m

Dr. Mustafa Elattar

Program Director of Artificial Intelligence (AI)

Faculty Office Ext.

1754

Faculty Building

UB1

Office Number

210

Biography

Dr. Mustafa Elattar, born in Cairo, Egypt in 1986, is a highly accomplished professional in the fields of biomedical engineering, image analysis, medical imaging, and artificial intelligence. He embarked on his academic journey at Cairo University, where he earned his bachelor’s degree in systems and biomedical engineering in 2008, Continuing his pursuit of knowledge and innovation, Mustafa received his Ph.D. in Biomedical Engineering and Physics, Faculty of Medicine, in 2016, from the Academic Medical Center, University of Amsterdam, The Netherlands. His doctoral research centered around developing a preoperative planning framework for transcatheter aortic valve implantation, showcasing his proficiency in leveraging advanced technologies to enhance surgical procedures. After completing his Ph.D., Mustafa joined the Netherlands Cancer Institute (NKI) as a postdoctoral fellow in 2016. During his time there, he focused on conducting research for image-guided radiotherapy, further expanding his expertise in the intersection of medical imaging and cancer treatment. In August 2017, Mustafa joined Nile University as an assistant professor at the Information Technology and Computer Science School. He is also the director of the Artificial Intelligence undergraduate program. Mustafa has gained valuable industry experience. He has worked in the research and development divisions of renowned companies such as Diagnosoft Inc., 3mensio B.V., PieMedical N.V., and Myocardial Solutions Inc. Furthermore, in August 2018, Mustafa founded Intixel Co. S.A.E., where he currently serves as its CEO

Achievements
  1. Initiated the first African network for AI and Medical imaging enthusiasts, researchers and scientists.
  2. IVLP Impact Award from U.S. Department of State (2022).
  3. Best poster award at the Novel Intelligent and Leading Emerging Sciences Conference (2019).
  4. Top 5 startups in Young Business Hub Entrepreneurship Investment Summit, Bahrain (2019).
  5. Fareed Bader Award in World Entrepreneurs and Investments Forum (WEIF) (2019).
  6. Pitch deck winner and winning the best Health-tech startup at Takeoff Istanbul International Startup Summit after being evaluated by the jury members and 150+ mentors (2019).
  7. Top 10 Startups to be selected for the “2WiN Mentoring Program” supported by the German Chamber of Commerce (2019).
  8. Best poster in the Postgraduate Research Forum, Nile University (2018).
  9. Best Support for research assistant from Nile University (2018).
  10. Best Support for research assistant from Banque Misr (2017).
  11. 3rd place in Left ventricular segmentation challenge from cardiac MRI (STACOM 2011).
  12. Best poster in Image Analysis and Recognition Conference (2010).
  13. Full scholarship for master’s studies at Nile University (2008).
  14. Fourth Place in Made in Egypt (MIE) competition for the best graduation project (2007).
Recent Publications

Convolutional Neural Network with Attention Modules for Pneumonia Detection

In 2017, pneumonia was the primary diagnosis for 1.3 million visits to the Emergency Department (ED) in the United States. The mortality rate was estimated to be 5%-10% of hospitalized patients, whereas it rises to 30% for severe cases admitted to the Intensive Care Unit (ICU). Among all cases admitted to ED, 30% were misdiagnosed, and they did not suffer from pneumonia, which raises a flag for

Artificial Intelligence
Healthcare

Deep convolutional encoder-decoders with aggregated multi-resolution skip connections for skin lesion segmentation

The prevalence of skin melanoma is rapidly increasing as well as the recorded death cases of its patients. Automatic image segmentation tools play an important role in providing standardized computer-assisted analysis for skin melanoma patients. Current state-of-the-art segmentation methods are based on fully convolutional neural networks, which utilize an encoder-decoder approach. However, these

Artificial Intelligence

Deep Ensemble Learning for Skin Lesion Classification from Dermoscopic Images

Skin cancer is one of the leading causes of death globally. Early diagnosis of skin lesion significantly increases the prevalence of recovery. Automatic classification of the skin lesion is a challenging task to provide clinicians with the ability to differentiate between different kind of lesion categories and recommend the suitable treatment. Recently, Deep Convolutional Neural Networks have

Artificial Intelligence

Lvlnet: Lightweight left ventricle localizer using encoder-decoder neural network

Automatic localization of the left ventricle (LV) is an important preprocessing step in any further analysis or quantification of LV function. Also, LV localization is usually done manually by MRI operator to plan Cardiac Magnetic Resonance Imaging (Cardiac MR) acquisition which can be standardized and automated to reduce the operator's error. In this study, we propose LVLNET; an automatic left

A computed tomography-based planning tool for predicting difficulty of minimally invasive aortic valve replacement

OBJECTIVES Minimally invasive aortic valve replacement has proven its value over the last decade by its significant advancement and reduction in mortality, morbidity and admission time. However, minimally invasive aortic valve replacement is associated with some on-site difficulties such as limited aortic annulus exposure. Currently, computed tomography scans are used to evaluate the anatomical

Artificial Intelligence

A collaborative resource to build consensus for automated left ventricular segmentation of cardiac MR images

A collaborative framework was initiated to establish a community resource of ground truth segmentations from cardiac MRI. Multi-site, multi-vendor cardiac MRI datasets comprising 95 patients (73 men, 22 women; mean age 62.73. ±. 11.24. years) with coronary artery disease and prior myocardial infarction, were randomly selected from data made available by the Cardiac Atlas Project ( Fonseca et al

Artificial Intelligence

Myocardial segmentation using constrained multi-seeded region growing

Multi-slice short-axis acquisitions of the left ventricle are fundamental for estimating the volume and mass of the left ventricle in cardiac MRI scans. Manual segmentation of the myocardium in all time frames per each cross-section is a cumbersome task. Therefore, automatic myocardium segmentation methods are essential for cardiac functional analysis. Region growing has been proposed to segment

Energy and Water
Agriculture and Crops
Mechanical Design
Innovation, Entrepreneurship and Competitiveness

Segmentation of left ventricle in cardiac MRI images using adaptive multi-seeded region growing

Multi-slice short-axis acquisitions of the left ventricle are fundamental for estimating the volume and mass of the left ventricle in cardiac MRI scans. Manual segmentation of the myocardium in all time frames per each cross-section is a cumbersome task. Therefore, automatic myocardium segmentation methods are essential for cardiac functional analysis. Region growing has been proposed to segment

Artificial Intelligence
Healthcare

Performance evaluation of cardiac MRI image denoising techniques

Black-blood cardiac Magnetic Resonance Imaging (MRI) plays an important role in diagnosing a number of heart diseases. The technique suffers inherently from low contrast-tonoise ratio between the myocardium and the blood. In this work, we examined the performance of different classification techniques that can be used. The three techniques successfully removed the noise with different performance

Artificial Intelligence
Research Tracks
  • Medical Imaging
  • Artificial Intelligence
  • Image Analysis
  • Knowledge Aggregation
  • Graph Optimization
  • Clinical Research
  • Computational Cardiology
Projects
a
Research Project

Lung Cancer Detection in Chest X-Ray Images Empowered by 3D Computed Tomography Deep Convolutional Radiomics (CXRClear)

Objective/Contributions: Cancer is treatable if it is discovered at an early stage, and lung cancer screening is a critical component in a preventive care protocol. Although CT imaging affords higher spatial resolution and 3D density information than digital chest X-rays, there are still limitations to having it as a cheap and fast method for rural areas outreach. These limitations are outlined in
3
Research Project

Smart Agricultural Clinic: Egyptian Farmer Electronic Platform for the Future

Objective/Contributions: Smart agricultural clinic (SAC) aims to: 1) Provide an integrated end-to-end digital system to effectively deliver personalized agriculture extension and veterinary services, including best cultivation, fertilization and breeding practices, to farmers and animal producers through the use of mobile/handheld devices. 2) Use advanced computer vision and deep learning
1
Research Project

Artificial Intelligence Based Cloud Computing for Autonomous Traffic Management

Automobile-related deaths rank as one of the most common causes of death in many places, particularly developing countries; Egypt loses about 12,000 lives due to road traffic crashes every year. The greatest danger to human beings is not cars but people themselves because cars are not dangerous if driven by care and more attention. Cell phone use, whether by talking on the phone or texting