Print PDF

Seyed Alireza Khoshsirat

26 years old, single

Tehran, Iran

arkhoshsirat@gmail.com

www.khoshsirat.com

Research Interests

I'm interested in combination of machine learning and image processing methods, and their application in medical imaging analysis.

I have experience of working with Convolutional Neural Networks, Active Shape Models, and Level-set methods.

Education

Master's

Allameh Tabataba'i University (Tehran)

Computer Science / Intelligent Systems, GPA: 3.5/4

Sep 2015 – Sep 2017
Bachelor's

University of Industries & Mines (Tehran)

Computer / Software Engineering, GPA: 3.5/4

Feb 2012 – Feb 2014
Associate's

Shahid Shamsipour Technical College (Tehran)

Computer / Software Engineering

Feb 2009 – Sep 2011

Master's Thesis

Combined Deep-Learning and Level-set Approach to Segmentation of the Left Ventricle in 3D Cardiac MRI

Supervisor: Farzad Eskandari

Advisor: Roya Hashempour

Examiner: Puya Khalilzadeh

Publications

Designing Evidence Based Risk Assessment System For Cancer Screening As An Applicable Approach For The Estimating Of Treatment Roadmap

Elham Maserat, Reza Safdari, Hamid Asadzadeh Aghdaei, Alireza Khoshsirat, Mohammad Reza Zali

BMJ Open, The 5th International Society for Evidence-Based Healthcare Congress, Kish Island, Iran

February 2017 - Volume 7 - Issue 1

doi: 10.1136/bmjopen-2016-015415.43

Standardized Tests

TOEFL

Total: 98, Reading: 26, Listening: 26, Speaking: 24, Writing: 22

GRE

Quantitative Reasoning: 158 (69th percentile), Verbal Reasoning: 146 (39th percentile), Analytical Writing: 3 (20th percentile)

Professional Service

Software Programmer

Mehrsys (Tehran)

Working on different software projects using up-to-date frameworks and technologies including: Java (Spring, Hibernate, JasperReports), NodeJS, AngularJS, Ionic, MongoDB, SQL Server, TypeScript, Wordpress.

Sep 2014 – Present
Software Programmer

Raydana (Tehran)

Working on an ERP system (Enterprise Resource Planning) using Java (Struts, Spring, Hibernate, JSP, JSF, GWT), Oracle, MySQL, and etc.

Jun 2011 – Sep 2014
Software Programmer

Faranam (Tehran)

Frontend and backend software development with ASP.NET MVC, WPF, Entity Framework, SQL Server and jQuery.

Dec 2010 – Jun 2011

Technical Skills

Machine Learning

Convolutional Neural Networks, AutoEncoders, Principal Component Analysis

Image Processing

TensorFlow, Caffe, OpenCV, Active Shape Models, Active Appearance Models, Level-set methods

Database

Oracle, MongoDB, SQL Server, Sqlite, LevelDB, HDF5

Programming Languages

Java, Python, Matlab, NodeJS, C#, TypeScript, HTML, JavaScript, CSS

Programming Frameworks

JavaEE, Spring, Hibernate, Struts, express.js, mongoose.js, Microsoft .NET, Entity Framework

User Interface

AngularJS, Telerik, KendoUI, Bootstrap, Ionic, Apache tiles, JavaFX, ASP.NET, ASP.NET MVC, WPF

Others

Wordpress, Apache Maven, Apache Tomcat, JasperReports, Version Control Systems, gulp.js, CentOS, Photoshop

References

Roya Hashempour

Allameh Tabataba'i University

Professor of Machine Vision

roya.hashempour@atu.ac.ir

Puya Khalilzadeh

Allameh Tabataba'i University

Professor of Discrete Math

puya.khalilzadeh@atu.ac.ir

Mohammad Zebarjad

Mehrsys Co.

Chief Executive Officer

info@mehrsys.com

Appendix

Master's Thesis Abstract

Segmentation of the left ventricle (LV) in cardiac magnetic resonance images (MRI) is an essential step for calculation of clinical indices such as ventricular volume and ejection fraction. In this thesis, we first explain essential concepts, then review existing methods for segmentation of LV. We continue by implementing and evaluating a method which employs deep learning algorithms combined with level-set method to fully automatically segment the LV in short-axis cardiac MRI datasets.
The method employs deep learning algorithms to learn the segmentation task from the ground truth data. Convolutional networks are employed to automatically detect the LV chamber in MRI dataset. Stacked autoencoders are utilized to infer the shape of the LV. The inferred shape is incorporated into level-set method to improve the accuracy and robustness of the segmentation. We validated our method using 45 cardiac MRI datasets taken from the MICCAI 2009 LV segmentation challenge and compared the results to the state-of-the-art methods. Excellent agreement with the ground truth was achieved. We computed validation metrics such as percentage of good contours, Dice metric, average perpendicular distance, and conformity as respectively 83%, 80%, 3.4mm and 70%.

Keywords: Deep-Learning, Level-set method, Left Ventricle, Cardiac MRI, Machine Learning