Noise Reduction in Brain CT: A Comparative Study of Deep Learning and Hybrid Iterative Reconstruction Using Multiple Parameters
Objectives: We evaluated the noise reduction effects of deep learning reconstruction (DLR) and hybrid iterative reconstruction (HIR) in brain computed tomography (CT). Methods: CT images of a 16 cm dosimetry phantom, a head phantom, and the brains of 11 patients were reconstructed using filtered bac...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Tomography |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2379-139X/10/12/147 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846102589027909632 |
|---|---|
| author | Yusuke Inoue Hiroyasu Itoh Hirofumi Hata Hiroki Miyatake Kohei Mitsui Shunichi Uehara Chisaki Masuda |
| author_facet | Yusuke Inoue Hiroyasu Itoh Hirofumi Hata Hiroki Miyatake Kohei Mitsui Shunichi Uehara Chisaki Masuda |
| author_sort | Yusuke Inoue |
| collection | DOAJ |
| description | Objectives: We evaluated the noise reduction effects of deep learning reconstruction (DLR) and hybrid iterative reconstruction (HIR) in brain computed tomography (CT). Methods: CT images of a 16 cm dosimetry phantom, a head phantom, and the brains of 11 patients were reconstructed using filtered backprojection (FBP) and various levels of DLR and HIR. The slice thickness was 5, 2.5, 1.25, and 0.625 mm. Phantom imaging was also conducted at various tube currents. The noise reduction ratio was calculated using FBP as the reference. For patient imaging, overall image quality was visually compared between DLR and HIR images that exhibited similar noise reduction ratios. Results: The noise reduction ratio increased with increasing levels of DLR and HIR in phantom and patient imaging. For DLR, noise reduction was more pronounced with decreasing slice thickness, while such thickness dependence was less evident for HIR. Although the noise reduction effects of DLR were similar between the head phantom and patients, they differed for the dosimetry phantom. Variations between imaging objects were small for HIR. The noise reduction ratio was low at low tube currents for the dosimetry phantom using DLR; otherwise, the influence of the tube current was small. In terms of visual image quality, DLR outperformed HIR in 1.25 mm thick images but not in thicker images. Conclusions: The degree of noise reduction using DLR depends on the slice thickness, tube current, and imaging object in addition to the level of DLR, which should be considered in the clinical use of DLR. DLR may be particularly beneficial for thin-slice imaging. |
| format | Article |
| id | doaj-art-b14aa7eaab9c4fb1b2e2ffcfd1bf4303 |
| institution | Kabale University |
| issn | 2379-1381 2379-139X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Tomography |
| spelling | doaj-art-b14aa7eaab9c4fb1b2e2ffcfd1bf43032024-12-27T14:56:24ZengMDPI AGTomography2379-13812379-139X2024-12-0110122073208610.3390/tomography10120147Noise Reduction in Brain CT: A Comparative Study of Deep Learning and Hybrid Iterative Reconstruction Using Multiple ParametersYusuke Inoue0Hiroyasu Itoh1Hirofumi Hata2Hiroki Miyatake3Kohei Mitsui4Shunichi Uehara5Chisaki Masuda6Department of Diagnostic Radiology, Kitasato University School of Medicine, Sagamihara 252-0374, JapanDepartment of Radiology, Kitasato University Hospital, Sagamihara 252-0375, JapanDepartment of Radiology, Kitasato University Hospital, Sagamihara 252-0375, JapanDepartment of Radiology, Kitasato University Hospital, Sagamihara 252-0375, JapanDepartment of Diagnostic Radiology, Kitasato University School of Medicine, Sagamihara 252-0374, JapanDepartment of Diagnostic Radiology, Kitasato University School of Medicine, Sagamihara 252-0374, JapanDepartment of Diagnostic Radiology, Kitasato University School of Medicine, Sagamihara 252-0374, JapanObjectives: We evaluated the noise reduction effects of deep learning reconstruction (DLR) and hybrid iterative reconstruction (HIR) in brain computed tomography (CT). Methods: CT images of a 16 cm dosimetry phantom, a head phantom, and the brains of 11 patients were reconstructed using filtered backprojection (FBP) and various levels of DLR and HIR. The slice thickness was 5, 2.5, 1.25, and 0.625 mm. Phantom imaging was also conducted at various tube currents. The noise reduction ratio was calculated using FBP as the reference. For patient imaging, overall image quality was visually compared between DLR and HIR images that exhibited similar noise reduction ratios. Results: The noise reduction ratio increased with increasing levels of DLR and HIR in phantom and patient imaging. For DLR, noise reduction was more pronounced with decreasing slice thickness, while such thickness dependence was less evident for HIR. Although the noise reduction effects of DLR were similar between the head phantom and patients, they differed for the dosimetry phantom. Variations between imaging objects were small for HIR. The noise reduction ratio was low at low tube currents for the dosimetry phantom using DLR; otherwise, the influence of the tube current was small. In terms of visual image quality, DLR outperformed HIR in 1.25 mm thick images but not in thicker images. Conclusions: The degree of noise reduction using DLR depends on the slice thickness, tube current, and imaging object in addition to the level of DLR, which should be considered in the clinical use of DLR. DLR may be particularly beneficial for thin-slice imaging.https://www.mdpi.com/2379-139X/10/12/147computed tomographybraindeep learning reconstructionhybrid iterative reconstructionimage noise |
| spellingShingle | Yusuke Inoue Hiroyasu Itoh Hirofumi Hata Hiroki Miyatake Kohei Mitsui Shunichi Uehara Chisaki Masuda Noise Reduction in Brain CT: A Comparative Study of Deep Learning and Hybrid Iterative Reconstruction Using Multiple Parameters Tomography computed tomography brain deep learning reconstruction hybrid iterative reconstruction image noise |
| title | Noise Reduction in Brain CT: A Comparative Study of Deep Learning and Hybrid Iterative Reconstruction Using Multiple Parameters |
| title_full | Noise Reduction in Brain CT: A Comparative Study of Deep Learning and Hybrid Iterative Reconstruction Using Multiple Parameters |
| title_fullStr | Noise Reduction in Brain CT: A Comparative Study of Deep Learning and Hybrid Iterative Reconstruction Using Multiple Parameters |
| title_full_unstemmed | Noise Reduction in Brain CT: A Comparative Study of Deep Learning and Hybrid Iterative Reconstruction Using Multiple Parameters |
| title_short | Noise Reduction in Brain CT: A Comparative Study of Deep Learning and Hybrid Iterative Reconstruction Using Multiple Parameters |
| title_sort | noise reduction in brain ct a comparative study of deep learning and hybrid iterative reconstruction using multiple parameters |
| topic | computed tomography brain deep learning reconstruction hybrid iterative reconstruction image noise |
| url | https://www.mdpi.com/2379-139X/10/12/147 |
| work_keys_str_mv | AT yusukeinoue noisereductioninbrainctacomparativestudyofdeeplearningandhybriditerativereconstructionusingmultipleparameters AT hiroyasuitoh noisereductioninbrainctacomparativestudyofdeeplearningandhybriditerativereconstructionusingmultipleparameters AT hirofumihata noisereductioninbrainctacomparativestudyofdeeplearningandhybriditerativereconstructionusingmultipleparameters AT hirokimiyatake noisereductioninbrainctacomparativestudyofdeeplearningandhybriditerativereconstructionusingmultipleparameters AT koheimitsui noisereductioninbrainctacomparativestudyofdeeplearningandhybriditerativereconstructionusingmultipleparameters AT shunichiuehara noisereductioninbrainctacomparativestudyofdeeplearningandhybriditerativereconstructionusingmultipleparameters AT chisakimasuda noisereductioninbrainctacomparativestudyofdeeplearningandhybriditerativereconstructionusingmultipleparameters |