Combining Deep Learning and Adaptive Sparse Modeling for Low-dose CT Reconstruction

TL;DR

This paper introduces a hybrid deep learning and sparse modeling framework for low-dose CT reconstruction that combines neural networks with traditional priors in a cascaded fixed-point iteration, improving image quality with limited training data.

Contribution

It proposes a novel hybrid supervised-unsupervised learning framework integrating neural networks and sparse priors for CT reconstruction, demonstrating effectiveness with limited data.

Findings

Outperforms recent reconstruction methods in low-dose CT tasks.

Effectively combines neural networks with sparse priors in a cascaded architecture.

Shows promising results on NIH AAPM Mayo Clinic dataset.

Abstract

Traditional model-based image reconstruction (MBIR) methods combine forward and noise models with simple object priors. Recent application of deep learning methods for image reconstruction provides a successful data-driven approach to addressing the challenges when reconstructing images with measurement undersampling or various types of noise. In this work, we propose a hybrid supervised-unsupervised learning framework for X-ray computed tomography (CT) image reconstruction. The proposed learning formulation leverages both sparsity or unsupervised learning-based priors and neural network reconstructors to simulate a fixed-point iteration process. Each proposed trained block consists of a deterministic MBIR solver and a neural network. The information flows in parallel through these two reconstructors and is then optimally combined, and multiple such blocks are cascaded to form a reconstruction pipeline. We demonstrate the efficacy of this learned hybrid model for low-dose CT image reconstruction with limited training data, where we use the NIH AAPM Mayo Clinic Low Dose CT Grand Challenge dataset for training and testing. In our experiments, we study combinations of supervised deep network reconstructors and sparse representations-based (unsupervised) learned or analytical priors. Our results demonstrate the promising performance of the proposed framework compared to recent reconstruction methods.