Image-domain material decomposition for dual-energy CT using unsupervised learning with data-fidelity loss Journal Article


Authors: Peng, J.; Chang, C. W.; Xie, H.; Qiu, R. L. J.; Roper, J.; Wang, T.; Ghavidel, B.; Tang, X.; Yang, X.
Article Title: Image-domain material decomposition for dual-energy CT using unsupervised learning with data-fidelity loss
Abstract: Background: Dual-energy computed tomography (DECT) and material decomposition play vital roles in quantitative medical imaging. However, the decomposition process may suffer from significant noise amplification, leading to severely degraded image signal-to-noise ratios (SNRs). While existing iterative algorithms perform noise suppression using different image priors, these heuristic image priors cannot accurately represent the features of the target image manifold. Although deep learning-based decomposition methods have been reported, these methods are in the supervised-learning framework requiring paired data for training, which is not readily available in clinical settings. Purpose: This work aims to develop an unsupervised-learning framework with data-measurement consistency for image-domain material decomposition in DECT. Methods: The proposed framework combines iterative decomposition and deep learning-based image prior in a generative adversarial network (GAN) architecture. In the generator module, a data-fidelity loss is introduced to enforce the measurement consistency in material decomposition. In the discriminator module, the discriminator is trained to differentiate the low-noise material-specific images from the high-noise images. In this scheme, paired images of DECT and ground-truth material-specific images are not required for the model training. Once trained, the generator can perform image-domain material decomposition with noise suppression in a single step. Results: In the simulation studies of head and lung digital phantoms, the proposed method reduced the standard deviation (SD) in decomposed images by 97% and 91% from the values in direct inversion results. It also generated decomposed images with structural similarity index measures (SSIMs) greater than 0.95 against the ground truth. In the clinical head and lung patient studies, the proposed method suppressed the SD by 95% and 93% compared to the decomposed images of matrix inversion. Conclusions: Since the invention of DECT, noise amplification during material decomposition has been one of the biggest challenges, impeding its quantitative use in clinical practice. The proposed method performs accurate material decomposition with efficient noise suppression. Furthermore, the proposed method is within an unsupervised-learning framework, which does not require paired data for model training and resolves the issue of lack of ground-truth data in clinical scenarios. © 2024 American Association of Physicists in Medicine.
Keywords: unsupervised learning; signal noise ratio; tomography, x-ray computed; computerized tomography; medical imaging; image processing, computer-assisted; image processing; biological organs; ground truth; signal to noise ratio; procedures; heuristic algorithms; learning systems; signal-to-noise ratio; learning frameworks; humans; human; iterative methods; noise suppression; x-ray computed tomography; image denoising; deep learning; unsupervised machine learning; dect; gan; generative adversarial networks; data fidelity; image domain; material decomposition; dual-energy computed tomography; image priors; model training; noise amplification
Journal Title: Medical Physics
Volume: 51
Issue: 9
ISSN: 0094-2405
Publisher: American Association of Physicists in Medicine  
Date Published: 2024-09-01
Start Page: 6185
End Page: 6195
Language: English
DOI: 10.1002/mp.17255
PUBMED: 38865687
PROVIDER: scopus
PMCID: PMC11489026
DOI/URL:
Notes: The MSK Cancer Center Support Grant (P30 CA008748) is acknowledge in the PDF -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Tonghe Wang
    51 Wang
  2. Huiqiao Xie
    9 Xie