Cycloidal CT with CNN-based sinogram completion and in-scan generation of training data
Abstract In x-ray computed tomography (CT), the achievable image resolution is typically limited by several pre-fixed characteristics of the x-ray source and detector. Structuring the x-ray beam using a mask with alternating opaque and transmitting septa can overcome this limit. However, the use of...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-04910-y |
| _version_ | 1828127356751970304 |
|---|---|
| author | Daniël M. Pelt Oriol Roche i Morgó Charlotte Maughan Jones Alessandro Olivo Charlotte K. Hagen |
| author_facet | Daniël M. Pelt Oriol Roche i Morgó Charlotte Maughan Jones Alessandro Olivo Charlotte K. Hagen |
| author_sort | Daniël M. Pelt |
| collection | DOAJ |
| description | Abstract In x-ray computed tomography (CT), the achievable image resolution is typically limited by several pre-fixed characteristics of the x-ray source and detector. Structuring the x-ray beam using a mask with alternating opaque and transmitting septa can overcome this limit. However, the use of a mask imposes an undersampling problem: to obtain complete datasets, significant lateral sample stepping is needed in addition to the sample rotation, resulting in high x-ray doses and long acquisition times. Cycloidal CT, an alternative scanning scheme by which the sample is rotated and translated simultaneously, can provide high aperture-driven resolution without sample stepping, resulting in a lower radiation dose and faster scans. However, cycloidal sinograms are incomplete and must be restored before tomographic images can be computed. In this work, we demonstrate that high-quality images can be reconstructed by applying the recently proposed Mixed Scale Dense (MS-D) convolutional neural network (CNN) to this task. We also propose a novel training approach by which training data are acquired as part of each scan, thus removing the need for large sets of pre-existing reference data, the acquisition of which is often not practicable or possible. We present results for both simulated datasets and real-world data, showing that the combination of cycloidal CT and machine learning-based data recovery can lead to accurate high-resolution images at a limited dose. |
| first_indexed | 2024-04-11T15:48:08Z |
| format | Article |
| id | doaj.art-7d912e10d9e4453aab7ee51c2669ff56 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-11T15:48:08Z |
| publishDate | 2022-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-7d912e10d9e4453aab7ee51c2669ff562022-12-22T04:15:27ZengNature PortfolioScientific Reports2045-23222022-01-0112111310.1038/s41598-022-04910-yCycloidal CT with CNN-based sinogram completion and in-scan generation of training dataDaniël M. Pelt0Oriol Roche i Morgó1Charlotte Maughan Jones2Alessandro Olivo3Charlotte K. Hagen4Leiden Institute of Advanced Computer Science, Leiden UniversityDepartment of Medical Physics and Biomedical Engineering, University College LondonDepartment of Medical Physics and Biomedical Engineering, University College LondonDepartment of Medical Physics and Biomedical Engineering, University College LondonDepartment of Medical Physics and Biomedical Engineering, University College LondonAbstract In x-ray computed tomography (CT), the achievable image resolution is typically limited by several pre-fixed characteristics of the x-ray source and detector. Structuring the x-ray beam using a mask with alternating opaque and transmitting septa can overcome this limit. However, the use of a mask imposes an undersampling problem: to obtain complete datasets, significant lateral sample stepping is needed in addition to the sample rotation, resulting in high x-ray doses and long acquisition times. Cycloidal CT, an alternative scanning scheme by which the sample is rotated and translated simultaneously, can provide high aperture-driven resolution without sample stepping, resulting in a lower radiation dose and faster scans. However, cycloidal sinograms are incomplete and must be restored before tomographic images can be computed. In this work, we demonstrate that high-quality images can be reconstructed by applying the recently proposed Mixed Scale Dense (MS-D) convolutional neural network (CNN) to this task. We also propose a novel training approach by which training data are acquired as part of each scan, thus removing the need for large sets of pre-existing reference data, the acquisition of which is often not practicable or possible. We present results for both simulated datasets and real-world data, showing that the combination of cycloidal CT and machine learning-based data recovery can lead to accurate high-resolution images at a limited dose.https://doi.org/10.1038/s41598-022-04910-y |
| spellingShingle | Daniël M. Pelt Oriol Roche i Morgó Charlotte Maughan Jones Alessandro Olivo Charlotte K. Hagen Cycloidal CT with CNN-based sinogram completion and in-scan generation of training data Scientific Reports |
| title | Cycloidal CT with CNN-based sinogram completion and in-scan generation of training data |
| title_full | Cycloidal CT with CNN-based sinogram completion and in-scan generation of training data |
| title_fullStr | Cycloidal CT with CNN-based sinogram completion and in-scan generation of training data |
| title_full_unstemmed | Cycloidal CT with CNN-based sinogram completion and in-scan generation of training data |
| title_short | Cycloidal CT with CNN-based sinogram completion and in-scan generation of training data |
| title_sort | cycloidal ct with cnn based sinogram completion and in scan generation of training data |
| url | https://doi.org/10.1038/s41598-022-04910-y |
| work_keys_str_mv | AT danielmpelt cycloidalctwithcnnbasedsinogramcompletionandinscangenerationoftrainingdata AT oriolrocheimorgo cycloidalctwithcnnbasedsinogramcompletionandinscangenerationoftrainingdata AT charlottemaughanjones cycloidalctwithcnnbasedsinogramcompletionandinscangenerationoftrainingdata AT alessandroolivo cycloidalctwithcnnbasedsinogramcompletionandinscangenerationoftrainingdata AT charlottekhagen cycloidalctwithcnnbasedsinogramcompletionandinscangenerationoftrainingdata |