ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis

TL;DR

ViCTr is a novel two-stage framework that enables high-fidelity, pathology-aware medical image synthesis with efficient one-step sampling, significantly improving realism and control over pathological features.

Contribution

Introduces ViCTr, combining rectified flow and Tweedie-corrected diffusion for pathology-aware image synthesis with reduced inference steps and fine-grained severity control.

Findings

Achieves state-of-the-art MFID of 17.01 for cirrhosis synthesis

Improves nnUNet segmentation by +3.8% mDSC with data augmentation

Radiologists find generated images clinically indistinguishable from real scans

Abstract

Synthesizing medical images remains challenging due to limited annotated pathological data, modality domain gaps, and the complexity of representing diffuse pathologies such as liver cirrhosis. Existing methods often struggle to maintain anatomical fidelity while accurately modeling pathological features, frequently relying on priors derived from natural images or inefficient multi-step sampling. In this work, we introduce ViCTr (Vital Consistency Transfer), a novel two-stage framework that combines a rectified flow trajectory with a Tweedie-corrected diffusion process to achieve high-fidelity, pathology-aware image synthesis. First, we pretrain ViCTr on the ATLAS-8k dataset using Elastic Weight Consolidation (EWC) to preserve critical anatomical structures. We then fine-tune the model adversarially with Low-Rank Adaptation (LoRA) modules for precise control over pathology severity. By reformulating Tweedie's formula within a linear trajectory framework, ViCTr supports one-step sampling, reducing inference from 50 steps to just 4, without sacrificing anatomical realism. We evaluate ViCTr on BTCV (CT), AMOS (MRI), and CirrMRI600+ (cirrhosis) datasets. Results demonstrate state-of-the-art performance, achieving a Medical Frechet Inception Distance (MFID) of 17.01 for cirrhosis synthesis 28% lower than existing approaches and improving nnUNet segmentation by +3.8% mDSC when used for data augmentation. Radiologist reviews indicate that ViCTr-generated liver cirrhosis MRIs are clinically indistinguishable from real scans. To our knowledge, ViCTr is the first method to provide fine-grained, pathology-aware MRI synthesis with graded severity control, closing a critical gap in AI-driven medical imaging research.