PHASOR: Anatomy- and Phase-Consistent Volumetric Diffusion for CT Virtual Contrast Enhancement

2026-04-01

AI Summary

This work addresses the limitations of existing virtual contrast enhancement methods, which often suffer from inconsistent enhancement and structural distortions when synthesizing contrast-enhanced CT from non-contrast CT due to anatomical heterogeneity and spatial misalignment. To overcome these challenges, the authors propose a voxel-wise diffusion framework that models 3D CT volumes as coherent sequences and leverages video diffusion models to improve structural consistency and volumetric fidelity. The approach introduces two key innovations: an Anatomy-Routed Mixture-of-Experts (AR-MoE) module for organ-specific enhancement and an Intensity-Phase-aware Representation Alignment (IP-REPA) module to strengthen contrast signals and mitigate spatial misalignment. Evaluated on three datasets, the method significantly outperforms current state-of-the-art techniques, achieving superior performance in both synthesis quality and enhancement accuracy.

Abstract

Contrast-enhanced computed tomography (CECT) is pivotal for highlighting tissue perfusion and vascularity, yet its clinical ubiquity is impeded by the invasive nature of contrast agents and radiation risks. While virtual contrast enhancement (VCE) offers an alternative to synthesizing CECT from non-contrast CT (NCCT), existing methods struggle with anatomical heterogeneity and spatial misalignment, leading to inconsistent enhancement patterns and incorrect details. This paper introduces PHASOR, a volumetric diffusion framework for high-fidelity CT VCE. By treating CT volumes as coherent sequences, we leverage a video diffusion model to enhance structural coherence and volumetric accuracy. To ensure anatomy-phase consistent synthesis, we introduce two complementary modules. First, anatomy-routed mixture-of-experts (AR-MoE) anchors distinct enhancement patterns to anatomical semantics, with organ-specific memory to capture salient details. Second, intensity-phase aware representation alignment (IP-REPA) highlights intricate contrast signals while mitigating the impact of imperfect spatial alignment. Extensive experiments across three datasets demonstrate that PHASOR significantly outperforms state-of-the-art methods in both synthesis quality and enhancement accuracy.

Problem

• virtual contrast enhancement
• anatomical heterogeneity
• spatial misalignment
• contrast-enhanced CT
• non-contrast CT

Innovation

• volumetric diffusion
• virtual contrast enhancement
• anatomy-phase consistency
• mixture-of-experts
• representation alignment