Neuroimaging is key for improving our understanding of brain diseases

Avatar

Dr. Mostafa Salem

RESEARCHER IN MEDICAL IMAGE ANALYSIS

Faculty of Computers and Information, Assiut University

Biography

I received the BSc degree in Computer Science (2006), received the MSc degree in Computer Graphics& Vision (2013) from the Faculty of Computers and Information, Assiut University, Egypt. Recently, I received the PhD degree in medical image analysis (Brain MRI) from the VICOROB Group, University of Girona, under the supervision of Prof. Xavier Lladó and Prof. Joaquim Salvi. My current research interests include the development of techniques to automatically detect and segment multiple sclerosis lesions in longitudinal and cross-sectional brain MRI. Now, I am working as a assistant professor at computer science departement, Faculty of Computers and Information, Assiut University, Egypt, Assiut, Egypt. Also, Manager of Computers Consultations Center (CCC)، Assiut University.

Interests

  • Medical image analysis
  • Deep learning
  • Convolutional Neural Networks (CNNs)
  • Magnetic Resonance Imaging (MRI)
  • Multiple Sclerosis (MS)
  • Brain tumor detection and segmentation
  • Image processing, Computer vision, and 3D Reconstruction

Education

  • PhD in Medical Image Analysis, 2020

    University of Girona, Spain

  • MSC in Computer Science, 2013

    FCI, Assuit University, Egypt

  • BSc in in Computer Science, 2006

    FCI, Assuit University, Egypt

Skills

Programming

Python, C++, C#, Java

Deep learning

Keras, Pytorch

ITK

Insight Segmentation and Registration Toolkit

Matlab & Simulink

Git

SQL

Research Output

A novel approach to predicting the stability of the smart grid utilizing MLP-ELM technique

Alexandria Engineering Journal, 2023. Quality index: ([JCR N IF 6.626, Q1(7/92)].
PDF DOI

Utilizing CNN-LSTM techniques for the enhancement of medical systems

Alexandria Engineering Journal, 2023. Quality index: ([JCR N IF 6.626, Q1(7/92)].
PDF DOI

An Efficient Indoor Localization Based on Deep Attention Learning Model

Computer Systems Science and Engineering 2023. Quality index: (JCR N IF 4.397, Q1(13/54)).
PDF DOI

Improving the detection of new lesions in multiple sclerosis with a cascaded 3D fully convolutional neural network approach

Frontiers in Neuroscience, 2022. Quality index: (JCR N IF 3.707, Q2(97/272)).
PDF DOI

A blockchain-based hybrid platform for multimedia data processing in IoT-Healthcare

Alexandria Engineering Journal, 2022. Quality index: ([JCR N IF 6.626, Q1(7/92)].
PDF DOI

Evaluating the use of synthetic T1-w images in new T2 lesion detection in multiple sclerosis

Frontiers in Neuroscience, Brain Imaging Methods, 2022. Quality index: (JCR N IF 5.152, Q2(87/274)).
PDF DOI

Transductive Transfer Learning for Domain Adaptation in Brain Magnetic Resonance Image Segmentation

Frontiers in Neuroscience, 2021. Quality index: (JCR N IF 3.707, Q2(97/272)).
PDF DOI

Deep learning methods for automated detection of new multiple sclerosis lesions in longitudinal magnetic resonance images

PhD thesis in Brain Medical Image Analysis, Department of Computer Architecture and Technology, University of Girona, Spain, 2020.
PDF

A fully convolutional neural network for new T2-w lesion detection in multiple sclerosis

NeuroImage: Clinical, 2020. Quality index: (JCR N IF 3.943, Q1(3/14)).
PDF DOI

Multiple Sclerosis Lesion Synthesis in MRI Using an Encoder-Decoder U-NET

IEEE Access, 2019. Quality index: (JCR CSIS IF 4.098, Q1(23/155)).
PDF Code DOI

Detecting the appearance of new T2-w multiple sclerosis lesions in longitudinal studies using deep convolutional neural networks

Abstract in Multiple Sclerosis Journal, Stockholm Sweden, September, 2019 (JCR CN IF:5.649 Q1(23/199)).
PDF Poster

Lesion synthesis for extending MRI training datasets and improving automatic multiple sclerosis lesion segmentation

Abstract in Multiple Sclerosis Journal, Stockholm Sweden, September, 2019 (JCR CN IF:5.649 Q1(23/199)).
PDF Poster

One-shot domain adaptation in multiple sclerosis lesion segmentation using convolutional neural networks

NeuroImage: Clinical, 2019. Quality index: (JCR N IF 3.943, Q1(3/14)).
PDF Code DOI

Manual delineation of only one image in unseen databases is sufficient for accurate performance in automated multiple sclerosis lesion segmentation

Abstract in Multiple Sclerosis Journal, Berlin, Germany, October, 2018 (JCR CN IF:5.649 Q1(23/199)).
PDF

A supervised framework with intensity subtraction and deformation field features for the detection of new T2-w lesions in multiple sclerosis

NeuroImage: Clinical, 2018. Quality index: (JCR N IF 3.943, Q1(3/14)).
PDF Code DOI

Supervised detection of newly appearing T2-w multiple sclerosis lesions with subtraction and deformation fields features

Abstract in Multiple Sclerosis Journal, Paris, France, October, 2017 (JCR CN IF:5.649 Q1(23/199)).
PDF

3D Face Reconstruction and Animation

Master's thesis in Computer Science, Department of Computer Science, Faculty of Computers and Information, Assiut University, Egypt, …
PDF Video FCI

Projector calibration using passive stereo and triangulation

International Journal of Future Computer and Communication, 2013
PDF Slides DOI

Work experience

 
 
 
 
 

Assistant Professor

Assiut University

Sep 2020 – Present Assiut, Egypt
Responsibilities include:

  • Full-Time.
  • Manager of Computers Consultations Center (CCC), Assiut University.
 
 
 
 
 

Researcher & PhD Student

University of Girona

Jan 2016 – Sep 2020 Girona, Spain
Responsibilities include:

  • MRI, Cross-sectional and longitudinal multiple sclerosis lesion detection and segmentation, Lesion Synthesis in MRI, Image analysis.
  • Machine learning, Deep learning.
 
 
 
 
 

Assistant Lecturer

Assiut University

Jan 2014 – Sep 2020 Assiut, Egypt
 
 
 
 
 

Demonstrator

Assiut University

Sep 2006 – Jan 2014 Assiut, Egypt
Responsibilities include:

  • Doing scientific research in computer science and publishing high-quality papers. Besides, pursuing my Master and Doctorate degrees.
  • Participate and assist in teaching courses mainly in lab to students. Courses that I had already participated in teaching are (Computer Vision, Object-Oriented Programming using C++, Introduction to JAVA Programming, Introduction To Computers, Data Structure, Algorithms, Artificial Intelligence, Operating Systems, Automata, Compiler Theory).
  • Supervising final year students in their final year projects: by closely guiding them and solving various problems that arise until they finish the project before the delivery time.

Projects

EVOLUTION

Predictive models for multiple sclerosis using brain magnetic resonance imaging biomarkers.

BiomarkEM.cat

New technologies applied to clinical practice for obtaining biomarkers of atrophy and lesions in magnetic resonance images of patients …

NICOLE

Herramientas de neuroimagen para mejorar el diagnosis y el seguimiento clínico de los pacientes con esclerosis múltiple.

Conferences & Summer Schools

ECTRIMS2019 (Stockholm, Sweden): 35th Congress of the European Committee for Treatment and Research in Multiple Sclerosis

ECTRIMS September 11, 2019 – September 13, 2019
I participated with 2 posters:

  • Detecting the appearance of new T2-w multiple sclerosis lesions in longitudinal studies using Deep convolutional neural networks
  • Lesion synthesis for extending MRI training datasets and improving automatic multiple sclerosis lesion segmentation
See certificate

MICCAI2018 (Granada, Spain): 21st INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING & COMPUTER ASSISTED INTERVENTION

MICCAI September 16, 2018 – September 20, 2018
MICCAI satellite events:

  • 4th Workshop on Deep Learning in Medical Image Analysis (DLMIA)
  • Brain Lesion (BrainLes)
  • Multimodal Brain Tumor Segmentation Challenge (BraTS)
  • Ischemic Stroke Lesion Segmentation Challenge (ISLES)
See certificate

DeepLearn2017 (Bilbao, Spain): International Summer School on Deep Learning

University of Deusto July 17, 2017 – July 21, 2017
Some attended cources:

  • Basics of Deep Learning with Applications to Image Processing, Pattern Recognition and Computer Vision
  • Interpretable Deep Learning Models for Healthcare Applications
  • Generative Modeling and Unsupervised Learning
  • Visual Perception using Deep Convolutional Neural Networks
  • Deep Learning for Computer Vision
  • Incorporating Domain Bias into Neural Networks
  • Deep Learning in the Brain
See certificate

INIT/AERFAI Summer School on Machine Learning (Valencia, Spain)

UNIVERSITAT JAUME I - The Institute of New Imaging Technologies June 26, 2017 – June 30, 2017
Some attended cources:

  • Ensemble Learning
  • Probabilistic Graphical Models
  • Semi-Supervised Learning
  • Evolutionary Computing: Models, Scalability and Big Data Approaches
  • Adversarial Machine Learning
  • Deep Learning
  • Learning Classifiers from Streaming Data
See certificate

Recent Posts

I DEFENDED MY PHD THESIS

On 13 of Febraury, I defended my PhD thesis and finally got the DOCTOR title.
Last updated on Feb 17, 2020 3 min read

WE ATTENDED THE 35TH ECTRIMS

35th Congress of the European Committee for Treatment and Research in Multiple Sclerosis, Stockholm, Sweden.
Last updated on Jan 4, 2020 2 min read

Popular Topics

3D Reconstruction attention module Automatic detection Automatic lesion segmentation Automatic new lesion detection Availability Brain Convolutional neural networks Correspondences Data augmentation Deep Learning Fully convolutional neural networks Image synthesis Learning-based registration Machine learning Magnetic resonance imaging MRI Multiple Sclerosis Projector calibration Triangulation

Contact

  • +201007870383
  • Computer Science Dept., Faculty of Computers and Information, Assiut University, Assiut, Assiut 71515
  • Enter The Lab building, Floor 1, Walk to to Office 10 (Computer Science Dept.)
  • Wednesday 17:00 to 19:00
  • Book an appointment
  • Skype Me