Medical AI Research
Medical image analysis, AI-assisted diagnosis, healthcare AI, and clinical decision-support research.
AI ENGINEER // MEDICAL AI RESEARCHER
I work across applied AI research, deep learning, computer vision, medical image analysis, software, and digital operations—connecting technical work with practical applications.
Professional Overview
My professional profile combines research-oriented AI work with technology implementation, digital operations, and organisational execution.
Medical image analysis, AI-assisted diagnosis, healthcare AI, and clinical decision-support research.
Deep learning, computer vision, image-based AI solutions, and applied research and development.
Technology implementation, CRM and website development, system optimisation, UI/UX integration, and digital product operations.
Multidisciplinary team leadership, cross-functional coordination, content development, and operational execution.
Career Journey
Designed responsive web interfaces and translated UI/UX prototypes into front-end implementations.
Led a multidisciplinary team and oversaw CRM, website, UI/UX, content, and e-commerce technology operations.
Develops deep learning models for medical image classification and AI-assisted diagnosis.
Received hands-on training and project-based experience in Artificial Intelligence, Machine Learning, Deep Learning, and Computer Vision, including data preprocessing, model development, training, and evaluation. Applied AI/ML techniques to practical projects using Python and deep learning frameworks, strengthening skills in experimentation, performance analysis, and end-to-end AI research workflows.
Develops deep learning and computer vision solutions for image-based applications and contributes to AI system integration and automation.
Research
Research interests include Artificial Intelligence, Deep Learning, Computer Vision, Medical Image Analysis, Healthcare AI, Explainable AI, and Clinical Decision Support.
Research Matrix
The current research direction connects core AI methods with computer vision and healthcare-oriented applications.
Selected Publications
M. Y. Mitu & M. A. Hossain. Xception achieved 99.84% accuracy in four-class CT classification of normal, cyst, stone, and tumor.
M. Y. Mitu & M. A. Siddiki. NASNetLarge achieved 91.0% accuracy, 90.5% precision, 90.8% recall, and 90.6% F1-score.
Education
International University of Business Agriculture and Technology (IUBAT), Bangladesh · 2013–2016 · CGPA 3.74/4.00.
Connect
Current Focus
Current areas of focus include deep learning, computer vision, medical image analysis, healthcare AI, explainable AI, and clinical decision support.