Manifold Reconstruction of Differences: A Model-Based Iterative Statistical Estimation Algorithm with a Data-Driven Prior

TL;DR

This paper introduces MRoD, an iterative CT reconstruction algorithm that combines manifold learning with physical models, enabling noise reduction and patient-specific feature extraction in low-dose CT imaging.

Contribution

The paper presents a novel manifold-based iterative reconstruction method that separates typical features from patient-specific differences, improving noise reduction and feature detection.

Findings

Effective noise reduction with less bias than traditional methods

Ability to isolate patient-specific differences from typical features

Demonstrated success in simulated lung data reconstruction

Abstract

Manifold learning using deep neural networks been shown to be an effective tool for building sophisticated prior image models that can be applied to noise reduction in low-dose CT. We propose a new iterative CT reconstruction algorithm, called Manifold Reconstruction of Differences (MRoD), which combines physical and statistical models with a data-driven prior based on manifold learning. The MRoD algorithm involves estimating a manifold component, approximating common features among all patients, and the difference component which has the freedom to fit the measured data. By applying a sparsity-promoting penalty to the difference image rather than a hard constraint to the manifold, the MRoD algorithm is able to reconstruct features which are not present in the training data. The difference component itself may be independently useful. While the manifold captures typical patient features (e.g. healthy anatomy), the difference image highlights patient-specific elements (e.g. pathology). In this work, we present a description of an optimization framework which combines trained manifold-based modules with physical modules. We present a simulation study using anthropomorphic lung data showing that the MRoD algorithm can both isolate differences between a particular patient and the typical distribution, but also provide significant noise reduction with less bias than a typical penalized likelihood estimator in composite manifold plus difference reconstructions.