Starting June 13, 2026

AI in
Medical Imaging
Summer Series

A weekly online deep-dive into AI for medical imaging, covering the full stack: from the ML cycle, SVMs, and neural networks to CNNs, Transformers, medical image modalities, and hands-on sessions with BioMedCLIP, RAD DINO, UNet, and state-of-the-art generative models.

Every Saturday 6:00 PM Beirut Time Online 30 Spots Max
Register Now , $25 View Curriculum
AIxMED Summer Saturdays
First Cohort · Summer 2026
  • Machine Learning Cycle
  • Hands-on Scikit-Learn & SVM
  • NNs, CNNs & Transformers
  • Medical Image Modalities
  • Medical Tasks & Hands-on Models
  • BioMedCLIP, RAD DINO, UNet
  • Nvidia Generative Models
  • Capstone Project
$25
First cohort
30 spots only
10
Sessions
1–2h
Per Session
30
Max Participants
$25
First Cohort Price
Curriculum

What You Will Learn

A hands-on progression from ML foundations to the architectures powering modern medical AI systems.

Session 01
Machine Learning Cycle
End-to-end ML workflow: problem framing, data preparation, model training, evaluation, and iteration.
Session 02
Hands-on Scikit-Learn & SVM
Support Vector Machines and classical ML in practice using Scikit-Learn on real datasets.
Session 03
Intro to Neural Networks
Perceptrons, backpropagation, activation functions, and training dynamics from the ground up.
Session 04
CNNs & Transformers
Convolutional networks for image features and Vision Transformers for global context in medical imaging.
Session 05
Medical Image Modalities
X-ray, MRI, CT, ultrasound, and pathology slides: characteristics, challenges, and preprocessing.
Session 06
Medical Tasks
Classification, regression, segmentation, and generation as the four core paradigms in medical AI.
Session 07
Classification: BioMedCLIP
Hands-on classification using BioMedCLIP, a vision-language model trained on biomedical image-text pairs.
Session 08
Regression: RAD DINO
Hands-on regression for radiology with RAD DINO, covering dose and outcome prediction from imaging data.
Session 09
Segmentation: UNet
Hands-on medical image segmentation using UNet, the gold-standard encoder-decoder architecture.
Session 10
Generation: Nvidia Models
Generative AI for medical imaging using Nvidia's medical AI models for synthetic data and augmentation.
Capstone
Project
Apply the full pipeline to a real medical imaging problem of your choice, from data to a working model.
Format

How It Works

Structured to fit busy professionals while keeping sessions deep and hands-on.

100% Online

Live sessions streamed online. Join from anywhere in the world.

Every Saturday

Consistent weekly schedule starting June 13, 2026 at 6:00 PM Beirut time.

Hands-on Code

Every session includes live coding, exercises, and real medical imaging examples.

Small Cohort

Maximum 30 participants for a focused, interactive learning experience.

Instructor

Meet Your Instructor

Ahmad Mustapha
Ahmad Mustapha
Doctoral Researcher · American University of Beirut

Ahmad is a doctoral researcher at AUB specializing in AI for medical imaging, with a focus on unsupervised deep learning, representation learning, and bias in medical AI systems. He has led and contributed to projects spanning X-ray disease detection, vehicle detection in the wild, and multi-service AI platforms. His mission is to make cutting-edge medical AI accessible to clinicians, researchers, and engineers alike.

Google Scholar LinkedIn GitHub Email
Pricing

Simple, Transparent Pricing

Early-cohort pricing , spots are strictly limited.

First Cohort · Summer 2026
$25
One-time payment · Payment instructions sent after registration
  • 8–10 live weekly online sessions
  • Hands-on coding exercises
  • Session recordings (where available)
  • Course completion certificate
  • Direct access to instructor
Only 30 spots available. First come, first served.

Have a question? Contact me on WhatsApp

2nd Cohort · Sep 21 – Oct 2, 2026

AI in
Medical Imaging
Intensive Bootcamp

The full AIxMed curriculum delivered in person as a focused, hands-on bootcamp. The complete stack, from the ML cycle and SVMs to CNNs, Transformers, and hands-on BioMedCLIP, RAD DINO, UNet, and generative models, packed into two intensive weeks at IMCAN, Beirut, for those who want to go from foundations to deployed fast.

Sep 21 – Oct 2, 2026 2–3 hours per session IMCAN, Centro Mall, Jnah, Beirut In Person 12 Spots Max
Register Now , $150 View Curriculum
AIxMED Intensive Bootcamp
2nd Cohort · In Person · IMCAN, Beirut
  • Machine Learning Cycle
  • Hands-on Scikit-Learn & SVM
  • NNs, CNNs & Transformers
  • Medical Image Modalities
  • Medical Tasks & Hands-on Models
  • BioMedCLIP, RAD DINO, UNet
  • Nvidia Generative Models
  • Capstone Project
$150
In-person intensive
12 spots only
10
In-Person Sessions
2 wks
Sep 21 – Oct 2
12
Max Participants
$150
Full Price
Curriculum

What You Will Learn

The same complete curriculum as the Summer series, delivered in person across ten daily sessions over two weeks, capped by a capstone project.

Day 01 · Sep 21
Machine Learning Cycle
End-to-end ML workflow: problem framing, data preparation, model training, evaluation, and iteration.
Day 02 · Sep 22
Hands-on Scikit-Learn & SVM
Support Vector Machines and classical ML in practice using Scikit-Learn on real datasets.
Day 03 · Sep 23
Intro to Neural Networks
Perceptrons, backpropagation, activation functions, and training dynamics from the ground up.
Day 04 · Sep 24
CNNs & Transformers
Convolutional networks for image features and Vision Transformers for global context in medical imaging.
Day 05 · Sep 25
Medical Image Modalities
X-ray, MRI, CT, ultrasound, and pathology slides: characteristics, challenges, and preprocessing.
Day 06 · Sep 28
Medical Tasks
Classification, regression, segmentation, and generation as the four core paradigms in medical AI.
Day 07 · Sep 29
Classification: BioMedCLIP
Hands-on classification using BioMedCLIP, a vision-language model trained on biomedical image-text pairs.
Day 08 · Sep 30
Regression: RAD DINO
Hands-on regression for radiology with RAD DINO, covering dose and outcome prediction from imaging data.
Day 09 · Oct 1
Segmentation: UNet
Hands-on medical image segmentation using UNet, the gold-standard encoder-decoder architecture.
Day 10 · Oct 2
Generation: Nvidia Models
Generative AI for medical imaging using Nvidia's medical AI models for synthetic data and augmentation.
Capstone
Project
Apply the full pipeline to a real medical imaging problem of your choice, from data to a working model.
Format

How It Works

Built for those who want to master the full stack fast, hands-on and in person.

In Person

Held on-site at IMCAN, Centro Mall, Jnah, Beirut. Face-to-face with the instructor.

Two Intensive Weeks

Ten daily sessions from Sep 21 to Oct 2, 2026, each running 2–3 hours: the whole curriculum, start to finish.

Hands-on Code

Every session includes live coding, exercises, and real medical imaging examples.

Tight Cohort

Maximum 12 participants for a high-touch, interactive intensive experience.

Prerequisite · Python Experience

Comfort with basic Python (variables, functions, loops, and working with libraries) so you can dive straight into the hands-on coding.

Audience

Who It's For

Designed for students and researchers ready to build real medical-AI skills.

Students
Computer Science Students
CS students who want to add applied AI and medical imaging to their toolkit.
Students
Computer Engineering Students
CE students looking to pair systems knowledge with modern AI engineering.
Students
Biomedical Students
Biomedical students who want to bring AI into their research and clinical work.
Professionals
Researchers
Researchers aiming to apply state-of-the-art models to their own imaging problems.
Outcomes

What You Get

Concrete, career-focused skills you can put to work right away.

For Software Engineers

AI engineering skills that let software engineers step into AI engineering roles and jobs.

For Biomedical Engineers

AI engineering skills that let biomedical engineers grow and advance as researchers.

Instructor

Meet Your Instructor

Ahmad Mustapha
Ahmad Mustapha
Doctoral Researcher · American University of Beirut

Ahmad is a doctoral researcher at AUB specializing in AI for medical imaging, with a focus on unsupervised deep learning, representation learning, and bias in medical AI systems. He has led and contributed to projects spanning X-ray disease detection, vehicle detection in the wild, and multi-service AI platforms. His mission is to make cutting-edge medical AI accessible to clinicians, researchers, and engineers alike.

Google Scholar LinkedIn GitHub Email
Testimonials

What Our Students Say

Feedback from participants of the first AIxMED cohort.

I truly learned a lot from this course and really appreciate the effort you put into this course.

H
Hawraa
First Cohort Participant

I am grateful to have had the opportunity to be part of this first cohort through which I have learned a lot.

S
Sundos
First Cohort Participant

We truly learned a lot throughout the sessions, and we really appreciate the time, guidance, and effort you put into making the series such a valuable experience for us.

A
Abeer
First Cohort Participant
Pricing

Simple, Transparent Pricing

In-person intensive pricing , spots are strictly limited.

2nd Cohort · In-Person Intensive · Beirut 2026
$150
One-time payment · Payment instructions sent after registration
  • 10 in-person sessions (Sep 21 – Oct 2)
  • On-site at IMCAN, Centro Mall, Jnah, Beirut
  • Hands-on coding exercises
  • Course completion certificate
  • Direct access to instructor
Only 12 spots available. First come, first served.

Have a question? Contact me on WhatsApp

Sponsors

Our Sponsors