JSover: Joint Spectrum Estimation and Multi-Material Decomposition from Single-Energy CT Projections

TL;DR

JSover introduces a novel one-step framework for multi-material decomposition from single-energy CT data, jointly estimating material compositions and energy spectrum, thus reducing artifacts and improving accuracy over traditional two-step methods.

Contribution

The paper presents JSover, a new physics-informed, joint reconstruction method using implicit neural representations for accurate, efficient multi-material decomposition from single-energy CT projections.

Findings

JSover outperforms existing methods in accuracy on simulated and real data.

JSover achieves higher computational efficiency compared to traditional approaches.

Incorporating spectral priors and neural representations enhances decomposition quality.

Abstract

Multi-material decomposition (MMD) enables quantitative reconstruction of tissue compositions in the human body, supporting a wide range of clinical applications. However, traditional MMD typically requires spectral CT scanners and pre-measured X-ray energy spectra, significantly limiting clinical applicability. To this end, various methods have been developed to perform MMD using conventional (i.e., single-energy, SE) CT systems, commonly referred to as SEMMD. Despite promising progress, most SEMMD methods follow a two-step image decomposition pipeline, which first reconstructs monochromatic CT images using algorithms such as FBP, and then performs decomposition on these images. The initial reconstruction step, however, neglects the energy-dependent attenuation of human tissues, introducing severe nonlinear beam hardening artifacts and noise into the subsequent decomposition. This paper proposes JSover, a fundamentally reformulated one-step SEMMD framework that jointly reconstructs multi-material compositions and estimates the energy spectrum directly from SECT projections. By explicitly incorporating physics-informed spectral priors into the SEMMD process, JSover accurately simulates a virtual spectral CT system from SE acquisitions, thereby improving the reliability and accuracy of decomposition. Furthermore, we introduce implicit neural representation (INR) as an unsupervised deep learning solver for representing the underlying material maps. The inductive bias of INR toward continuous image patterns constrains the solution space and further enhances estimation quality. Extensive experiments on both simulated and real CT datasets show that JSover outperforms state-of-the-art SEMMD methods in accuracy and computational efficiency.