L Wang1,2, Y Wang1,2, Z Bian1,2, J Ma1,2, J Huang1,2. 1. School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China. 2. Guangzhou Key Laboratory of Medical Radiation Imaging and Detection Technology, Guangzhou 510515, China.
Abstract
OBJECTIVE: To propose a nonlocal spectral similarity-induced material decomposition network (NSSD-Net) to reduce the correlation noise in the low-dose spectral CT decomposed images. METHODS: We first built a model-driven iterative decomposition model for dual-energy CT, optimized the objective function solving process using the iterative shrinking threshold algorithm (ISTA), and cast the ISTA decomposition model into the deep learning network. We then developed a novel cost function based on the nonlocal spectral similarity to constrain the training process. To validate the decomposition performance, we established a material decomposition dataset by real patient dual-energy CT data. The NSSD-Net was compared with two traditional model-driven material decomposition methods, one data-based material decomposition method and one data-model coupling-driven material decomposition supervised learning method. RESULTS: The quantitative results showed that compared with the two traditional methods, the NSSD-Net method obtained the highest PNSR values (31.383 and 31.444) and SSIM values (0.970 and 0.963) and the lowest RMSE values (2.901 and 1.633). Compared with the datamodel coupling-driven supervised decomposition method, the NSSD-Net method obtained the highest SSIM values on water and bone decomposed results. The results of subjective image quality assessment by clinical experts showed that the NSSD-Net achieved the highest image quality assessment scores on water and bone basis material (8.625 and 8.250), showing significant differences from the other 4 decomposition methods (P < 0.001). CONCLUSION: The proposed method can achieve high-precision material decomposition and avoid training data quality issues and model unexplainable issues.
OBJECTIVE: To propose a nonlocal spectral similarity-induced material decomposition network (NSSD-Net) to reduce the correlation noise in the low-dose spectral CT decomposed images. METHODS: We first built a model-driven iterative decomposition model for dual-energy CT, optimized the objective function solving process using the iterative shrinking threshold algorithm (ISTA), and cast the ISTA decomposition model into the deep learning network. We then developed a novel cost function based on the nonlocal spectral similarity to constrain the training process. To validate the decomposition performance, we established a material decomposition dataset by real patient dual-energy CT data. The NSSD-Net was compared with two traditional model-driven material decomposition methods, one data-based material decomposition method and one data-model coupling-driven material decomposition supervised learning method. RESULTS: The quantitative results showed that compared with the two traditional methods, the NSSD-Net method obtained the highest PNSR values (31.383 and 31.444) and SSIM values (0.970 and 0.963) and the lowest RMSE values (2.901 and 1.633). Compared with the datamodel coupling-driven supervised decomposition method, the NSSD-Net method obtained the highest SSIM values on water and bone decomposed results. The results of subjective image quality assessment by clinical experts showed that the NSSD-Net achieved the highest image quality assessment scores on water and bone basis material (8.625 and 8.250), showing significant differences from the other 4 decomposition methods (P < 0.001). CONCLUSION: The proposed method can achieve high-precision material decomposition and avoid training data quality issues and model unexplainable issues.
Entities:
Keywords:
deep learning; material decomposition methods; nonlocal spectral; spectral CT
Authors: Nils Große Hokamp; Simon Lennartz; Johannes Salem; Daniel Pinto Dos Santos; Axel Heidenreich; David Maintz; Stefan Haneder Journal: Eur Radiol Date: 2019-11-26 Impact factor: 5.315
Authors: Kai Higashigaito; André Euler; Matthias Eberhard; Thomas G Flohr; Bernhard Schmidt; Hatem Alkadhi Journal: Acad Radiol Date: 2021-08-11 Impact factor: 3.173