Comparative assessment of noise properties for two deep learning CT image reconstruction techniques and filtered back projection.
computed tomography
deep learning image reconstruction
noise reduction
Journal
Medical physics
ISSN: 2473-4209
Titre abrégé: Med Phys
Pays: United States
ID NLM: 0425746
Informations de publication
Date de publication:
Oct 2022
Oct 2022
Historique:
revised:
25
07
2022
received:
23
03
2022
accepted:
03
08
2022
pubmed:
2
9
2022
medline:
19
10
2022
entrez:
1
9
2022
Statut:
ppublish
Résumé
Two deep learning image reconstruction (DLIR) techniques from two different computed tomography (CT) vendors have recently been introduced into clinical practice. To characterize the noise properties of two DLIR techniques with different training methods, using a phantom containing a simple uniform and a complex non-uniform region. A water-bath phantom with a diameter of 300 mm was used as a base phantom. A textured phantom with a diameter of 128 mm, which was made of two materials, one equivalent to water and the other being 12 mg/ml diluted iodine, irregularly mixed to create a complex texture (non-uniform region), was placed in the base phantom. Thirty repeated phantom scans were performed using two CT scanners (Revolution CT with Apex Edition, GE Healthcare; Aquilion One PRISM Edition, Canon Medical Systems) at two dose levels (CT dose index: 5 and 15 mGy). Images were reconstructed with each CT system's filtered back projection (FBP) and DLIR [TrueFidelity (TF), GE Healthcare; Advanced intelligent Clear-IQ Engine Body Sharp (AC), Canon Medical Systems] for three process strengths. For basic characteristics of noise, the standard deviation (SD) and noise power spectrum (NPS) were measured for the uniform (water) region. A noise magnitude map was generated by calculating the inter-image SD at each pixel position across the 30 images. Then, a noise reduction map (NRM), which visualizes the relative differences in noise magnitude between FBP and DLIR, was calculated. The NRM values ranged from 0.0 to 1.0. A low NRM value represents a less aggressive noise reduction. The histograms of the NRM value were analyzed for the uniform and non-uniform regions. The reduction in noise magnitude compared with FBP tended to be greater with AC (45%-85%) than with TF (32%-65%). The average NPS frequencies of TF and AC were almost comparable to those of FBP, except for the low-dose condition and the high noise reduction strength for AC. The NRM values of TF and AC were higher in the uniform region than in the non-uniform region. In the non-uniform region, TF's average NRM values (0.21-0.48) tended to be lower than AC's (0.39-0.78). The histograms for TF showed a small overlap between the uniform and the non-uniform regions; in contrast, those for AC showed a greater overlap. This difference seems to indicate that TF processes the uniform and non-uniform regions more differently than AC does. This study has revealed a distinct difference in characteristics between the two DLIR techniques: TF tends to offer less aggressive noise reduction in non-uniform regions and preserve the original signals, whereas AC tends to prioritize noise filtering over edge-preservation, especially at the low-dose condition and with the high noise reduction strength.
Sections du résumé
BACKGROUND
BACKGROUND
Two deep learning image reconstruction (DLIR) techniques from two different computed tomography (CT) vendors have recently been introduced into clinical practice.
PURPOSE
OBJECTIVE
To characterize the noise properties of two DLIR techniques with different training methods, using a phantom containing a simple uniform and a complex non-uniform region.
METHODS
METHODS
A water-bath phantom with a diameter of 300 mm was used as a base phantom. A textured phantom with a diameter of 128 mm, which was made of two materials, one equivalent to water and the other being 12 mg/ml diluted iodine, irregularly mixed to create a complex texture (non-uniform region), was placed in the base phantom. Thirty repeated phantom scans were performed using two CT scanners (Revolution CT with Apex Edition, GE Healthcare; Aquilion One PRISM Edition, Canon Medical Systems) at two dose levels (CT dose index: 5 and 15 mGy). Images were reconstructed with each CT system's filtered back projection (FBP) and DLIR [TrueFidelity (TF), GE Healthcare; Advanced intelligent Clear-IQ Engine Body Sharp (AC), Canon Medical Systems] for three process strengths. For basic characteristics of noise, the standard deviation (SD) and noise power spectrum (NPS) were measured for the uniform (water) region. A noise magnitude map was generated by calculating the inter-image SD at each pixel position across the 30 images. Then, a noise reduction map (NRM), which visualizes the relative differences in noise magnitude between FBP and DLIR, was calculated. The NRM values ranged from 0.0 to 1.0. A low NRM value represents a less aggressive noise reduction. The histograms of the NRM value were analyzed for the uniform and non-uniform regions.
RESULTS
RESULTS
The reduction in noise magnitude compared with FBP tended to be greater with AC (45%-85%) than with TF (32%-65%). The average NPS frequencies of TF and AC were almost comparable to those of FBP, except for the low-dose condition and the high noise reduction strength for AC. The NRM values of TF and AC were higher in the uniform region than in the non-uniform region. In the non-uniform region, TF's average NRM values (0.21-0.48) tended to be lower than AC's (0.39-0.78). The histograms for TF showed a small overlap between the uniform and the non-uniform regions; in contrast, those for AC showed a greater overlap. This difference seems to indicate that TF processes the uniform and non-uniform regions more differently than AC does.
CONCLUSION
CONCLUSIONS
This study has revealed a distinct difference in characteristics between the two DLIR techniques: TF tends to offer less aggressive noise reduction in non-uniform regions and preserve the original signals, whereas AC tends to prioritize noise filtering over edge-preservation, especially at the low-dose condition and with the high noise reduction strength.
Substances chimiques
Water
059QF0KO0R
Iodine
9679TC07X4
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
6359-6367Informations de copyright
© 2022 American Association of Physicists in Medicine.
Références
Mileto A, Guimaraes LS, McCollough CH, Fletcher JG, Yu L. State of the art in abdominal CT: the limits of iterative reconstruction algorithms. Radiology. 2019;293(3):191422. https://doi.org/10.1148/radiol.2019191422
Ehman EC, Yu L, Manduca A, et al. Methods for clinical evaluation of noise reduction techniques in abdominopelvic CT. Radiographics. 2014;34(4):849-862. https://doi.org/10.1148/rg.344135128
Geyer LL, Schoepf UJ, Meinel FG, et al. State of the art: iterative CT reconstruction techniques. Radiology. 2015;276(2):339-357. https://doi.org/10.1148/radiol.2015132766
Samei E, Richard S. Assessment of the dose reduction potential of a model-based iterative reconstruction algorithm using a task-based performance metrology. Med Phys. 2015;42(1):314-323. https://doi.org/10.1118/1.4903899
Hsieh J, Liu E, Nett B, Tang J, Thibeault JB, Sahney S. A new era of image reconstruction: TrueFidelityTM. Technical White Paper on Deep Learning Image Reconstruction. 2019; GE Healthcare white paper.
Solomon J, Lyu P, Marin D, Samei E. Noise and spatial resolution properties of a commercially available deep learning-based CT reconstruction algorithm. Med Phys. 2020;47(9):3961-3971. https://doi.org/10.1002/mp.14319
Nagayama Y, Sakabe D, Goto M, et al. Deep learning-based reconstruction for lower-dose pediatric CT: technical principles, image characteristics, and clinical implementations. Radiographics. 2021;41(7):1936-1953. https://doi.org/10.1148/rg.2021210105
Greffier J, Dabli D, Frandon J, et al. Comparison of two versions of a deep learning image reconstruction algorithm on CT image quality and dose reduction: a phantom study. Med Phys. 2021;48(10):5743-5755. https://doi.org/10.1002/mp.15180
Greffier J, Hamard A, Pereira F, et al. Image quality and dose reduction opportunity of deep learning image reconstruction algorithm for CT: a phantom study. Eur Radiol. 2020;30(7):3951-3959. https://doi.org/10.1007/s00330-020-06724-w
Kawashima H, Ichikawa K, Takata T, et al. Performance of clinically available deep learning image reconstruction in computed tomography: a phantom study. J Medical Imaging. 2020;7(06):063503. https://doi.org/10.1117/1.jmi.7.6.063503
Racine D, Becce F, Viry A, et al. Task-based characterization of a deep learning image reconstruction and comparison with filtered back-projection and a partial model-based iterative reconstruction in abdominal CT: a phantom study. Phys Med. 2020;76:28-37. https://doi.org/10.1016/j.ejmp.2020.06.004
Higaki T, Nakamura Y, Zhou J, et al. Deep learning reconstruction at CT: phantom study of the image characteristics. Acad Radiol. 2020;27(1):82-87. https://doi.org/10.1016/j.acra.2019.09.008
Urikura A, Yoshida T, Nakaya Y, Nishimaru E, Hara T, Endo M. Deep learning-based reconstruction in ultra-high-resolution computed tomography: can image noise caused by high definition detector and the miniaturization of matrix element size be improved? Phys Med. 2021;81:121-129. https://doi.org/10.1016/j.ejmp.2020.12.006
Akagi M, Nakamura Y, Higaki T, et al. Deep learning reconstruction improves image quality of abdominal ultra-high-resolution CT. Eur Radiol. 2019;29(11):6163-6171. https://doi.org/10.1007/s00330-019-06170-3
Samei E, Bakalyar D, Boedeker KL, et al. Performance evaluation of computed tomography systems: summary of AAPM Task Group 233. Med Phys. 2019;46(11):e735-e756. https://doi.org/10.1002/mp.13763
Solomon J, Samei E. Quantum noise properties of CT images with anatomical textured backgrounds across reconstruction algorithms: FBP and SAFIRE. Med Phys. 2014;41(9):091908. https://doi.org/10.1118/1.4893497
Guleng A, Bolstad K, Dalehaug I, Flatabø S, Aadnevik D, Pettersen HES. Spatial distribution of noise reduction in four iterative reconstruction algorithms in CT-a technical evaluation. Diagnostics. 2020;10(9):647. https://doi.org/10.3390/diagnostics10090647
Smith-Bindman R, Moghadassi M, Wilson N, et al. Radiation doses in consecutive CT examinations from Five University of California Medical Centers. Radiology. 2015;277(1):134-141.
Boedeker KL, Cooper VN, McNitt-Gray MF. Application of the noise power spectrum in modern diagnostic MDCT: part I. Measurement of noise power spectra and noise equivalent quanta. Phys Med Biol. 2007;52(14):4027-4046. https://doi.org/10.1088/0031-9155/52/14/002
Greffier J, Frandon J, Larbi A, Beregi JP, Pereira F. CT iterative reconstruction algorithms: a task-based image quality assessment. Eur Radiol. 2020;30(1):487-500. https://doi.org/10.1007/s00330-019-06359-6
Jensen CT, Gupta S, Saleh MM, et al. Reduced-dose deep learning reconstruction for abdominal CT of liver metastases. Radiology. 2022;303(1):90-98. https://doi.org/10.1148/radiol.211838
Ria F, Solomon JB, Wilson JM, Samei E. Technical note: validation of TG 233 phantom methodology to characterize noise and dose in patient CT data. Med Phys. 2020;47(4):1633-1639. https://doi.org/10.1002/mp.14089