Deep learning–based reconstruction may improve non-contrast cerebral CT imaging compared to other current reconstruction algorithms
Objectives To evaluate image quality and reconstruction times of a commercial deep learning reconstruction algorithm (DLR) compared to hybrid-iterative reconstruction (Hybrid-IR) and model-based iterative reconstruction (MBIR) algorithms for cerebral non-contrast CT (NCCT). Methods Cerebral NCCT acquisitions of 50 consecutive patients were reconstructed using DLR, Hybrid-IR and MBIR with a clinical CT system. Image quality, in terms of six subjective characteristics (noise, sharpness, grey-white matter differentiation, artefacts, natural appearance and overall image quality), was scored by five observers. As objective metrics of image quality, the noise magnitude and signal-difference-to-noise ratio (SDNR) of the grey and white matter were calculated. Mean values for the image quality characteristics scored by the observers were estimated using a general linear model to account for multiple readers. The estimated means for the reconstruction methods were pairwise compared. Calculated measures were compared using paired t tests. Results For all image quality characteristics, DLR images were scored significantly higher than MBIR images. Compared to Hybrid-IR, perceived noise and grey-white matter differentiation were better with DLR, while no difference was detected for other image quality characteristics. Noise magnitude was lower for DLR compared to Hybrid-IR and MBIR (5.6, 6.4 and 6.2, respectively) and SDNR higher (2.4, 1.9 and 2.0, respectively). Reconstruction times were 27 s, 44 s and 176 s for Hybrid-IR, DLR and MBIR respectively. Conclusions With a slight increase in reconstruction time, DLR results in lower noise and improved tissue differentiation compared to Hybrid-IR. Image quality of MBIR is significantly lower compared to DLR with much longer reconstruction times. Key Points • Deep learning reconstruction of cerebral non-contrast CT results in lower noise and improved tissue differentiation compared to hybrid-iterative reconstruction. • Deep learning reconstruction of cerebral non-contrast CT results in better image quality in all aspects evaluated compared to model-based iterative reconstruction. • Deep learning reconstruction only needs a slight increase in reconstruction time compared to hybrid-iterative reconstruction, while model-based iterative reconstruction requires considerably longer processing time..
Medienart: |
Artikel |
---|
Erscheinungsjahr: |
2021 |
---|---|
Erschienen: |
2021 |
Enthalten in: |
Zur Gesamtaufnahme - volume:31 |
---|---|
Enthalten in: |
European radiology - 31(2021), 8 vom: 10. März, Seite 5498-5506 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Oostveen, Luuk J. [VerfasserIn] |
---|
Links: |
Volltext [lizenzpflichtig] |
---|
Themen: |
---|
Anmerkungen: |
© The Author(s) 2021 |
---|
doi: |
10.1007/s00330-020-07668-x |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
OLC2126540847 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | OLC2126540847 | ||
003 | DE-627 | ||
005 | 20230519011459.0 | ||
007 | tu | ||
008 | 230505s2021 xx ||||| 00| ||eng c | ||
024 | 7 | |a 10.1007/s00330-020-07668-x |2 doi | |
035 | |a (DE-627)OLC2126540847 | ||
035 | |a (DE-He213)s00330-020-07668-x-p | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | 4 | |a 610 |q VZ |
082 | 0 | 4 | |a 610 |q VZ |
100 | 1 | |a Oostveen, Luuk J. |e verfasserin |0 (orcid)0000-0003-0445-9436 |4 aut | |
245 | 1 | 0 | |a Deep learning–based reconstruction may improve non-contrast cerebral CT imaging compared to other current reconstruction algorithms |
264 | 1 | |c 2021 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
338 | |a Band |b nc |2 rdacarrier | ||
500 | |a © The Author(s) 2021 | ||
520 | |a Objectives To evaluate image quality and reconstruction times of a commercial deep learning reconstruction algorithm (DLR) compared to hybrid-iterative reconstruction (Hybrid-IR) and model-based iterative reconstruction (MBIR) algorithms for cerebral non-contrast CT (NCCT). Methods Cerebral NCCT acquisitions of 50 consecutive patients were reconstructed using DLR, Hybrid-IR and MBIR with a clinical CT system. Image quality, in terms of six subjective characteristics (noise, sharpness, grey-white matter differentiation, artefacts, natural appearance and overall image quality), was scored by five observers. As objective metrics of image quality, the noise magnitude and signal-difference-to-noise ratio (SDNR) of the grey and white matter were calculated. Mean values for the image quality characteristics scored by the observers were estimated using a general linear model to account for multiple readers. The estimated means for the reconstruction methods were pairwise compared. Calculated measures were compared using paired t tests. Results For all image quality characteristics, DLR images were scored significantly higher than MBIR images. Compared to Hybrid-IR, perceived noise and grey-white matter differentiation were better with DLR, while no difference was detected for other image quality characteristics. Noise magnitude was lower for DLR compared to Hybrid-IR and MBIR (5.6, 6.4 and 6.2, respectively) and SDNR higher (2.4, 1.9 and 2.0, respectively). Reconstruction times were 27 s, 44 s and 176 s for Hybrid-IR, DLR and MBIR respectively. Conclusions With a slight increase in reconstruction time, DLR results in lower noise and improved tissue differentiation compared to Hybrid-IR. Image quality of MBIR is significantly lower compared to DLR with much longer reconstruction times. Key Points • Deep learning reconstruction of cerebral non-contrast CT results in lower noise and improved tissue differentiation compared to hybrid-iterative reconstruction. • Deep learning reconstruction of cerebral non-contrast CT results in better image quality in all aspects evaluated compared to model-based iterative reconstruction. • Deep learning reconstruction only needs a slight increase in reconstruction time compared to hybrid-iterative reconstruction, while model-based iterative reconstruction requires considerably longer processing time. | ||
650 | 4 | |a Tomography, X-ray computed | |
650 | 4 | |a Deep learning | |
650 | 4 | |a Brain | |
700 | 1 | |a Meijer, Frederick J. A. |4 aut | |
700 | 1 | |a de Lange, Frank |4 aut | |
700 | 1 | |a Smit, Ewoud J. |4 aut | |
700 | 1 | |a Pegge, Sjoert A. |4 aut | |
700 | 1 | |a Steens, Stefan C. A. |4 aut | |
700 | 1 | |a van Amerongen, Martin J. |4 aut | |
700 | 1 | |a Prokop, Mathias |4 aut | |
700 | 1 | |a Sechopoulos, Ioannis |4 aut | |
773 | 0 | 8 | |i Enthalten in |t European radiology |d Springer Berlin Heidelberg, 1991 |g 31(2021), 8 vom: 10. März, Seite 5498-5506 |w (DE-627)170641937 |w (DE-600)1085366-2 |w (DE-576)028039076 |x 0938-7994 |7 nnns |
773 | 1 | 8 | |g volume:31 |g year:2021 |g number:8 |g day:10 |g month:03 |g pages:5498-5506 |
856 | 4 | 1 | |u https://doi.org/10.1007/s00330-020-07668-x |z lizenzpflichtig |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a SYSFLAG_A | ||
912 | |a GBV_OLC | ||
912 | |a SSG-OLC-PHA | ||
912 | |a GBV_ILN_4112 | ||
951 | |a AR | ||
952 | |d 31 |j 2021 |e 8 |b 10 |c 03 |h 5498-5506 |