Self-Supervised Dynamic CT Perfusion Image Denoising With Deep Neural Networks

Dufan Wu, Hui Ren, Quanzheng Li

Introduction

Dynamic Computed Tomography Perfusion (CTP) is a cornerstone in the diagnosis of acute ischemic strokes, providing critical maps of cerebral blood flow by tracking a contrast agent through the brain. However, the repeated scanning required for these temporal maps exposes patients to significant radiation. While reducing the radiation dose is desirable, low-dose CT imaging introduces substantial "salt-and-pepper" noise and artifacts. These distortions can degrade the quality of hemodynamic maps, potentially leading to misdiagnosis. Traditional denoising methods often blur structural details, and standard deep learning approaches typically require high-dose "ground truth" images, which are ethically and logistically difficult to obtain in clinical practice.

Methods

This research introduces a self-supervised deep learning framework that eliminates the need for clean reference scans by adapting the Noise2Noise principle for temporal medical data. The core strategy leverages the high correlation between adjacent video frames in a CTP sequence.

Self-Supervised Temporal Mapping

Instead of training a network to map a noisy image to a clean one, the model is trained to map a specific frame $x(t)$ to an estimation derived from its temporal neighbors, $x(t-1)$ and $x(t+1)$. Because the noise in these frames is independent while the underlying anatomy is consistent, the network learns to extract the common signal.

Overview of the self-supervised denoising workflow, including the UNet architecture and deconvolution process.

Technical Refinements

To handle the rapid intensity changes during contrast agent transit, the authors implemented several key features:

  • Linear Correction: A correction factor ($\kappa$) is applied to neighbors to better estimate the current frame's intensity, preventing bias during peak contrast flow.
  • Bias Compensation Loss: A specific loss term ensures that the low-frequency structural components of the denoised image remain consistent with the original noisy input, preventing over-smoothing.
  • Efficient Backbone: The system utilizes a 2D UNet architecture, ensuring rapid inference times suitable for emergency clinical environments.

Datasets and Evaluation

The model was validated using two distinct datasets:

  1. Simulation Data: Open-source phantoms were used to create ground-truth benchmarks for infarct cores and penumbra areas, allowing for precise quantitative error measurement.
  2. Real-World Data: The model was tested on clinical scans from 20 patients in the 2018 ISLES challenge, evaluating its performance against actual clinical noise and artifacts.

Results

In simulation trials, the proposed self-supervised method significantly outperformed conventional filters such as Gaussian, TIPS, and TTV. Notably, it achieved performance levels nearly identical to supervised models that had access to clean ground-truth data.

Quantitative comparison of CBF RMSE across different noise levels (N0), showing the proposed method (Noise2Noise) outperforming traditional filters.

On the real-world ISLES dataset, the self-supervised model achieved a Contrast-to-Noise Ratio (CNR) of 3.29, surpassing both the supervised model (2.57) and traditional filtering techniques. Furthermore, the model is computationally efficient, processing a standard CTP slice in approximately 1.5 seconds on a GPU, which is vital for time-sensitive stroke interventions.

Discussion and Conclusion

The "neighbor as label" strategy effectively bypasses the need for high-dose training data by utilizing the temporal redundancy inherent in dynamic imaging. By training directly on real clinical data, the model avoids the "domain shift" issues common in supervised models trained on synthetic data.

While the model assumes zero-mean noise and is sensitive to extreme patient motion, it represents a significant step toward safer, low-dose diagnostic imaging. Future work may involve extending this framework to other dynamic modalities, such as myocardial CT perfusion or dynamic PET scans, and incorporating recurrent neural networks to leverage longer temporal sequences.

Summary updated

Abstract

Dynamic computed tomography perfusion (CTP) imaging is a promising approach for acute ischemic stroke diagnosis and evaluation. Hemodynamic parametric maps of cerebral parenchyma are calculated from repeated CT scans of the first pass of iodinated contrast through the brain. It is necessary to reduce the dose of CTP for routine applications due to the high radiation exposure from the repeated scans, where image denoising is necessary to achieve a reliable diagnosis. In this article, we proposed a self-supervised deep learning method for CTP denoising, which did not require any high-dose reference images for training. The network was trained by mapping each frame of CTP to an estimation from its adjacent frames. Because the noise in the source and target was independent, this approach could effectively remove the noise. Being free from high-dose training images granted the proposed method easier adaptation to different scanning protocols. The method was validated on both simulation and a public real dataset. The proposed method achieved improved image quality compared to conventional denoising methods. On the real data, the proposed method also had improved spatial resolution and contrast-to-noise ratio compared to supervised learning which was trained on the simulation data.
BibTeX
@article{wu2020self,
  author = {Dufan Wu and Hui Ren and Quanzheng Li},
  title = {{Self-Supervised Dynamic CT Perfusion Image Denoising With Deep Neural Networks}},
  journal = {IEEE Transactions on Radiation and Plasma Medical Sciences},
  year = {2020},
  doi = {10.1109/trpms.2020.2996566},
}
Figure