Next RISE-MICCAI Tutorial - April 10, 2026
Tuesday 31st March 2026
Join the next RISE-MICCAI Tutorial:
Brain Tumor Segmentation with U-Net Using the BraTS Dataset: A Beginner's Tutorial
Friday, April 10, 2026 at 10:00 am EDT / 4:00 pm CET
Brain tumor segmentation is an important task in medical image analysis, enabling automated identification of tumor regions in MRI scans and supporting clinical tasks such as diagnosis, treatment planning, and disease monitoring. Deep learning methods—particularly the U-Net architecture—have become widely used for this problem due to their strong performance in biomedical image segmentation. Public datasets such as the Brain Tumor Segmentation (BraTS) dataset have also played a key role in advancing research by providing standardized data and benchmarks.
This tutorial provides a beginner-friendly, hands-on introduction to brain tumor segmentation using deep learning. Using the BraTS dataset, participants will follow a practical workflow including exploratory data analysis, building and training a 2D U-Net model, evaluating segmentation performance, and visualizing model predictions. The tutorial then extends this approach to a 3D U-Net model, highlighting the key differences between 2D and 3D approaches. The session concludes with a discussion of practical challenges, limitations, and resources for further learning in medical image segmentation.
Presenter: Yasar Mehmood, Information Technology University of the Punjab, Lahore, Pakistan
Yasar Mehmood received his Ph.D. from COMSATS University Islamabad, Lahore Campus, where his research focused on developing resource-efficient methods for domain-adaptive pre-training of medical imaging models. During his Ph.D., he received the NVIDIA Academic Hardware Grant (2022) and collaborated with Prof. Anne Martel (University of Toronto) and Prof. Jianming Liang (Arizona State University) on medical AI research.
He is currently a Teaching Fellow at the Information Technology University of the Punjab, Lahore, Pakistan, where he teaches undergraduate computing courses and supervises Master’s students. His current research focuses on foundation models for medical data, in collaboration with Prof. Jianming Liang. (Arizona State University).
Registration is free and open to everyone.