Muhammad Junaid Ali

PhD in Informatics | Research & Teaching

Learn More

About Me

Profile picture

I am a PhD candidate in Informatics at the University Haute Alsace, with a strong focus on automatic machine learning and metaheuristic techniques for medical imaging tasks. My research contributes to automating complex processes like hyperparameter optimization and Neural Architecture Search. I hold a Master's in Computer Science from COMSATS University Islamabad, where I proposed an FCN-based architecture for breast pectoral muscle segmentation, a crucial step for breast cancer detection. My background also includes a Bachelor's in Computer Science from FAST NUCES. I have a proven track record in research, including a top-ranked achievement in the BraTS 2020 Competition, and a passion for teaching and mentoring students.

BraTS 2020 Competition: Ranked 3rd in Overall Survival (OS) prediction task.

Technical Skills

Languages

  • Python (NumPy, Flask, Django, Matplotlib, Keras, Pandas, ScikitLearn, NLTK, PyTorch, Tensorflow)
  • Java, C/C++
  • PHP, MySQL
  • Spark (Beginner), Bash scripting

Web & Database

  • HTML, CSS, JavaScript, jQuery
  • SQL, MySQL

DevOps & Cloud

  • CI, Docker, Kubernetes, Logging
  • Amazon SageMaker, E3

IDE

  • PyCharm, Eclipse, Visual Studio, VS Code, Spyder

Awards & Grants

  • Funded MS Thesis under HEC grant from 2019-2020
  • National ICT Scholarship program for BS studies from 2013-2017
  • PhD scholarship under ANR project
  • Received monetary award worth $300 from Intel Corporation for BraTS 2020 Competition.

Academic Publications

Journal Publications

  • Muhammad Junaid Ali et al. "A Review of AutoML Optimization Techniques for Medical Image Applications". Computerized Medical Imaging and Graphics (2024).
  • Nazir, Maria, Muhammad Junaid Ali et al. "Multi-task learning architecture for brain tumor detection and segmentation in MRI images." Journal of Electronic Imaging (2022).
  • Muhammad Junaid Ali et al. "Multi-level Kronecker Convolutional Neural Network (ML-KCNN) for Gliomas Segmentation from Multi-Modal MRI Volumetric Data". Journal of Digital Imaging.
  • Muhammad Junaid Ali et al. "Enhancing breast pectoral muscle segmentation performance by using skip connections in fully convolutional network". Int J Imaging Syst Technol (2020).

Conference Publications

  • Muhammad Junaid Ali et al. "Evolutionary Neural Architecture Search for 2D and 3D Medical Image Classification". 24th International Conference on Computational Science (2024).
  • Muhammad Junaid Ali et al. "Robust Neural Architecture Search using Differential Evolution for Medical Images". 27th International Conference on Applications of Evolutionary Computing (2024).
  • Muhammad Junaid Ali et al. "Designing Convolutional Neural Networks using Surrogate assisted Genetic Algorithm for Medical Image Classification". GECCO '23 Companion (2023).
  • Presented our top ranked survival prediction method in Brain Lesion (BrainLes) workshop, a satellite event of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2020 (Virtual).
  • Presented Paper titled "A novel approach for POS tagging of Pashto" at first international conference on emerging technologies held at Rayadh Saudi Arabia (Virtual)
  • Presented Paper titled "Robust Neural Architecture Search for Medical Image Classification" at EvoApps Conference held at Aberystwyth, UK

Experience

Tutor/Instructor

Virtual University, Islamabad Campus | April 2021 to November 2023

  • Teaching and mentoring students in their undergraduate courses.
  • Checking assignments and quizzes.
  • Supervising students in their projects.

Research Assistant

Medical Imaging and Diagnostics Lab, COMSATS University | December 2020 to April 2021

  • Worked on brain stroke detection and segmentation.
  • Wrote academic papers on findings.
  • Developed AI-based diagnosis systems for breast cancer detection and brain tumor segmentation.

Projects

Machine Learning Name Entity (NE) Recognition

Part of the Machine Learning course, this project involved using different machine learning algorithms for Name Entity Recognition.

Classification and Clustering with Apache Spark

A semester project for a Big Data course where I performed classification and clustering of data using Apache Spark on Google Colab.

Web-based CADx System for Brain Tumor Segmentation

Developed a web interface for a brain tumor segmentation approach for lab demonstration at the Medical Imaging and Diagnostics Lab.