Deep generative models such as Generative Adversarial Network (GAN) and Variational Auto-Encoder (VAE) are currently receiving widespread attention from not only the computer vision and machine learning communities, but also in the MIC and CAI community. These models combine the advanced deep neural networks with classical density estimation (either explicit or implicit) for achieving state-of-the-art results. DGM4MICCAI workshop at MICCAI 2025 will be all about Deep Generative Models in Medical Image Computing and Computer Assisted Interventions.

Submission Details

The online submission for DGM4MICCAI is open until 24. June 2025, 11:59 PM Pacific Time. Contributions must be submitted online through the CMT submission system.

We seek contributions that include, but are not limited to:

• Novel architectures, loss functions, and theoretical developments for:
  • GANs and Adversarial Learning
  • Variational Auto-Encoder
  • Disentanglement
  • Flow
  • Autoregressive models
• Stable Diffusion Models
• Causal generative models
• Multi-Modality and Cross-Modality linking
• Novel metrics and uncertainty estimates for performance assessment and interpretability of generative models
• Generative models under limited, sparse and noisy image inputs
• Supervised and Unsupervised Domain Adaptation, Transfer Learning and Multi-Task Learning
• Segmentation, Detection, Synthesis, Reconstruction, Denoising, Supersampling, Registration
• Image-to-Image translation for Synthetic Training Data Generation or Augmented Reality
• Neural Rendering
• Diffusion Models, Normalizing Flow Models, Invertible Networks

We particularly welcome papers driven by the theme "MIC meets CAI". Interesting novel applications of deep generative models in MIC and CAI beyond these topics are also welcome.

Workshop proceedings are published as part of Springer Nature's Lecture Notes in Computer Science (LNCS) series. Manuscripts will be reviewed in double-blinded peer-review. Please prepare your workshop papers according to the MICCAI submission guidelines (LNCS template, 8 pages maximum).
Supplementary material: PDF documents or mp4 videos, 10 MB maximum file size.

Reviewing Responsibility: At least one co-author must volunteer to review for DGM4MICCAI 2025. The submission form will request the name and email address of the qualified co-author nominated for reviewing duties.

Program

DGM4MICCAI workshop will be a half-day event (Location: TBA), following the agenda below:
All times are given in KST time. Please note that times might be subject to change, so keep an eye on the schedule or follow us on LinkedIn to be up-to-date.

Long Orals 1

Paper ID	Title
2	The Devil is in the Prompts: De-Identification Traces Enhance Memorization Risks in Synthetic Chest X-Ray Generation
8	MedSymmFlow: Bridging Generative Modeling and Classification in Medical Imaging through Symmetrical Flow Matching
10	Evaluation of 3D Counterfactual Brain MRI Generation
12	Med-Art: Diffusion Transformer for 2D Medical Text-to-Image Generation
13	Conditional diffusion models for guided anomaly detection in brain MRI using fluid-driven anomaly randomization
14	Hierarchical Diffusion Framework for Pseudo-Healthy Brain MRI Inpainting with Enhanced 3D Consistency
18	Masked Registration and Autoencoding of CT Images for Predictive Tibia Reconstruction
19	GANs vs. Diffusion Models for virtual staining with the HER2match dataset
20	From Scope to Script: An Automated Report Generation Model for Gastrointestinal Endoscopy
22	PathSegDiff: Pathology Segmentation using Diffusion model representations
29	fastWDM3D: Fast and Accurate 3D Healthy Tissue Inpainting

Short Orals 1

Paper ID	Title
4	Robust Noisy Pseudo-label Learning for Semi-supervised Medical Image Segmentation Using Diffusion Model
6	Unsupervised Brain Tumor Segmentation via Bi-Level Optimization Guided by Radiological Reports
16	CogGNN: Cognitive Graph Neural Networks in Generative Connectomics
17	ACNEDIT: Acne Creation and Non-Destructive Editing with Dynamic Intensity Tuning using Deep Learning on Facial Images for Dermatological Application
24	RealDeal: Enhancing Realism and Details in Brain Image Generation via Image-to-Image Diffusion Models
25	Resolution Invariant Autoencoder
31	Pre to Post-Treatment Glioblastoma MRI Prediction using a Latent Diffusion Model
33	Latent 3D Brain MRI counterfactual

Long Orals 2

Paper ID	Title
34	Leveraging Adversarial Learning for Pathological Fidelity in Virtual Staining
41	Uncovering Aβ Accumulation Patterns via Multi-modal Latent Space Clustering using Residual Diffusion Model
43	3D CBCT Artefact Removal Using Perpendicular Score-Based Diffusion Models
47	Unsupervised anomaly detection using Bayesian flow networks: application to brain FDG PET in the context of Alzheimer's disease
56	Frequency-Calibrated Membership Inference Attacks on Medical Image Diffusion Models
57	Controllable Surface Diffusion Generative Model for Neurodevelopmental Trajectories
58	CtrlEndoDiff: Diffusion-Based Synthetic Image Generation for Enhanced ACF Segmentation
60	MedIL: Generating Arbitrary-Resolution Medical Images with Implicit Latent Spaces
63	Neural Autoregressive Modeling of Brain Aging

Short Orals 2

Paper ID	Title
36	EchoAdapter: Adapting Pretrained Image Diffusion Models for Cardiac Ultrasound Video Generation
37	Tubular Anatomy-Aware 3D Semantically Conditioned Image Synthesis
51	Reconstruct or Generate: Exploring the Spectrum of Generative Modeling for Cardiac MRI
54	Pixel Perfect MegaMed: A Megapixel-Scale Vision-Language Foundation Model for Generating High Resolution Medical Images
55	Anatomically Guided 3D Diffusion Models for Synthetic Prostate MRI Generation