Super-Energy-Resolution Material Decomposition for Spectral Photon-Counting CT Using Pixel-Wise Learning
Spectral photon-counting CT offers novel potentialities to achieve quantitative decomposition of material components, in comparison with traditional energy-integrating CT or dual-energy CT. Nonetheless, achieving accurate material decomposition, especially for low-concentration materials, is still e...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9645431/ |
| _version_ | 1798034813151608832 |
|---|---|
| author | Bingqing Xie Yuemin Zhu Pei Niu Ting Su Feng Yang Lihui Wang Pierre-Antoine Rodesch Loic Boussel Philippe Douek Philippe Duvauchelle |
| author_facet | Bingqing Xie Yuemin Zhu Pei Niu Ting Su Feng Yang Lihui Wang Pierre-Antoine Rodesch Loic Boussel Philippe Douek Philippe Duvauchelle |
| author_sort | Bingqing Xie |
| collection | DOAJ |
| description | Spectral photon-counting CT offers novel potentialities to achieve quantitative decomposition of material components, in comparison with traditional energy-integrating CT or dual-energy CT. Nonetheless, achieving accurate material decomposition, especially for low-concentration materials, is still extremely challenging for current sCT, due to restricted energy resolution stemming from the trade-off between the number of energy bins and undesired factors such as quantum noise. We propose to improve material decomposition by introducing the notion of super-energy-resolution in sCT. The super-energy-resolution material decomposition consists in learning the relationship between simulation and physical phantoms in image domain. To this end, a coupled dictionary learning method is utilized to learn such relationship in a pixel-wise way. The results on both physical phantoms and in vivo data showed that for the same decomposition method using lasso regularization, the proposed super-energy-resolution method achieves much higher decomposition accuracy and detection ability in contrast to traditional image-domain decomposition method using L1-norm regularization. |
| first_indexed | 2024-04-11T20:48:44Z |
| format | Article |
| id | doaj.art-e26706fd73094786b0d9bba9d1ed8b40 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T20:48:44Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e26706fd73094786b0d9bba9d1ed8b402022-12-22T04:03:55ZengIEEEIEEE Access2169-35362021-01-01916848516849510.1109/ACCESS.2021.31346369645431Super-Energy-Resolution Material Decomposition for Spectral Photon-Counting CT Using Pixel-Wise LearningBingqing Xie0https://orcid.org/0000-0001-9573-7424Yuemin Zhu1Pei Niu2https://orcid.org/0000-0002-3738-404XTing Su3Feng Yang4https://orcid.org/0000-0002-8334-7450Lihui Wang5https://orcid.org/0000-0002-3558-5112Pierre-Antoine Rodesch6https://orcid.org/0000-0001-6199-0042Loic Boussel7Philippe Douek8Philippe Duvauchelle9Centre National de la Recherche Scientifique (CNRS), CREATIS UMR 5220, U1294, INSA Lyon, Inserm, University of Lyon, Lyon, FranceCentre National de la Recherche Scientifique (CNRS), CREATIS UMR 5220, U1294, INSA Lyon, Inserm, University of Lyon, Lyon, FranceCentre National de la Recherche Scientifique (CNRS), CREATIS UMR 5220, U1294, INSA Lyon, Inserm, University of Lyon, Lyon, FranceResearch Center for Medical Artificial Intelligence, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaLister Hill National Center for Biomedical Communications, National Library of Medicine (NLM), National Institutes of Health (NIH), Bethesda, MD, USAKey Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, School of Computer Science and Technology, Guizhou University, Guiyang, ChinaRadiology Department, Hospices Civils de Lyon, Inserm, INSA-Lyon, CREATIS, CNRS, University of Lyon, Lyon, FranceRadiology Department, Hospices Civils de Lyon, Inserm, INSA-Lyon, CREATIS, CNRS, University of Lyon, Lyon, FranceRadiology Department, Hospices Civils de Lyon, Inserm, INSA-Lyon, CREATIS, CNRS, University of Lyon, Lyon, FranceLaboratoire Vibrations Acoustique (LVA), INSA Lyon, University of Lyon, Villeurbanne, FranceSpectral photon-counting CT offers novel potentialities to achieve quantitative decomposition of material components, in comparison with traditional energy-integrating CT or dual-energy CT. Nonetheless, achieving accurate material decomposition, especially for low-concentration materials, is still extremely challenging for current sCT, due to restricted energy resolution stemming from the trade-off between the number of energy bins and undesired factors such as quantum noise. We propose to improve material decomposition by introducing the notion of super-energy-resolution in sCT. The super-energy-resolution material decomposition consists in learning the relationship between simulation and physical phantoms in image domain. To this end, a coupled dictionary learning method is utilized to learn such relationship in a pixel-wise way. The results on both physical phantoms and in vivo data showed that for the same decomposition method using lasso regularization, the proposed super-energy-resolution method achieves much higher decomposition accuracy and detection ability in contrast to traditional image-domain decomposition method using L1-norm regularization.https://ieeexplore.ieee.org/document/9645431/X-ray CTmaterial decompositionphoton-counting detectorsuper energy resolution |
| spellingShingle | Bingqing Xie Yuemin Zhu Pei Niu Ting Su Feng Yang Lihui Wang Pierre-Antoine Rodesch Loic Boussel Philippe Douek Philippe Duvauchelle Super-Energy-Resolution Material Decomposition for Spectral Photon-Counting CT Using Pixel-Wise Learning IEEE Access X-ray CT material decomposition photon-counting detector super energy resolution |
| title | Super-Energy-Resolution Material Decomposition for Spectral Photon-Counting CT Using Pixel-Wise Learning |
| title_full | Super-Energy-Resolution Material Decomposition for Spectral Photon-Counting CT Using Pixel-Wise Learning |
| title_fullStr | Super-Energy-Resolution Material Decomposition for Spectral Photon-Counting CT Using Pixel-Wise Learning |
| title_full_unstemmed | Super-Energy-Resolution Material Decomposition for Spectral Photon-Counting CT Using Pixel-Wise Learning |
| title_short | Super-Energy-Resolution Material Decomposition for Spectral Photon-Counting CT Using Pixel-Wise Learning |
| title_sort | super energy resolution material decomposition for spectral photon counting ct using pixel wise learning |
| topic | X-ray CT material decomposition photon-counting detector super energy resolution |
| url | https://ieeexplore.ieee.org/document/9645431/ |
| work_keys_str_mv | AT bingqingxie superenergyresolutionmaterialdecompositionforspectralphotoncountingctusingpixelwiselearning AT yueminzhu superenergyresolutionmaterialdecompositionforspectralphotoncountingctusingpixelwiselearning AT peiniu superenergyresolutionmaterialdecompositionforspectralphotoncountingctusingpixelwiselearning AT tingsu superenergyresolutionmaterialdecompositionforspectralphotoncountingctusingpixelwiselearning AT fengyang superenergyresolutionmaterialdecompositionforspectralphotoncountingctusingpixelwiselearning AT lihuiwang superenergyresolutionmaterialdecompositionforspectralphotoncountingctusingpixelwiselearning AT pierreantoinerodesch superenergyresolutionmaterialdecompositionforspectralphotoncountingctusingpixelwiselearning AT loicboussel superenergyresolutionmaterialdecompositionforspectralphotoncountingctusingpixelwiselearning AT philippedouek superenergyresolutionmaterialdecompositionforspectralphotoncountingctusingpixelwiselearning AT philippeduvauchelle superenergyresolutionmaterialdecompositionforspectralphotoncountingctusingpixelwiselearning |