Generative Models for Synthesizing Medical Images

About

Medical imaging is essential for diagnosis and treatment but faces challenges like high costs, patient risks (e.g., radiation exposure), and limited datasets, which hinder the generalizability of AI models. Generative models—such as GANs, VAEs, and Diffusion Models—offer solutions by synthesizing realistic medical images to augment datasets, reduce biases, and simulate disease progression. However, medical data scarcity, privacy concerns, and the complexity of high-dimensional 3D imaging (e.g., MRIs) demand specialized approaches to ensure anatomical accuracy and ethical compliance.

This tutorial addresses these challenges through hands-on exploration of generative architectures, privacy-preserving techniques (e.g., federated learning), and multi-modal synthesis using tools like PyTorch and MONAI. It emphasizes practical implementation with real-world datasets (e.g., ADNI) and evaluation frameworks that combine technical metrics (e.g., visual realism) with clinical validation to meet regulatory standards. Focus areas include 3D MRI/CT generation and strategies to balance innovation with patient safety and data integrity.

Date, Time, and Location

Date: September 23, 2025

Time: 8am-12:30pm (see Schedule below)

Location: TBD

Format and Schedule

Each speaker will present for 35 minutes, followed by 10 minutes for Q&A.

The final panel discussion will be attended by available speakers and moderated by an organizer.

Schedule:

08:00am-08:30am - Introduction and overview

08:30am-09:15am - Kilian Pohl

Title: Building Diffusion Models to Accelerate Discovery in Neuroscience

Abstract: While generative models of structural brain MRIs generally prioritize capturing coarse, visible effects of diseases (such as ventricular enlargement in Alzheimer’s disease), many neuroscience studies focus on detecting morphometric group differences between cohorts that are too subtle to identify visually in individuals. In this talk, we review several diffusion models designed to generate high-quality T1-weighted MRIs specifically tailored for neuroscience discovery. We present a systematic procedure for evaluating the ability of these synthetic MRIs to capture macrostructural properties of brain regions including subtle, disease-related effects. Finally, we highlight the successes and limitations of current technology in meeting critical criteria for incorporating synthetic MRIs into neuroscience research.

09:15am-10:00am - Ben Glocker

Title: Deep Structural Causal Models

Abstract: TBD

10:00am-10:30am - Break

10:30am-11:15am - Ulas Bagci

Title: TBD

Abstract: TBD

11:15am-12:00pm - Qingyu Zhao

Title: Generating and Evaluating Anatomical Plausibility in Brain Morphometry and Longitudinal Change

Abstract: Accurately characterizing and predicting changes in brain morphometry is essential for understanding normal neurodevelopment and aging, as well as deviations associated with brain disorders. In this talk, I will present recent advances in generating and evaluating the realism of brain morphometry using anatomically informed AI models. These approaches include deformation-based modeling, latent diffusion, spatiotemporal modeling, and segmentation-guided supervision to produce realistic morphometric changes from limited data while preserving topology and tissue boundaries. I will also highlight methods for rigorously assessing the anatomical plausibility of synthetic brain MRIs and their longitudinal trajectories. Together, these advances offer a pathway toward both generating realistic brain morphometry over time and rigorously validating its anatomical plausibility for research and clinical applications.

12:00pm-12:30pm - Panel discussion

Objectives

There are four objectives for this half-day tutorial:

1. Understand the Role and Challenges of training deep learning methods on High Dimensional Medical Images.

1. • Comprehend the critical role of medical imaging in modern healthcare

   • Recognize the challenges in 3D medical image acquisition (cost, time, radiation exposure)

   • Understand how synthetic data can expand and diversify training datasets and thus enhance model robustness and address population biases

2. Learn the Fundamentals and Adaptation of Generative Models

1. • Master core principles of advanced generative architectures (e.g., Diffusion Models) 

   • Understand the transition from 2D natural image synthesis to 3D medical imaging

   • Navigate unique challenges in generating 3D Medical Images:

     • Dataset scarcity and privacy considerations

     •  High-dimensional data handling

     • Learn specialized models to account for those challenges

3. Explore Advanced Approaches for Anatomy Plausibility Enhancement and Evaluate Generative Models
   
   • Examine state-of-the-art models for generating biologically plausible brain MRIs 

• Master evaluation frameworks combining:

• Traditional metrics (FID, SSIM)

• Domain-specific measures of anatomical accuracy – Clinical validation approaches

• Review best practices for ensuring anatomical and pathological accuracy • Understand quality assessment protocols for synthetic medical images

4. Engage in Practical Implementation and Disease Simulation

   •  Gain hands-on experience with PyTorch and medical imaging libraries (MONAI, TorchIO) 

   • Implement generative models using real-world medical datasets

   •  Learn techniques for disease progression simulation