MedForj: An open, large-scale foundational generative prior for high-resolution 3D brain MRI

arXiv:2510.26834 · eess.IV, cs.AI · Submitted 2025-10-29 · Read on arXiv

eess.IV, cs.AI

Submitted: 2025-10-29

Updated: 2026-10-05

Code: https://github.com/piksl-research/medforj

Terminology

• Diffusion Model — 1× in this paper · explained in 9 episodes
• Frechet Inception Distance — 1× in this paper
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes

Sources

• Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision
• Foundation Models for Biomedical Image Segmentation: A Survey
• Foundation Models in Medical Imaging: A Review and Outlook
• Diffusion Posterior Sampling for General Noisy Inverse Problems
• High-Resolution Image Synthesis with Latent Diffusion Models
• Back to Basics: Let Denoising Generative Models Denoise
• Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency
• MONAI: An open-source framework for deep learning in healthcare

Related papers

• PanoDiff-SR: Synthesizing Dental Panoramic Radiographs using Diffusion and Super-resolution
• Revisiting Integration of Image and Metadata for DICOM Series Classification: Cross-Attention and Dictionary Learning
• VesselSDF: Distance Field Priors for Vascular Network Reconstruction
• cSVR: Convolutional Slice-to-Volume Reconstruction
• NAIMA: Semantics Aware RGB Guided Depth Super-Resolution
• AneumoBench: A Source-Linked Benchmark for Synthetic-Geometry Transfer in Aneurysm CFD