Journal article
Iterative material decomposition for spectral CT using self-supervised Noise2Noise prior
Physics in medicine & biology, Vol.66(15), p.155013
08/07/2021
DOI: 10.1088/1361-6560/ac0afd
PMID: 34126602
Abstract
Compared to conventional computed tomography (CT), spectral CT can provide the capability of material decomposition, which can be used in many clinical diagnosis applications. However, the decomposed images can be very noisy due to the dose limit in CT scanning and the noise magnification of the material decomposition process. To alleviate this situation, we proposed an iterative one-step inversion material decomposition algorithm with a Noise2Noise prior. The algorithm estimated material images directly from projection data and used a Noise2Noise prior for denoising. In contrast to supervised deep learning methods, the designed Noise2Noise prior was built based on self-supervised learning and did not need external data for training. In our method, the data consistency term and the Noise2Noise network were alternatively optimized in the iterative framework, respectively, using a separable quadratic surrogate (SQS) and the Adam algorithm. The proposed iterative algorithm was validated and compared to other methods on simulated spectral CT data, preclinical photon-counting CT data and clinical dual-energy CT data. Quantitative analysis showed that our proposed method performs promisingly on noise suppression and structure detail recovery.
Details
- Title: Subtitle
- Iterative material decomposition for spectral CT using self-supervised Noise2Noise prior
- Creators
- Wei Fang - Tsinghua UniversityDufan Wu - Massachusetts General HospitalKyungsang Kim - Massachusetts General HospitalMannudeep K. Kalra - Harvard UniversityRamandeep Singh - Massachusetts General HospitalLiang Li - Tsinghua UniversityQuanzheng Li - Massachusetts General Hospital
- Resource Type
- Journal article
- Publication Details
- Physics in medicine & biology, Vol.66(15), p.155013
- Publisher
- Iop Publishing Ltd
- DOI
- 10.1088/1361-6560/ac0afd
- PMID
- 34126602
- ISSN
- 0031-9155
- eISSN
- 1361-6560
- Number of pages
- 17
- Grant note
- 2018YFC0115502 / National Key R&D Program of China 11775124 / NSFC; National Natural Science Foundation of China (NSFC)
- Language
- English
- Date published
- 08/07/2021
- Academic Unit
- Radiology
- Record Identifier
- 9984697729802771
Metrics
2 Record Views