| Time | Duration | Event |
| 13:30 - 13:35 | 5 min | Introduction to SASHIMI 2026 (Welcome + Opening remarks) |
| 13:35 - 14:35 | 60 min | Keynote (talk + Q&A) |
| | From multi-atlas registration to diffusion priors: a decade of individual anomaly detection in PET imaging |
| | Ninon Burgos |
| 14:35 - 15:30 | 55 min | Oral presentations (4 talks, 10 min presentation + 2 min Q&A) |
| | • CytoSyn: a Foundation Diffusion Model for Histopathology Image Synthesis |
| | Thomas Duboudin |
| | • Does FLAIR super-resolution erase or hallucinate small white-matter lesions? |
| | Zahra Khodakarami |
| | • AxonSynth: Domain-Randomized Synthetic Data for Zero-Shot 3D Axon Segmentation in Light-Sheet Microscopy |
| | Edward Gaibor |
| | • Sample Structure, Refine Contrast: Zero-Shot MR Image Harmonization with a Phase-Preserving Diffusion Prior |
| | Muhammad Faizyab Ali Chaudhary |
| 15:30 - 16:00 | 30 min | Coffee break |
| 16:00 - 16:50 | 50 min | Poster session |
| | Poster Theme 1: Advances in generative frameworks |
| | • nnDiffusion: A Standardized 3D Diffusion Framework for Medical Image Synthesis |
| | • Few-Shot Flow Matching with Stochastic Barycentric Sampling for Image Synthesis |
| | • MedPCFM-TED: One-Step Point Cloud Flow Matching for Implant Generation |
| | • Clinically Steerable Retinal Image Generation from Foundation Model Latent Spaces |
| | • CONFLUX: A Latent Diffusion Model for 3D Chest-CT Synthesis with RL Post-Training |
| | • CytoSyn: a Foundation Diffusion Model for Histopathology Image Synthesis |
| | • SonoSPADE: Real-Time, Per-Tissue Ultrasound Texture Synthesis |
| | • Enhancing 3D Brain MRI Synthesis with Wavelet Latent Diffusion Models |
| | • MRIComp4Flow: Compression of 3D Brain MRI for Training Multi-Modal Generative Models |
| | • DRIFT: Dual-Distillation Reference-Free One-Step Image Flow for Brain MRI Through-Plane SR |
| | • Uncertainty-Aware 3D Residual Wavelet Diffusion for Ultra Low-Field MRI Super-Resolution |
| | • RECON: Restoration-Guided Conditioning for Thin-Structure-Coherent CT Super-Resolution |
| | Poster Theme 2: Cross-modality translation, harmonization and domain adaptation |
| | • RAFM: Retrieval-Augmented Flow Matching for Unpaired CBCT-to-CT Translation |
| | • A Latent Single-Step Network is Sufficient for Accurate CBCT-CT Translation |
| | • Compositional Cross-Modality Translation via Whole-Volume Multitask Latent Flow Matching |
| | • Synthesizing CT-based Functional Lung Ventilation Map |
| | • nnDiffusion: A Standardized 3D Diffusion Framework for Medical Image Synthesis |
| | • LoRCA: LoRA Cycle Adaptation for Histology to HiP-CT Translation with DINOv3 |
| | • Relative Loss Balancing for High-Fidelity Synthetic CT Generation in the Abdomen |
| | • Any-to-One CT Kernel Conversion without Source-Kernel Data |
| | • Sample Structure, Refine Contrast: Zero-Shot MR Image Harmonization |
| | • SymmAdapt: Symmetrical Flow Matching for Source-Free Domain Adaptation |
| | Poster Theme 3: Synthetic data for downstream tasks |
| | • OTLesMix: Wasserstein Barycenter and Optimal Transport Map for Synthetic Lesion Generation |
| | • Synthetic training for long-tail haemorrhagic lesion segmentation in data-scarce settings |
| | • Realistic Synthetic Data for Annotation-Free Pretraining in Liver Vasculature Segmentation |
| | • AxonSynth: Domain-Randomized Synthetic Data for Zero-Shot 3D Axon Segmentation |
| | • Synthetic Data Augmentation via Stable Diffusion for Polyp Characterisation |
| | • Simulating the Radiological Appearance of Focal Cortical Dysplasia in MRI |
| | • Virtual Patients, Real Gains: Simulated CT from Digital Twins for Lung Nodule Analysis |
| | • From Undersampled to Diagnostic: Flow-Translated Embeddings for Knee Pathology Classification |
| | Poster Theme 4: Longitudinal modelling and validation of synthetic images |
| | • Delta-Diffusion: Modeling Longitudinal Brain Amyloid-PET Trajectories |
| | • Regulate, Modulate, Differentiate: Towards Modelling Subtle Changes in Longitudinal MS MRI |
| | • Reverse Spatio-Temporal Disease Progression Modelling |
| | • Discovering Subtypes of Neurodegenerative Progression with a Connectome-Constrained Dynamic Model |
| | • DisMorph: learning to disentangle technical distortions from true biological change |
| | • Beyond Visual Realism: The Neuro-Fidelity Index for Validating Geometric Integrity |
| | • WAND-CXR: A Morphometric Wasserstein Metric for Evaluating Anatomical Plausibility |
| | • Does FLAIR super-resolution erase or hallucinate small white-matter lesions? |
| 16:50 - 17:00 | 10 min | Awards, sponsors, and closing |
