To what extent can Plug-and-Play methods outperform neural networks alone in low-dose CT reconstruction

TL;DR

This study compares Plug-and-Play (PnP) methods with deep learning in low-dose CT reconstruction, showing PnP's advantages in preserving image texture and improving segmentation accuracy despite slightly lower MSE and PSNR.

Contribution

The paper introduces an improved PnP framework with clinical segmentation metrics, demonstrating its superiority in texture preservation and segmentation tasks over pure deep learning methods.

Findings

PnP images better match the power spectrum of full-dose images.

PnP outperforms DL in airway segmentation accuracy.

PnP preserves image texture more effectively.

Abstract

The Plug-and-Play (PnP) framework was recently introduced for low-dose CT reconstruction to leverage the interpretability and the flexibility of model-based methods to incorporate various plugins, such as trained deep learning (DL) neural networks. However, the benefits of PnP vs. state-of-the-art DL methods have not been clearly demonstrated. In this work, we proposed an improved PnP framework to address the previous limitations and develop clinical-relevant segmentation metrics for quantitative result assessment. Compared with the DL alone methods, our proposed PnP framework was slightly inferior in MSE and PSNR. However, the power spectrum of the resulting images better matched that of full-dose images than that of DL denoised images. The resulting images supported higher accuracy in airway segmentation than DL denoised images for all the ten patients in the test set, more substantially on the airways with a cross-section smaller than 0.61cm$^2$, and outperformed the DL denoised images for 45 out of 50 lung lobes in lobar segmentation. Our PnP method proved to be significantly better at preserving the image texture, which translated to task-specific benefits in automated structure segmentation and detection.