Ashraf Ul Alam
Experience in medical image analysis · Computer vision · Domain adaptation
My interests span machine learning and its applications. I’ve explored medical image analysis, computer vision, domain adaptation and NLP, and I’m keen to deepen my research in natural language processing, language models and information systems security.
I’d love to join a research team, bring my experience and curiosity, and explore new ideas together.
A little about me
I’m currently pursuing a Master of Information Systems and Technology at Curtin University. I completed my B.Sc. in Computer Science and Engineering at Rajshahi University of Engineering & Technology (RUET), Bangladesh.
My undergraduate research explored unsupervised domain adaptation and knowledge distillation for medical image segmentation, working with both retinal fundus images and brain MRI.
Previously, I worked as a Research Assistant at the Young Learners’ Research Lab and a Software Engineer at Sasthotech, contributing to medical image analysis, Bengali document understanding and healthcare software.
I’m keen to deepen my research in natural language processing, language models and information systems security, while continuing to explore new applications of machine learning.
Explore my projects →Research interests & directions
Domain adaptation & generalisation
Building on my experience in medical imaging to explore transfer learning, knowledge distillation and models that adapt to new domains.
Natural language processing & language models
Keen to explore language understanding, language-model adaptation and agentic AI in greater depth.
Information systems security
Interested in how information systems can be made more secure, with a focus on threat detection, data privacy and applications of AI in cybersecurity.
Selected research
All publications →
PRODIA
A probability distribution alignment framework for unsupervised domain adaptation in medical image segmentation.
Research overview →
NeuroSeg3D
Exploring residual connections and spatial attention in a 3D U-Net for brain tumour segmentation.
Explore the project →
BanglaOngko
A dataset and YOLOv8-based workflow for detecting handwritten Bengali mathematical expressions.
View the publication →Background at a glance
More about my experience →Master of Information Systems and Technology
B.Sc. in Computer Science and Engineering
Software Engineer · Healthcare software and explainable AI
Research Assistant · Medical imaging and Bengali OCR
Let’s connect
I welcome conversations about research opportunities and collaborations in medical imaging, computer vision and machine learning.
ashrafamit9227@gmail.com ↗