Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Zilong Li, Dongyang Li, Chenglong Ma, Zhan Feng, Dakai Jin, Junping Zhang, Hao Luo, Fan Wang, Hongming Shan

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.

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

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.

Paper Structure

This paper contains 33 sections, 8 equations, 8 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Virtual Contrast Enhancement
  4. Volumetric Latent Diffusion Models
  5. Method
  6. Overview of Phasor
  7. Anatomy-Routed Mixture-of-Experts (AR-MoE)
  8. Anatomy router.
  9. Organ-specific expert.
  10. Intensity-Phase Aware Representation Alignment (IP-REPA)
  11. Intensity-based weighting.
  12. Intensity-aware alignment.
  13. Phase-aware alignment.
  14. Objective Function
  15. Result
  16. ...and 18 more sections

Figures (8)

  • Figure 1: Overview of Phasor, which takes NCCT as input and synthesizes CECT. (a) IP-REPA aligns DiT features with representations extracted from a teacher encoder during training. (b) TotalSegmentor provides organ-wise anatomy masks. (c) AR-MoE routes tokens to specialized experts based on the anatomy masks.
  • Figure 2: Quantitative comparison of NCCT-to-CECT synthesis on the (a) VinDr-Multiphase and (b) WAW-TRACE datasets. "Prec." denotes the precision score.
  • Figure 3: Qualitative comparison of different methods on the VinDr-Multiphase and WAW-TRACE dataset. The display window is [-160, 240] HU.
  • Figure 4: Qualitative comparison of different methods on the Abdomen dataset. The display window is [-160, 240] HU.
  • Figure 5: 3D visualization of the subtraction volume between the synthesized CECT and the NCCT. Zoom in for better view.
  • ...and 3 more figures