Javad Alirezaie

Toronto Metropolitan University · Electrical Computer and Biomedical Engineering

With the increasing concern regarding the radiation exposure of patients undergoing computed tomography (CT) scans, researchers have been using deep learning techniques to improve the quality of denoised low-dose CT (LDCT) images. In this paper, a cascaded dilated residual network (ResNet) with integrated attention modules, specifically spatial- an...

Deep learning techniques have emerged in de-noising low-dose computed tomography (CT) images to avoid the potential health risks of high ionizing radiation dose on patients. Although these post-processing methods display high quality denoised images, the denoising performance still has the potential to improve. The primary purpose of this work was...

Automatic mandible segmentation of CT images is an essential step to achieve an accurate preoperative prediction of an intended target in three-dimensional (3D) virtual surgical planning. Segmentation of the mandible is a challenging task due to the complexity of the mandible structure, imaging artifacts, and metal implants or dental filling materi...

X-ray computed tomography (CT) is a non-invasive medical diagnostic tool that has raised public concerns due to the associated health risks of radiation dose to patients. Reducing the radiation dose leads to noise artifacts, making the low-dose CT images unreliable for diagnosis. Hence, low-dose CT (LDCT) image reconstruction techniques have offere...

The capability of Hyperspectral Imaging (HSI) in rapidly acquiring abundant reflectance data in a non-invasive manner, makes it an ideal tool for obtaining diagnostic information about tissue pathology. Identifying wavelengths that provide the most discriminatory clues for specific pathologies will greatly assist in understanding their underlying b...

CT machines can be tuned in order to reduce the radiation dose used for imaging, yet reducing the radiation dose results in noisy images which are not suitable in clinical practice. In order for low dose CT to be used effectively in practice this issue must be addressed. Generative Adversarial Networks (GAN) have been used widely in computer vision...

Glioma is a highly invasive type of brain tumor with an irregular morphology and blurred infiltrative borders that may affect different parts of the brain. Therefore, it is a challenging task to identify the exact boundaries of the tumor in an MR image. In recent years, deep learning-based Convolutional Neural Networks (CNNs) have gained popularity...

Image denoising of Low-dose computed tomography (LDCT) images has continues to receive attention in the research community due to ongoing concerns about high-dose radiation exposure of patients for diagnosis. The use of low radiation CT image, however, could lead to inaccurate diagnosis due to the presence of noise. Deep learning techniques are bei...

Glioma is a highly invasive type of brain tumor that appears in different parts of brain with various sizes, shapes, and blurred borders. Therefore, it is a challenging task to identify the exact boundaries of the tumor in an MR image. In recent years, deep learning based CNNs methods have gained popularity in the field of image processing and have...

Low Dose CT Denoising research aims to reduce the risks of radiation exposure to patients. Recently researchers have used deep learning to denoise low dose CT images with promising results. However, approaches that use mean-squared-error (MSE) tend to over smooth the image resulting in loss of fine structural details in low contrast regions of the...

This paper proposes a new numerical framework to simulate ultrasound wave propagation in 3D viscoelastic heterogeneous media based on the elastodynamic wave equation including a 3D second-order time-domain perfectly matched layer formulation. A finite difference discretization of this formulation is presented, along with a stability analysis. The r...

Low-dose CT denoising is a challenging task that has been studied by many researchers. Some studies have used deep neural networks to improve the quality of low-dose CT images and achieved fruitful results. In this paper, we propose a deep neural network that uses dilated convolutions with different dilation rates instead of standard convolution he...

Low-dose CT imaging is a valid approach to reduce patients' exposure to X-ray radiation. However, reducing X-ray current increases noise and artifacts in the reconstructed CT images. Deep neural networks have been successfully employed to remove noise from low-dose CT images. This study proposes two novel techniques to boost the performance of a ne...

In this work, a super-resolution method is proposed for indoor scenes captured by low-resolution thermal cameras. The proposed method is called Edge Focused Thermal Super-resolution (EFTS) which contains an edge extraction module enforcing the neural networks to focus on the edge of images. Utilizing edge information, our model, based on residual d...

Low-dose CT denoising is a challenging task that has been studied by many researchers. Some studies have used deep neural networks to improve the quality of low-dose CT images and achieved fruitful results. In this paper, we propose a deep neural network that uses dilated convolutions with different dilation rates instead of standard convolution he...

The work aims to develop a new image-processing method to improve the guidance of transesophageal high intensity focused ultrasound (HIFU) atrial fibrillation therapy. Our proposal is a novel registration approach that aligns intraoperative 2D ultrasound with preoperative 3D-CT information. This approach takes advantage of the anatomical constraint...

Notwithstanding the widespread use of image guided neurosurgery systems in recent years, the accuracy of these systems is strongly limited by the intra-operative deformation of the brain tissue, the so-called brain shift. Intra-operative ultrasound (iUS) imaging as an effective solution to compensate complex brain shift phenomena update patients co...

Low-dose Computed Tomography (CT) is considered a solution for reducing the risk of X-ray radiation; however, lowering the X-ray current results in a degraded reconstructed image. To improve the quality of the image, different noise removal techniques have been proposed. Con- volutional neural networks also have shown promising results in denoising...

An essential objective in medical low-dose Computed Tomography (CT) imaging is how best to preserve the quality of the image. While, reducing the X-ray radiation dose is desired, in general, the image quality lowers by reducing the dose. Therefore, improving image quality is remarkably crucial for diagnostic purposes. A novel method to denoise low-...

In this work, a robust nonrigid motion compensation approach, is applied to the compressed sensing reconstruction of dynamic cardiac cine MRI sequences. Respiratory and cardiac motion separation coupled with a registration algorithm is used to provide accurate reconstruction of dynamic cardiac images. The proposed scheme employs a variable splittin...

Background and objective: To diagnose infertility in men, semen analysis is conducted in which sperm morphology is one of the factors that are evaluated. Since manual assessment of sperm morphology is time-consuming and subjective, automatic classification methods are being developed. Automatic classification of sperm heads is a complicated task d...

One of the critical topics in medical low-dose Computed Tomography (CT) imaging is how best to maintain image quality. As the quality of images decreases with lowering the X-ray radiation dose, improving image quality is extremely important and challenging. We have proposed a novel approach to denoise low-dose CT images. Our algorithm learns direct...

Objectives: In dynamic cardiac magnetic resonance imaging (MRI), the spatiotemporal resolution is often limited by low imaging speed. Compressed sensing (CS) theory can be applied to improve imaging speed and spatiotemporal resolution. The combination of compressed sensing and low-rank matrix completion represents an attractive means to further in...

This paper presents a method for modeling and simulation of shear wave generation from a nonlinear Acoustic Radiation Force Impulse (ARFI) that is considered as a distributed force applied at the focal region of a HIFU transducer radiating in nonlinear regime. The shear wave propagation is simulated by solving the Navier’s equation from the distrib...

Shear Wave Elastography (SWE) is a quantitative ultrasound-based imaging modality for distinguishing normal and abnormal tissue types by estimating the local viscoelastic properties of the tissue. These properties have been estimated in many studies by propagating ultrasound shear wave within the tissue and estimating parameters such as speed of wa...

Intra-operative ultrasound as an imaging based method has been recognized as an effective solution to compensate non rigid brain shift problem in recent years. Measuring brain shift requires registration of the pre-operative MRI images with the intra-operative ultrasound images which is a challenging task. In this study a novel hybrid method based...

In dynamic cardiac cine Magnetic Resonance Imaging (MRI), the spatiotemporal resolution is limited by the low imaging speed. Compressed sensing (CS) theory has been applied to improve the imaging speed and thus the spatiotemporal resolution. The purpose of this paper is to improve CS reconstruction of under sampled data by exploiting spatiotemporal...

Spinal fusion permanently connects two or more vertebrae in spine to improve stability, correct a deformity or reduce pain by immobilizing the vertebrae through pedicle screw fixation. Pedicle screws should be inserted very carefully to prevent possible irrecoverable damages to the spinal cord. Surgeons use CT/fluoroscopic images to find how to ins...

Combination of various intraoperative imaging modalities potentially can reduce error of brain shift estimation during neurosurgical operations. In the present work, a new combination of surface imaging and Doppler US images is proposed to calculate the displacements of cortical surface and deformation of internal vessels in order to estimate the t...

Image denoising and signal enhancement are the most challenging issues in low dose computed tomography (CT) imaging. Sparse representational methods have shown initial promise for these applications. In this work we present a wavelet based sparse representation denoising technique utilizing dictionary learning and clustering. By using wavelets we e...

With the increasing utilization of X-ray Computed Tomography (CT) in medical diagnosis, obtaining higher quality image with lower exposure to radiation has become a highly challenging task in image processing. In this paper, a novel sparse fusion algorithm is proposed to address the problem of lower Signal to Noise Ratio (SNR) in low dose CT images...

In this work, a new shape based method to improve the accuracy of Brain Ultrasound-MRI image registration is proposed. The method is based on modified Shape Context (SC) descriptor in combination with CPD algorithm. An extensive experiment was carried out to evaluate the robustness of this method against different initialization conditions. As the...

In recent years intra-operative ultrasound images have been used for many procedures in neurosurgery. The registration of intra-operative ultrasound images with preoperative magnetic resonance images is still a challenging problem. In this study a new hybrid method based on residual complexity is proposed for this problem. A new two stages method b...

This paper deals with the adaptation, the tuning and the evaluation of the multiple organs Optimal Surface Detection (OSD) algorithm for the T2 MRI prostate segmentation. This algorithm is initialized by first surface approximations of the prostate (obtained after a model adjustment), the bladder (obtained automatically) and the rectum (interactive...

Purpose: Compensation for brain shift is often necessary for image-guided neurosurgery, requiring registration of intra-operative ultrasound (US) images with preoperative magnetic resonance images (MRI). A new image similarity measure based on residual complexity (RC) to overcome challenges of registration of intra-operative US and preoperative MR...

Dictionary learning for sparse representation has recently attracted attention among the signal processing society in a variety of applications such as denoising, classification, and compression. The number of elements in a learned dictionary is crucial since it governs specificity and optimality of sparse representation. Sparsity level, number of...

This package is written and developped by Mahdi Marsousi, which is the implementation of the "An Adaptive Approach to Learn Overcomplete Dictionaries With Efficient Numbers of Elements", also called DLENE. This package only can be used for academic purposes, and its citation is required. For more information, please contact marsousi@comm.utoronto.c...

Compressed sensing (CS) is a data-reduction technique that has been applied to speed up the acquisition in MRI. In this work, the feasibility of the CS framework for accelerated dynamic MRI is assessed. The fundamental condition of sparsity required in the CS framework is exploited by applying a wavelet transform and a Fourier transform along spati...

In this paper, we present a novel routing algorithm in order to avoid deadlock and packet dropping. In our proposed algorithm the network-on-chip (NoC) is capable of tolerating faults in presence of control faults in combinational parts of routers. In addition, by modifying the functionality of the router, the router is enabled to test its own, as...

Generating synthetic physiological signals using information extracted from real world physiological signals plays an important role in the field of medical device development and education. Most of the existing approaches are limited in the sense that they either focus on a particular physiological signal or lack flexibility in generating signals...

A new multi-stage approach based on component extraction is proposed to more efficiently address the sparse representation problem. In each stage a pre-set number of coefficients are chosen for reconstructing each signal component. A global search is performed to extract a lower dimensional sub-dictionary consisting of a sorted set of candidate ato...

In this paper we present a novel method for stimulation of the electrodes in cochlear implants. The method is based on a wavelet packet decomposition strategy (db4, for 7 levels) which generates a series of channels with bandwidths exactly the same as Nucleus device. Finally, Performance of the recommended mapping is evaluated by estimating the cor...

In this paper, a new fully automated model-based approach for segmenting the prostate boundaries in transrectal ultrasound images is proposed. In the preprocessing step, the position of the initial model is automatically estimated using representative patterns. The Expectation Maximization algorithm (EM) and Markov Random Field (MRF) theory are uti...

Segmentation of prostate boundaries in transrectal ultrasound (TRUS) images plays a great role in early detection of prostate cancer. Due to the low signal to noise ratio and existence of the speckle noise in TRUS images, prostate image segmentation has proven to be an extremely difficult task. This paper introduces a new fully automatic model-base...

In this paper, A novel classification approach based on sparse representation framework is proposed. The method finds the minimum Euclidian distance between an input patch (pattern) and atoms (templates) of a learnt-base dictionary for different classes to perform the classification task. A mathematical approach is developed to map the sparse repre...

Reverse engineering of gene regulatory networks (GRNs) is the process of estimating genetic interactions of a cellular system from gene expression data. In this paper, we propose a novel hybrid systematic algorithm based on neurofuzzy network for recon-structing GRNs from observational gene expression data when only a medium-small number of measure...

In this work, we introduce a new approach for medical image denoising. An innovative method is proposed to extend the concept of low-pass filtering to the sparse representation framework. A weight matrix is applied to the definition of the sparse coding optimization problem intended to reduce coefficients corresponding to atoms with higher frequenc...

We present a method for coding speech signals for the simulation of a cochlear implant. The method is based on a wavelet packet decomposition strategy. We used wavelet packet db4 for 7 levels, generated a series of channels with bandwidths exactly the same as nucleus device, and applied an input stimulus to each channel. The processed signal was th...

In this paper, the problem of reducing noise from low-dose Computed Tomography (CT) is investigated. The process is composed of: sparse coding, dictionary update and denoising; that is a time consuming process. Hence, despite the promising results reported in literature, it has not attracted much attention in medical applications. In an attempt to...

Spatially-varying intensity inhomogeneity is a severe artifact, which occurs in intra-operative MR images of the brain. This artifact causes implications in the accuracy of image guided navigation systems being performed during neurosurgery procedures. Therefore, it is highly desirable to correct intensity inhomogeneity along with registration proc...

Segmenting lateral ventricle in medical images plays an important role in medical diagnosis. The volume of lateral ventricle increases with age and it is an important indicator of Alzheimer's, schizophrenia, and depressive disorders. In this article a new approach based on sparse representation and dictionary learning as a pre process of the existi...

In order to have a better understanding of function of the cochlear implant, we first need to understand the cochlea's response at different input frequencies. As a result, in this study we chose a mechanical model of the traveling wave across the basilar membrane. The model was modified to incorporate the effect of OHCs (active cochlea) to be capa...

With the increase in the number of identified rare diseases and the intricacy involved in diagnosis, as exemplified by metabolic brain diseases, the need for computerized diagnostic systems is inevitable. We propose a pilot computer-assisted medical decision support system (mCAD) which tries to identify and further categorize these diseases, utiliz...

In this paper, a fully automated multi-step approach for segmenting the Left Ventricle (LV) chamber in echocardiography images is proposed. A preprocessing step is applied to remove the dark background and find the seed point inside the LV chamber, eliminating the specialist intervention for identifying the seed point to initialize the segmentation...

In this article, an automatic method for detection of all chambers in apical two- and four-chamber views is proposed. The method is based on four evolving ellipses with their sizes and alignments (centre point) gradually changing through iterations until they reach to the point that approximates the chamber boundaries. The interaction between the i...

The diffusion-weighted imaging (DWI) technique can be utilized to investigate a variety of diseases. We propose an automated pilot system, which assists in the diagnosis of metabolic brain diseases, utilizing the DWI. In this study, DWI images are preprocessed and exponential apparent diffusion coefficient (eADC) images are produced. The eADC image...

from only given. Cloning or copy-move is a special type of forgery that tries to hide the regions of the image by a block that is copied from the same image. In this paper we introduce a new texturebased method to detect such forgeries in digital images. In the proposed approach, at first the image is divided into some overlapping blocks and then w...

Direct extension of (2D) matrix-based linear subspace algorithms to kernel-induced feature space is computationally intractable and also fails to exploit local characteristics of input data. In this letter, we develop a 2D generalized framework which integrates the concept of kernel machines with 2D principal component analysis (PCA) and 2D linear...

In this paper, a fully automated method for segmenting Left Ventricle (LV) in echocardiography images is proposed. A new method named active ellipse model is developed to automatically find the best ellipse inside the LV chamber without intervention of any specialist. A modified B-Spline Snake algorithm is used to segment the LV chamber in which th...

Nervous system conveys information by electrical signals called 'spikes', therefore, spikes detection and sorting are challenging topics in the neural data processing. The principal component analysis (PCA) is a convenient tool for clustering spikes; however it has some disadvantages for closely shaped and overlapped spikes. For such the cases, an...