Quantitative and qualitative assessments of deep learning image reconstruction in low-keV virtual monoenergetic dual-energy CT
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Quantitative and qualitative assessments of deep learning image reconstruction in low-keV virtual monoenergetic dual-energy CT. / Xu, Jack Junchi; Lonn, Lars; Budtz-Jorgensen, Esben; Hansen, Kristoffer L.; Ulriksen, Peter S.
I: European Radiology, Bind 32, 2022, s. 7098–7107.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Quantitative and qualitative assessments of deep learning image reconstruction in low-keV virtual monoenergetic dual-energy CT
AU - Xu, Jack Junchi
AU - Lonn, Lars
AU - Budtz-Jorgensen, Esben
AU - Hansen, Kristoffer L.
AU - Ulriksen, Peter S.
PY - 2022
Y1 - 2022
N2 - Objectives To evaluate a novel deep learning image reconstruction (DLIR) technique for dual-energy CT (DECT) derived virtual monoenergetic (VM) images compared to adaptive statistical iterative reconstruction (ASIR-V) in low kiloelectron volt (keV) images. Methods We analyzed 30 venous phase acute abdominal DECT (80/140 kVp) scans. Data were reconstructed to ASIR-V and DLIR-High at four different keV levels (40, 50, 74, and 100) with 1- and 3-mm slice thickness. Quantitative Hounsfield unit (HU) and noise assessment were measured within the liver, aorta, fat, and muscle. Subjective assessment of image noise, sharpness, texture, and overall quality was performed by two board-certified radiologists. Results DLIR reduced image noise by 19.9-35.5% (p < 0.001) compared to ASIR-V in all reconstructions at identical keV levels. Contrast-to-noise ratio (CNR) increased by 49.2-53.2% (p < 0.001) in DLIR 40-keV images compared to ASIR-V 50 keV, while no significant difference in noise was identified except for 1 and 3 mm in aorta and for 1-mm liver measurements, where ASIR-V 50 keV showed 5.5-6.8% (p < 0.002) lower noise levels. Qualitative assessment demonstrated significant improvement particularly in 1-mm reconstructions (p < 0.001). Lastly, DLIR 40 keV demonstrated comparable or improved image quality ratings when compared to ASIR-V 50 keV (p < 0.001 to 0.22). Conclusion DLIR significantly reduced image noise compared to ASIR-V. Qualitative assessment showed that DLIR significantly improved image quality particularly in thin sliced images. DLIR may facilitate 40 keV as a new standard for routine low-keV VM reconstruction in contrast-enhanced abdominal DECT.
AB - Objectives To evaluate a novel deep learning image reconstruction (DLIR) technique for dual-energy CT (DECT) derived virtual monoenergetic (VM) images compared to adaptive statistical iterative reconstruction (ASIR-V) in low kiloelectron volt (keV) images. Methods We analyzed 30 venous phase acute abdominal DECT (80/140 kVp) scans. Data were reconstructed to ASIR-V and DLIR-High at four different keV levels (40, 50, 74, and 100) with 1- and 3-mm slice thickness. Quantitative Hounsfield unit (HU) and noise assessment were measured within the liver, aorta, fat, and muscle. Subjective assessment of image noise, sharpness, texture, and overall quality was performed by two board-certified radiologists. Results DLIR reduced image noise by 19.9-35.5% (p < 0.001) compared to ASIR-V in all reconstructions at identical keV levels. Contrast-to-noise ratio (CNR) increased by 49.2-53.2% (p < 0.001) in DLIR 40-keV images compared to ASIR-V 50 keV, while no significant difference in noise was identified except for 1 and 3 mm in aorta and for 1-mm liver measurements, where ASIR-V 50 keV showed 5.5-6.8% (p < 0.002) lower noise levels. Qualitative assessment demonstrated significant improvement particularly in 1-mm reconstructions (p < 0.001). Lastly, DLIR 40 keV demonstrated comparable or improved image quality ratings when compared to ASIR-V 50 keV (p < 0.001 to 0.22). Conclusion DLIR significantly reduced image noise compared to ASIR-V. Qualitative assessment showed that DLIR significantly improved image quality particularly in thin sliced images. DLIR may facilitate 40 keV as a new standard for routine low-keV VM reconstruction in contrast-enhanced abdominal DECT.
KW - Artificial intelligence
KW - Deep learning
KW - Tomography
KW - X-ray computed
KW - Image processing
KW - computer-assisted
KW - ITERATIVE RECONSTRUCTION
KW - COMPUTED-TOMOGRAPHY
KW - OPTIMIZATION
KW - ALGORITHM
U2 - 10.1007/s00330-022-09018-5
DO - 10.1007/s00330-022-09018-5
M3 - Journal article
C2 - 35895120
VL - 32
SP - 7098
EP - 7107
JO - European Radiology
JF - European Radiology
SN - 0938-7994
ER -
ID: 315456722