Seminar & Pilot Demonstration • 10 July 2026
Quantum Machine Learning Meets Medical Imaging: Classifying Alzheimer’s from Brain MRI
A hands-on seminar and joint pilot demonstration of a practical QML pipeline for medical AI
Sungkyunkwan University (SKKU), Seoul, South Korea
On 10 July 2026, at Sungkyunkwan University (SKKU), Seoul, South Korea, I delivered a seminar titled “Quantum Machine Learning for Medical AI: Classifying Alzheimer’s from Brain MRI” as part of the project “Training and Joint Pilot Demonstration of a QML Practical Pipeline for Medical AI.” The session brought together the foundations of quantum machine learning and their real-world application to neurological disease detection, demonstrating an end-to-end pipeline that classifies Alzheimer’s disease directly from brain MRI scans.
The seminar covered the core building blocks of QML — qubits, quantum gates, angle encoding, and the variational quantum circuit (VQC) — before walking through the complete practical workflow: preparing and preprocessing the brain MRI dataset, reducing image features, encoding them into quantum states, and training a hybrid quantum–classical model to distinguish between disease stages. The talk concluded with a live pilot demonstration and an interactive question-and-answer discussion.
Seminar Highlights
- Foundations of quantum machine learning for medical image analysis
- A practical, reproducible QML pipeline built with PennyLane
- Alzheimer’s disease classification from brain MRI
- Live pilot demonstration and hands-on student training
Glimpses & Recordings from the Session
Looking Ahead
This seminar and pilot demonstration mark an important step toward integrating quantum machine learning into practical medical-AI workflows. By making these concepts accessible and reproducible, the goal is to equip students and researchers to explore quantum approaches for real clinical imaging problems — from Alzheimer’s detection to a broader range of diagnostic tasks.
Dr. Javeria Amin • Quantum Machine Learning for Medical AI • Sungkyunkwan University (SKKU), Seoul, South Korea
10 Comments
Amazon Session
ReplyDeleteMASHALLAH Great Job mam... God Bless u with many more
ReplyDeleteCongratulations, Mam! This is an outstanding contribution to the advancement of Quantum Machine Learning in healthcare. Successfully demonstrating a practical hybrid quantum–classical pipeline for Alzheimer's classification from brain MRI—covering feature engineering, quantum state encoding, variational quantum circuits (VQCs), and implementation with PennyLane—bridges the gap between theoretical quantum computing and real-world clinical AI. This work is an inspiring milestone toward next-generation intelligent medical imaging and precision diagnostics. Wishing you continued success in pioneering impactful research at the intersection of quantum computing and medical AI.
ReplyDeleteMashAllah...Such an interesting session
ReplyDeleteCongratulations maam!🤩
ReplyDeleteInteresting session. You are so talented. Keep growing and keep inspiring young talent from Pakistan.
ReplyDeleteCongratulations, Ma'am! 🎉 Wishing you continued success on this remarkable achievement. Your work in advancing Quantum Machine Learning for Medical AI is truly inspiring and will undoubtedly motivate students and researchers to explore innovative solutions for real-world healthcare challenges. Wishing you many more milestones and accomplishments ahead. Best wishes! 🌟
ReplyDeleteIncredible insights! I never thought about how quantum algorithms could help with personalized treatment plans and analyzing medical imaging data so fast. This is exactly the kind of innovation healthcare needs. Great work!
ReplyDeleteMashaAllah . May god give you more success
ReplyDeleteCongratulations, Ma'am! Bringing quantum computing and clinical imaging together in a single reproducible pipeline is impressive work. Starting from qubits and gates, moving through angle encoding, and ending with a trained hybrid quantum-classical model on brain MRI gives students a clear path from fundamentals to a real application - and building it on PennyLane means others can actually reproduce it. Excited to see this extended to other diagnostic tasks.
ReplyDelete