Deep generative models such as Diffusion Models, Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) 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 2026 will be all about Deep Generative Models in Medical Image Computing and Computer Assisted Interventions.

DGM4MICCAI Workshop Proceedings are available via this Springer Link.

Submission Details

The online submission for DGM4MICCAI is open until 19. June, 11:59 PM Pacific Time. Contributions must be submitted online through the OpenReview submission system

We seek contributions that include, but are not limited to novel architectures, loss functions, and theoretical developments for:

• Generative World Models
• Diffusion Models
• Causal generative models
• Neural Cellular Automata
• GANs and Adversarial Learning
• Variational Auto-Encoder
• Disentanglement
• Flow
• Autoregressive 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

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: Limited to multimedia content (e.g., videos in AVI, MP4 or WMV format). PDF files may not be submitted as supplementary materials in 2026 unless authors are citing a paper that has not yet been published. All supplementary material must be self-contained and zipped into a single file.

DGM4MICCAI workshop will be a half-day event (Location: Meeting Room "Berlin" on the Ground Floor), following the agenda below:
All times are given in CEST 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.

Short Orals

Paper ID	Title
7	Making Sparse Labels Reliable: Validity-gated ROI Guidance for Medical Image Generation with Conditional Latent Diffusion Model
11	Weakly Supervised Lung Nodule Segmentation via Plug-and-Play Guidance of 3D Rectified Flow
12	Patient-Adaptive Modality Attention for Multimodal Brain Tumor Synthesis via Latent Diffusion
23	Diffusion-Based Synthesis of Complete 3D Biparametric Prostate MRI
24	2D Versus 3D Diffusion for In Silico Training of Interventional X-ray AI Models
25	Large-Volume Conditioned 3D Latent Diffusion Models for CT Metal Artifact Suppression
27	Generation of Breast Tumors' Shear Wave Elastography Images from Corresponding Ultrasound Images with US2SWEdiff
28	LaST-Diff: Latent Spatiotemporal Diffusion for Temporally Stable Echocardiography Video Segmentation

Long Orals

Paper ID	Title
3	From Sparse X-rays to 3D CT: Training-Free Reconstruction with Diffusion Priors
6	FedDSR: Codebook-Based Distribution Alignment for Heterogeneous Federated CT Super-Resolution
8	PCaPaint: Prostate Cancer Inpainting by Mitigating Shortcut Learning
9	A Unified Latent Diffusion for High-Fidelity Any-to-Any Brain Modality Synthesis
10	When the Edit Changes the Patient: Measuring Identity Preservation in Counterfactual Retinal Images
13	Recovering Progression Beyond the Identity Shortcut: A Schrödinger Bridge Framework for Longitudinal Brain-MRI
14	Disentangled Retinal Fundus Synthesis with Non-Circular Vessel-Topology Evaluation
17	Feature-Space Guided Diffusion for Realistic Ultrasound Image Synthesis
20	Leveraging Multi-Representation Features from Diffusion Models for Unsupervised 3D Medical Image Segmentation
21	Unpaired D-FF-OCT-to-Histopathology Translation for Rapid Kidney Biopsy Visualization
22	Synthetic Data Generation for Automated Hair Instance Segmentation in Trichoscopy