 

With the dominance of digital imaging systems, we are often dealing with discrete-domain samples of an analog image. Due to physical limitations, all imaging devices apply a blurring kernel on the input image before taking samples to form the output pixels. In this paper, we focus on the reconstruction of binary shape images from few blurred samples. This problem has applications in medical imaging, shape processing, and image segmentation. Our method relies on representing the analog shape image in a discrete grid much finer than the sampling grid. We formulate the problem as the recovery of a rank $r$ matrix that is formed by a Hankel structure on the pixels. We further propose efficient... 

A state-of-the-art algorithm for perspective projection reconstruction of non-rigid surfaces from single-view and realistic videos is proposed. It overcomes the limitations arising from the usage of orthographic camera model and also the complexity and non-linearity issues of perspective projection equation. Unlike traditional non-rigid structure-from-motion (NRSfM) methods, which have been studied only on synthetic datasets and controlled lab environments that require some prior constraints (such as manually segmented objects, limited rotations and occlusions, and full-length trajectories); the proposed method can be used in realistic video sequences. In addition, contrary to previous... 

Recent years have seen an increasing trend in developing 3D action recognition methods. However, despite the advances, existing models still suffer from some major drawbacks including the lack of any provision for recognizing action sequences with some missing frames. This significantly hampers the applicability of these methods for online scenarios, where only an initial part of sequences are already provided. In this paper, we introduce a novel sequence-to-sequence representation-based algorithm in which a query sample is characterized using a collaborative frame representation of all the training sequences. This way, an optimal classifier is tailored for the existing frames of each query...