Dose Reduction Via Development of a Novel Image Reconstruction Method for Few-View Computed Tomography

, Ph.D. Dissertation Sharif University of Technology Khodajou Chokami, Hamid Reza (Author) ; Hosseini, Abolfazl (Supervisor) ; Ay, Mohammad Reza (Supervisor)

Abstract

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 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 two new frameworks based on deep learning (DL) that can quickly produce high-quality CT images from sparsely sampled projections and is able for clinical use. Our first 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...

Evaluation of Effective Factors on The Mammographic Images Utilizing Monte Carlo Simulation

, M.Sc. Thesis Sharif University of Technology Khodajou Chokami, Hamid Reza (Author) ; Sohrabpour, Mostafa (Supervisor)

Abstract

The Scattered radiation is the principal factor affecting the quality of the digital and screen-film mammography images. The contrast improvement factor and bucky factor which are also referred to as the benefit and risk of the anti-scattered grid cannot be properly assessed without a detailed knowledge of the scattered radiation. In this work the scatter to primary ratio has been calculated and an anti-scatter grid has been designed based on the reduction of the scattered radiation to reduce the patient dose to a minimum level and to improve the image quality simultaneously.The MCNPX 2.6.0 Monte Carlo code has been used to improve the geometry of the anti-scatter grid to both reduce the...

Design of linear anti-scatter grid geometry with optimum performance for screen-film and digital mammography systems

, Article Physics in Medicine and Biology ; Volume 60, Issue 15 , July , 2015 , Pages 5753-5765 ; 00319155 (ISSN) Khodajou Chokami, H ; Sohrabpour, M ; Sharif University of Technology

Institute of Physics Publishing 2015

Abstract

A detailed 3D Monte Carlo simulation of the grid geometrical parameters in screen-film mammography (SFM) and digital mammography (DM) systems has been performed. A combination of IEC 60627:2013 international standard conditions and other more clinically relevant parameters were used for this simulation. Accuracy of our results has been benchmarked with previously published data and good agreement has been obtained. Calculations in a wide range of linear anti-scatter grid geometries have been carried out. The evaluated parameters for the SFM system were the Bucky factor (BF) and contrast improvement factor (CIF) and for the DM system it was signal differenceto- noise ratio improvement factor...

MCNP-FBSM: Development of MCNP/MCNPX Source Model for Simulation of Multi-Slice Fan-Beam X-Ray CT Scanners

, Article 2019 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2019, 26 June 2019 through 28 June 2019 ; 2019 ; 9781538684276 (ISBN) Khodajou Chokami, H ; Hosseini, S. A ; Reza Ay, M ; Zaidi, H ; Sharif University of Technology

Institute of Electrical and Electronics Engineers Inc 2019

Abstract

Computed tomography (CT) is one of the most valuable diagnostic imaging tools in the clinic and is widely used worldwide. One of the main motivations driving research and development in CT is to achieve better image quality while keeping the radiation dose to the patient as low as possible. In this regard, computer simulations play a key role in the optimization of CT design. In this work, a fan-beam source model (FBSM) for the simulation of multi-slice fan-beam CT scanners using the MCNP Monte Carlo code, has been developed and implemented. The use of this model removes the need for using the collimator in the system configuration and thus to overcome the perennial problem of particle...

A novel method for measuring the MTF of CT scanners: A phantom study

, Article 2019 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2019, 26 June 2019 through 28 June 2019 ; 2019 ; 9781538684276 (ISBN) Khodajou Chokami, H ; Hosseini, S. A ; Reza Ay, M ; Safarzadehamiri, A ; Ghafarian, P ; Zaidi, H ; Sharif University of Technology

Institute of Electrical and Electronics Engineers Inc 2019

Abstract

The modulation transfer function (MTF) is well known as a crucial parameter in quality assurance of computed tomography (CT) scanners, which provides detailed information of both contrast and resolution of CT images. Different methods have been introduced and developed to calculate the MTF of CT scanners. However, a robust methodology which accurately estimates the MTF of CT scanners under the use of every range of object electron density and tube current-time product (mAs) has not been reported so far. To this aim, a new wavelet-based circular edge method for MTF measurement has been presented in this work. Owning to the edge spread function (ESF) susceptibility to noise, the approach was...

PARS-NET: A novel deep learning framework using parallel residual conventional neural networks for sparse-view CT reconstruction

, Article Journal of Instrumentation ; Volume 17, Issue 2 , 2022 ; 17480221 (ISSN) Khodajou Chokami, H ; Hosseini, S. A ; Ay, M. R ; Sharif University of Technology

IOP Publishing Ltd 2022

Abstract

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...

A deep learning method for high-quality ultra-fast CT image reconstruction from sparsely sampled projections

, Article Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment ; Volume 1029 , 2022 ; 01689002 (ISSN) Khodajou Chokami, H ; Hosseini, S. A ; Ay, M. R ; Sharif University of Technology

Elsevier B.V 2022

Abstract

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...

A hybrid deep model for automatic arrhythmia classification based on LSTM recurrent networks

, Article 15th IEEE International Symposium on Medical Measurements and Applications, MeMeA 2020, 1 June 2020 through 3 June 2020 ; 2020 Bitarafan, A ; Amini, A ; Baghshah, M. S ; Khodajou Chokami, H ; Sharif University of Technology

Institute of Electrical and Electronics Engineers Inc 2020

Abstract

Electrocardiogram (ECG) recording of electrical heart activities has a vital diagnostic role in heart diseases. We propose to tackle the problem of arrhythmia detection from ECG signals totally by a deep model that does not need any hand-designed feature or heuristic segmentation (e.g., ad-hoc R-peak detection). In this work, we first segment ECG signals by detecting R-peaks automatically via a convolutional network, including dilated convolutions and residual connections. Next, all beats are aligned around their R-peaks as the most informative section of the heartbeat in detecting arrhythmia. After that, a deep learning model, including both dilated convolution layers and a Long-Short Term...

Identification of the Set of Single Nucleotide Variants in Genome Responsible for the Differentiation of Expression of Genes

, M.Sc. Thesis Sharif University of Technology Khatami, Mahshid (Author) ; Rabiee, Hamid Reza (Supervisor) ; Beigi, Hamid (Supervisor)

Abstract

Single nucleotide polymorphs, There are changes caused by a mutation in a nucleotide in the Dena sequence. Mononucleotide polymorphisms are the most common type of genetic variation. Some of these changes have little or no effect on cells, while others cause significant changes in the expression of cell genes that can lead to disease or resistance to certain diseases. Because of the importance of these changes and their effect on cell function, the relationships between these changes are also important. Over the past decade, thousands of single disease-related mononucleotide polymorphisms have been identified in genome-related studies. Studies in this field have shown that the expression of...

Synthesis & Characterization of Au-HKUST-1 Nanocomposite and Evaluation of Plasmonic Properties of Gold Nanoparticles in this Nanocomposite

, M.Sc. Thesis Sharif University of Technology Moazzeni, Hamid Reza (Author) ; Madaah Hosseini, Hamid Reza (Supervisor)

Abstract

In the past few years, many research works on the controllable integration of metal nanoparticles and metal-organic frameworks were done, since the obtained composite material shows a synergism effect in catalysis and photocatalysis, drug delivery applications, gas, and energy storage, as well as sensing. For the first time, in this study, we employed template-assisted growth to synthesize Au-HKUST-1 Nanocomposite. XRD analysis entirely confirms that employing this strategy in synthesizing Au-HKUST-1 was wholly successful, and the plasmonic properties of this nanostructure were studied via UV-visible spectroscopy. In the course of synthesis, gold nanoparticles with 70nm diameter were...

Live Layered Video Streaming over Multichannel P2P Networks

, M.Sc. Thesis Sharif University of Technology Ghalebi, Elahe (Author) ; Rabiee, Hamid Reza (Supervisor)

Abstract

Nowadays, video streaming over peer-to-peer networks has become an interesting field to deliver video in large scale networks. As multi-channel live video streaming networks increase,distributing video with high quality among channels faces many challenges. The most significant challenges cause from frequent channel churns, unbalanced channel resources, network heterogeneity and diversity of users’ bandwidths. They include: nodes’ unstability, low users participations, large startup and playback delays, low video quality received by users and lack of resources in unpopular channels.In order to solve the above problems, we have proposed several solutions such as: 1- using distribution groups...

Local Community Detection in Social

, M.Sc. Thesis Sharif University of Technology Rajabi, Arezoo (Author) ; Rabiee, Hamid Reza (Supervisor)

Abstract

The fast growth of social networks and their wide range of applications have made the anal-ysis of them an interesting field of research. The growth of concern in modeling large social networksand investigation of their structural features leads studies towards community detec-tion in such networks. In recent years, a great amount of effort has been done for introducing community detection algorithms, many of which are based on optimization of a global cri-terion which needs network’s topology. However, because of big size of most of the social networks , accessing their global information tends to be impossible. Hence, local commu-nity detection algorithms have been introduced. In this...

Improving Graph Construction for Semi-supervised Learning in Computer Vision Applications

, M.Sc. Thesis Sharif University of Technology Mahdieh, Mostafa (Author) ; Rabiee, Hamid Reza (Supervisor)

Abstract

Semi-supervised Learning (SSL) is an extremely useful approach in many applications where unlabeled data can be easily obtained. Graph based methods are among the most studied branches in SSL. Since neighborhood graph is a key component in these methods, we focus on methods of graph construction in this project. Graph construction methods based on Euclidean distance have the common problem of creating shortcut edges. Shortcut edges refer to the edges which connect two nearby points that are far apart on the manifold. Specifically, we show both in theory and practice that using geodesic distance for selecting and weighting edges results in more appropriate neighborhood graphs. We propose an...

Investigating Conformal Vector Field on Riemannian Manifolds

, M.Sc. Thesis Sharif University of Technology Hessam, Hamed (Author) ; Fanai, Hamid Reza (Supervisor)

Abstract

At first the killing vector fields will be investigated. Conditions are introduced for the hypersurface of a Riemannian manifold with a killing vector field to be equipped with the same killing vector field. Then 2-killing vector field is studied and its relation with killing vector fields and monotone vector fields is presented. After that conformal vector fields are discussed and conditions are introduced in order that the Riemannian manifold equipped with a conformal vector field, isisometric to n-dimensional sphere with constant curvature. Finally we will present the conditions which conformal vector field is a 2-killing vector field. Then we will present the results in which the...

Network Topology Inference from Incomplete Data

, M.Sc. Thesis Sharif University of Technology Siyari, Payam (Author) ; Rabiee, Hamid Reza (Supervisor)

Abstract

During the last decade, there have been a great number of researches on complex networks.Data aggregation is the first step in the analysis of these networks. However, due to the large scale of them, almost never is there complete information about a network’s different aspects. Therefore, analysis of a complex network is usually done based on the incomplete data. Al-though a good sampling approach in a way that the achieved sample is a good representative of the whole network has its own challenges, analysis of incomplete data causes a significant alternation in the estimation results. Consequently, one of the first problems emerging after sampling is the possibility of predicting the...

Continuous Time Modeling of Marked Events

, Ph.D. Dissertation Sharif University of Technology Hosseini, Abbas (Author) ; Rabiee, Hamid Reza (Supervisor)

Abstract

A great deal of information are continuously generated by users in different contexts such as social networks and online service providers in terms of temporal marked events. These events indicate that what happened to who by when and where.Modeling such events and predicting future ones has interesting applications in different domains such as item recommendation in online service providers and trending topic prediction in online social networks. However, complex longitudinal dependencies among such events makes the prediction task challenging. Moreover, nonstationarity of generative model of events and large size of events, makes the modeling and learning the models challenging.In this...

Analysis and Modeling of User Behavior over Social Media

, Ph.D. Dissertation Sharif University of Technology Khodadadi, Ali (Author) ; Rabiee, Hamid Reza (Supervisor)

Abstract

Nowadays many of us spend a big part of our daily times on social media.One of the most important research problems in social media analysis is how to engage users. The trace of user activity over these websites is a valuable resource for user understanding and engagement, but this data is very huge and unstructured. An approach to deal with this problem is user behavior modeling. In this process, first a behavioral model is considered for users, then using the activity data and the behavioral model, some parameters are learned. Finally, using the learned parameters, a user profile is constructed for each user. This profile can be used for user engagement and many other applications....

Using Statistical Pattern Recognition on Gene Expression Data for Prediction of Cancer

, M.Sc. Thesis Sharif University of Technology Hajiloo, Mohsen (Author) ; Rabiee, Hamid Reza (Supervisor)

Abstract

The classification of different tumor types is of great importance in cancer diagnosis and drug discovery. However, most previous cancer classification studies are clinical based and have limited diagnostic ability. Cancer classification using gene expression data is known to contain the keys for addressing the fundamental problems relating to cancer diagnosis. The recent advent of DNA microarray technique has made simultaneous monitoring of thousands of gene expressions possible. With this abundance of gene expression data, researchers have started to explore the possibilities of cancer classification using gene expression data and quite a number of Pattern Recognition approaches have been...

Relations Between Dynamical Systems And Knot Theory

, M.Sc. Thesis Sharif University of Technology Madani, Meysam (Author) ; Fanaii, Hamid Reza (Supervisor)

Abstract

In fact knot theory is working by an elastic string. A knot is A smooth embedding of in . We say that two knots are equivalent if there is an ambient isotopic between them. In knot theory we study equivalent classes of knots. As it seems from its name, a dynamical system is the study of motions, mechanics and dynamics of a system. We will observe some systems and stability of orbits in theme. Then we define templates which contain orbits in themselves. At last, we observe relations between discrete dynamical systems and knot theory. Then for any arbitrary chaotic knot we observe that there exist an universal template that contain a copy of any kind of not. Finally we will study some open...

Sampling in Large-Scale Complex Networks

, Ph.D. Dissertation Sharif University of Technology Salehi, Mostafa (Author) ; Rabiei, Hamid Reza (Supervisor)

Abstract

Many real-world communication systems such as Internet, online social networks, and brain networks can be modeled as a complex network of interacting dynamical nodes. These networks have non-trivial topological features, i.e., features that do not occur in simple networks such as lattices or random networks. The tremendous growth of Internet and its applications in recent years has resulted in creation of large-scale complex networks involving tens or hundreds of millions of nodes and links. Thus, it may be impossible or costly to obtain a complete picture of these large networks, and sampling methods are essential for practical estimation of network properties. Therefore, in this thesis, we...