JCCS-PFGM: A Novel Circle-Supervision Based Poisson Flow Generative Model for Multiphase CECT Progressive Low-Dose Reconstruction with Joint Condition

Rongjun Ge, Yuting He, Cong Xia, Daoqiang Zhang

Abstract

Multiphase contrast-enhanced computed tomography (CECT) scan is clinically significant to demonstrate the anatomy at different phases. In practice, such a multiphase CECT scan inherently takes longer time and deposits much more radiation dose into a patient body than a regular CT scan, and reduction of the radiation dose typically compromise the CECT image quality and its diagnostic value. With Joint Condition and Circle-Supervision, here we propose a novel Poisson Flow Generative Model (JCCS-PFGM) to promote the progressive low-dose reconstruction for multiphase CECT. JCCS-PFGM is characterized by the following three aspects: a progressive low-dose reconstruction scheme, a circle-supervision strategy, and a joint condition mechanism. Our extensive experiments are performed on a clinical dataset consisting of 11436 images. The results show that our JCCS-PFGM achieves promising PSNR up to 46.3dB, SSIM up to 98.5%, and MAE down to 9.67 HU averagely on phases I, II and III, in quantitative evaluations, as well as gains high-quality readable visualizations in qualitative assessments. All of these findings reveal our method a great potential to be adapted for clinical CECT scans at a much-reduced radiation dose.

Introduction

Multiphase Contrast-Enhanced Computed Tomography (CECT) is a cornerstone of modern radiology, used to visualize blood flow and organ function by scanning a patient multiple times (e.g., arterial, venous, and delayed phases) after injecting a contrast agent.

Multiphase CECT scan phases and the noise challenge in low-dose imaging.

The catch? Each additional "phase" adds more ionizing radiation. A triple-phase scan can deposit three times the radiation of a standard CT, increasing long-term cancer risks. While we can lower the dose, doing so typically results in "noisy" images filled with artifacts that make them difficult for radiologists to read. Most existing AI denoising tools treat each phase in isolation, failing to exploit the fact that the patient's anatomy doesn't change between scans—only the contrast distribution does.

Methodology: The JCCS-PFGM Framework

The authors introduce JCCS-PFGM (Joint Condition and Circle-Supervision based Poisson Flow Generative Model). It moves away from standard denoising and toward a sophisticated generative approach based on three pillars:

The JCCS-PFGM framework featuring progressive reconstruction and circle-supervision.
  1. Progressive Reconstruction Scheme: Instead of an even dose distribution, the authors assign a higher dose to the first phase (30%) to establish a clear anatomical "anchor" and progressively lower doses to subsequent phases (15% and 5%).
  2. Poisson Flow Generative Model (PFGM): Unlike popular Diffusion Models that mimic gas moving through a room, PFGM is inspired by electrostatics. It treats image data points as electrical charges on a hyperplane, creating a "Poisson field." This approach is often more robust and computationally efficient for mapping noisy data back to clean images.
  3. Circle-Supervision Strategy: To prevent the model from "hallucinating" details, the authors implement a self-inspection loop. The model predicts a Poisson field, restores an image, perturbs it again, and checks if the new prediction matches the original. This "circle" ensures the model learns the actual underlying structure rather than just generic patterns.
  4. Joint Condition Mechanism: This uses attention-based "cross-fusion" to pull relevant anatomical details from previous phases into the current reconstruction, ensuring that the evolution of the contrast agent is the only thing changing, not the patient's organs.

Key Insights and Results

The study utilized a substantial clinical dataset of 38,496 CECT images from 247 patients. Low-dose versions were generated using a validated photon-counting model that simulates real-world physics like electronic noise and bowtie filters.

The JCCS-PFGM outperformed standard reconstruction (FBP) and state-of-the-art deep learning models (RED-CNN, DDPNet) across all metrics:

  • Quantitative Accuracy: Achieved a Peak Signal-to-Noise Ratio (PSNR) of up to 46.3dB and a Structural Similarity Index (SSIM) of 98.5%.
  • Error Reduction: The Mean Absolute Error (MAE) dropped to 9.67 HU (Hounsfield Units) on average across all phases.
  • Ultra-Low Dose Performance: Even at the 5% dose level (Phase III), the model preserved tiny features like small blood vessels that were completely lost or blurred in competing methods.

Limitations and Future Work

While the simulation model is highly accurate, the framework still needs to be validated on hardware-native low-dose scans where "real-world" artifacts might differ slightly. Additionally, the model assumes the patient hasn't moved significantly between phases. In clinical practice, respiratory motion can occur, which might require integrating a motion-correction step into the joint condition mechanism. Future work could also explore how this model performs on different organ systems (e.g., cardiac vs. abdominal) where contrast dynamics vary significantly.

Summary updated

Abstract

Multiphase contrast-enhanced computed tomography (CECT) scan is clinically significant to demonstrate the anatomy at different phases. But such multiphase scans inherently lead to the accumulation of huge radiation dose for patients, and directly reducing the scanning dose dramatically decrease the readability of the imaging. Therefore, guided with Joint Condition, a novel Circle-Supervision based Poisson Flow Generative Model (JCCS-PFGM) is proposed to promote the progressive low-dose reconstruction for multiphase CECT. JCCS-PFGM is constituted by three special designs: 1) a progressive low-dose reconstruction mechanism to leverages the imaging consistency and radiocontrast evolution along former-latter phases, so that enormously reduces the radiation dose needs and improve the reconstruction effect, even for the latter-phase scanning with extremely low dose; 2) a circle-supervision strategy embedded in PFGM to enhance the refactoring capabilities of normalized poisson field learned from the perturbed space to the specified CT image space, so that boosts the explicit reconstruction for noise reduction; 3) a joint condition to explore correlation between former phases and current phase, so that extracts the complementary information for current noisy CECT and guides the reverse process of diffusion jointly with multiphase condition for structure maintenance. The extensive experiments tested on the clinical dataset composed of 11436 images show that our JCCS-PFGM achieves promising PSNR up to 46.3dB, SSIM up to 98.5%, and MAE down to 9.67 HU averagely on phases I, II and III, in quantitative evaluations, as well as gains high-quality readable visualizations in qualitative assessments. All of these findings reveal our method a great potential in clinical multiphase CECT imaging.
BibTeX
@inproceedings{ge2023jccs,
  author = {Rongjun Ge and Yuting He and Cong Xia and Daoqiang Zhang},
  title = {{JCCS-PFGM: A Novel Circle-Supervision Based Poisson Flow Generative Model for Multiphase CECT Progressive Low-Dose Reconstruction with Joint Condition}},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
  year = {2023},
  doi = {10.48550/arxiv.2306.07824},
}
Figure