SUPER Learning: A Supervised-Unsupervised Framework for Low-Dose CT Image Reconstruction

TL;DR

This paper introduces SUPER, a hybrid framework combining supervised deep learning and unsupervised transform learning for low-dose CT image reconstruction, achieving superior results with fewer iterations.

Contribution

The paper presents a novel SUPER framework that integrates supervised and unsupervised learning for improved low-dose CT reconstruction, leveraging the strengths of both approaches.

Findings

SUPER outperforms individual supervised and unsupervised methods.

Fewer iterations are needed for convergence with SUPER.

SUPER achieves significant improvements in image quality.

Abstract

Recent years have witnessed growing interest in machine learning-based models and techniques for low-dose X-ray CT (LDCT) imaging tasks. The methods can typically be categorized into supervised learning methods and unsupervised or model-based learning methods. Supervised learning methods have recently shown success in image restoration tasks. However, they often rely on large training sets. Model-based learning methods such as dictionary or transform learning do not require large or paired training sets and often have good generalization properties, since they learn general properties of CT image sets. Recent works have shown the promising reconstruction performance of methods such as PWLS-ULTRA that rely on clustering the underlying (reconstructed) image patches into a learned union of transforms. In this paper, we propose a new Supervised-UnsuPERvised (SUPER) reconstruction framework for LDCT image reconstruction that combines the benefits of supervised learning methods and (unsupervised) transform learning-based methods such as PWLS-ULTRA that involve highly image-adaptive clustering. The SUPER model consists of several layers, each of which includes a deep network learned in a supervised manner and an unsupervised iterative method that involves image-adaptive components. The SUPER reconstruction algorithms are learned in a greedy manner from training data. The proposed SUPER learning methods dramatically outperform both the constituent supervised learning-based networks and iterative algorithms for LDCT, and use much fewer iterations in the iterative reconstruction modules.