Unsupervised Physics-Informed Deep Learning for Dual-Energy CT Material Decomposition

TL;DR

This paper introduces a physics-informed deep learning framework for dual-energy CT material decomposition that improves accuracy and efficiency without needing ground-truth labels, validated on a public challenge dataset.

Contribution

The novel approach integrates a polychromatic forward model into training, enabling unsupervised learning for DECT material decomposition with superior performance.

Findings

Achieved lowest RMSE in the projection domain compared to state-of-the-art methods.

Outperformed conventional methods in RMSE and SSIM for virtual monoenergetic images.

Validated on the AAPM DL-Spectral CT Challenge dataset with promising results.

Abstract

Dual-energy computed tomography (DECT) enables material-specific imaging through acquisitions at two different X-ray energy spectra. Material decomposition from DECT data is an ill-posed inverse problem that is highly sensitive to noise amplification. Conventional methods face challenges regarding accuracy and computational efficiency. We present a novel physics-informed deep learning (DL) framework for DECT material decomposition that eliminates the requirement for ground-truth material images during training. Our approach incorporates a polychromatic forward model into the training pipeline, enabling the network to learn the decomposition mapping by minimizing discrepancies in the projection domain. We validate our method on the AAPM DL-Spectral CT Challenge dataset, comparing performance against three state-of-the-art methods. In the projection domain, our method achieves the lowest root mean squared error (RMSE) across test datasets. For virtual monoenergetic images (VMIs) at 30 keV, 50 keV, and 70 keV, the approach consistently outperforms all conventional methods in both RMSE and structural similarity index (SSIM). These results demonstrate the potential of DL for accurate material decomposition in DECT without requiring labeled training data.