Self-supervised denoising of grating-based phase-contrast computed tomography
Abstract In the last decade, grating-based phase-contrast computed tomography (gbPC-CT) has received growing interest. It provides additional information about the refractive index decrement in the sample. This signal shows an increased soft-tissue contrast. However, the resolution dependence of the...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-83517-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559463264256000 |
|---|---|
| author | Sami Wirtensohn Clemens Schmid Daniel Berthe Dominik John Lisa Heck Kirsten Taphorn Silja Flenner Julia Herzen |
| author_facet | Sami Wirtensohn Clemens Schmid Daniel Berthe Dominik John Lisa Heck Kirsten Taphorn Silja Flenner Julia Herzen |
| author_sort | Sami Wirtensohn |
| collection | DOAJ |
| description | Abstract In the last decade, grating-based phase-contrast computed tomography (gbPC-CT) has received growing interest. It provides additional information about the refractive index decrement in the sample. This signal shows an increased soft-tissue contrast. However, the resolution dependence of the signal poses a challenge: its contrast enhancement is overcompensated by the low resolution in low-dose applications such as clinical computed tomography. As a result, the implementation of gbPC-CT is currently tied to a higher dose. To reduce the dose, we introduce the self-supervised deep learning network Noise2Inverse into the field of gbPC-CT. We evaluate the behavior of the Noise2Inverse parameters on the phase-contrast results. Afterward, we compare its results with other denoising methods, namely the Statistical Iterative Reconstruction, Block Matching 3D, and Patchwise Phase Retrieval. In the example of Noise2Inverse, we show that deep learning networks can deliver superior denoising results with respect to the investigated image quality metrics. Their application allows to increase the resolution while maintaining the dose. At higher resolutions, gbPC-CT can naturally deliver higher contrast than conventional absorption-based CT. Therefore, the application of machine learning-based denoisers shifts the dose-normalized image quality in favor of gbPC-CT, bringing it one step closer to medical application. |
| format | Article |
| id | doaj-art-bca06bd5842347c98fe1109670b0fbd0 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-bca06bd5842347c98fe1109670b0fbd02025-01-05T12:28:54ZengNature PortfolioScientific Reports2045-23222024-12-0114111310.1038/s41598-024-83517-xSelf-supervised denoising of grating-based phase-contrast computed tomographySami Wirtensohn0Clemens Schmid1Daniel Berthe2Dominik John3Lisa Heck4Kirsten Taphorn5Silja Flenner6Julia Herzen7Research Group Biomedical Imaging Physics, Department of Physics, TUM School of Natural Sciences, Technical University of MunichChair of Biomedical Physics, Department of Physics, TUM School of Natural Sciences, Technical University of MunichChair of Biomedical Physics, Department of Physics, TUM School of Natural Sciences, Technical University of MunichResearch Group Biomedical Imaging Physics, Department of Physics, TUM School of Natural Sciences, Technical University of MunichChair of Biomedical Physics, Department of Physics, TUM School of Natural Sciences, Technical University of MunichChair of Biomedical Physics, Department of Physics, TUM School of Natural Sciences, Technical University of MunichInstitute of Materials Physics, Helmholtz-Zentrum HereonResearch Group Biomedical Imaging Physics, Department of Physics, TUM School of Natural Sciences, Technical University of MunichAbstract In the last decade, grating-based phase-contrast computed tomography (gbPC-CT) has received growing interest. It provides additional information about the refractive index decrement in the sample. This signal shows an increased soft-tissue contrast. However, the resolution dependence of the signal poses a challenge: its contrast enhancement is overcompensated by the low resolution in low-dose applications such as clinical computed tomography. As a result, the implementation of gbPC-CT is currently tied to a higher dose. To reduce the dose, we introduce the self-supervised deep learning network Noise2Inverse into the field of gbPC-CT. We evaluate the behavior of the Noise2Inverse parameters on the phase-contrast results. Afterward, we compare its results with other denoising methods, namely the Statistical Iterative Reconstruction, Block Matching 3D, and Patchwise Phase Retrieval. In the example of Noise2Inverse, we show that deep learning networks can deliver superior denoising results with respect to the investigated image quality metrics. Their application allows to increase the resolution while maintaining the dose. At higher resolutions, gbPC-CT can naturally deliver higher contrast than conventional absorption-based CT. Therefore, the application of machine learning-based denoisers shifts the dose-normalized image quality in favor of gbPC-CT, bringing it one step closer to medical application.https://doi.org/10.1038/s41598-024-83517-xComputed tomographyX-ray imagingNoise reductionSelf-supervised learningPhase contrast |
| spellingShingle | Sami Wirtensohn Clemens Schmid Daniel Berthe Dominik John Lisa Heck Kirsten Taphorn Silja Flenner Julia Herzen Self-supervised denoising of grating-based phase-contrast computed tomography Scientific Reports Computed tomography X-ray imaging Noise reduction Self-supervised learning Phase contrast |
| title | Self-supervised denoising of grating-based phase-contrast computed tomography |
| title_full | Self-supervised denoising of grating-based phase-contrast computed tomography |
| title_fullStr | Self-supervised denoising of grating-based phase-contrast computed tomography |
| title_full_unstemmed | Self-supervised denoising of grating-based phase-contrast computed tomography |
| title_short | Self-supervised denoising of grating-based phase-contrast computed tomography |
| title_sort | self supervised denoising of grating based phase contrast computed tomography |
| topic | Computed tomography X-ray imaging Noise reduction Self-supervised learning Phase contrast |
| url | https://doi.org/10.1038/s41598-024-83517-x |
| work_keys_str_mv | AT samiwirtensohn selfsuperviseddenoisingofgratingbasedphasecontrastcomputedtomography AT clemensschmid selfsuperviseddenoisingofgratingbasedphasecontrastcomputedtomography AT danielberthe selfsuperviseddenoisingofgratingbasedphasecontrastcomputedtomography AT dominikjohn selfsuperviseddenoisingofgratingbasedphasecontrastcomputedtomography AT lisaheck selfsuperviseddenoisingofgratingbasedphasecontrastcomputedtomography AT kirstentaphorn selfsuperviseddenoisingofgratingbasedphasecontrastcomputedtomography AT siljaflenner selfsuperviseddenoisingofgratingbasedphasecontrastcomputedtomography AT juliaherzen selfsuperviseddenoisingofgratingbasedphasecontrastcomputedtomography |