Deep-learning-based reconstruction of T2-weighted magnetic
resonance imaging of the prostate accelerated by compressed
sensing provides improved image quality at half the acquisition
time

J 2024

Deep-learning-based reconstruction of T2-weighted magnetic resonance imaging of the prostate accelerated by compressed sensing provides improved image quality at half the acquisition time

JURKA, Martin, Iva MACOVA, Monika WAGNEROVA, Otakar CAPOUN, Roman JAKUBICEK et. al.

Základní údaje

Originální název

Deep-learning-based reconstruction of T2-weighted magnetic resonance imaging of the prostate accelerated by compressed sensing provides improved image quality at half the acquisition time

Autoři

JURKA, Martin (203 Česká republika), Iva MACOVA (203 Česká republika), Monika WAGNEROVA (203 Česká republika), Otakar CAPOUN (203 Česká republika), Roman JAKUBICEK (203 Česká republika), Petr OUŘEDNÍČEK (203 Česká republika, domácí), Lukas LAMBERT (203 Česká republika) a Andrea BURGETOVA (203 Česká republika)

Vydání

QUANTITATIVE IMAGING IN MEDICINE AND SURGERY, SHATIN, AME PUBL CO, 2024, 2223-4292

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

30224 Radiology, nuclear medicine and medical imaging

Stát vydavatele

Hongkong

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 2.800 v roce 2022

Organizační jednotka

Lékařská fakulta

DOI

http://dx.doi.org/10.21037/qims-23-1488

UT WoS

001250132200023

Klíčová slova anglicky

Magnetic resonance imaging (MRI); prostate cancer; artificial intelligence (AI); image reconstruction

Štítky

14110119, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 9. 7. 2024 08:47, Mgr. Tereza Miškechová

Anotace

V originále

Background: Deep-learning-based reconstruction (DLR) improves the quality of magnetic resonance (MR) images which allows faster acquisitions. The aim of this study was to compare the image quality of standard and accelerated T2 weighted turbo-spin-echo (TSE) images of the prostate reconstructed with and without DLR and to find associations between perceived image quality and calculated image characteristics. Methods: In a cohort of 47 prospectively enrolled consecutive patients referred for bi-parametric prostate magnetic resonance imaging (MRI), two T2-TSE acquisitions in the transverse plane were acquired on a 3T scanner-a standard T2-TSE sequence and a short sequence accelerated by a factor of two using compressed sensing (CS). The images were reconstructed with and without DLR in super-resolution mode. The image quality was rated in six domains. Signal-to-noise ratio (SNR), and image sharpness were measured. Results: The mean acquisition time was 281 +/- 23 s for the standard and 140 +/- 12 s for the short acquisition (P<0.0001). DLR images had higher sharpness compared to non-DLR (P<0.001). Short and short-DLR had lower SNR than the standard and standard-DLR (P<0.001). The perceived image quality of short-DLR was rated better in all categories compared to the standard sequence (P<0.001 to P=0.004). All domains of subjective evaluation were correlated with measured image sharpness (P<0.001). Conclusions: T2-TSE acquisition of the prostate accelerated using CS combined with DLR reconstruction provides images with increased sharpness that have a superior quality as perceived by human readers compared to standard T2-TSE. The perceived image quality is correlated with measured image contrast.

Citovat

JURKA, Martin, Iva MACOVA, Monika WAGNEROVA, Otakar CAPOUN, Roman JAKUBICEK, Petr OUŘEDNÍČEK, Lukas LAMBERT a Andrea BURGETOVA. Deep-learning-based reconstruction of T2-weighted magnetic resonance imaging of the prostate accelerated by compressed sensing provides improved image quality at half the acquisition time. QUANTITATIVE IMAGING IN MEDICINE AND SURGERY. SHATIN: AME PUBL CO, 2024, roč. 14, č. 5, s. 3534-3544. ISSN 2223-4292. Dostupné z: https://dx.doi.org/10.21037/qims-23-1488.

@article{2417619,
   author = {Jurka, Martin and Macova, Iva and Wagnerova, Monika and Capoun, Otakar and Jakubicek, Roman and Ouředníček, Petr and Lambert, Lukas and Burgetova, Andrea},
   article_location = {SHATIN},
   article_number = {5},
   doi = {http://dx.doi.org/10.21037/qims-23-1488},
   keywords = {Magnetic resonance imaging (MRI); prostate cancer; artificial intelligence (AI); image reconstruction},
   language = {eng},
   issn = {2223-4292},
   journal = {QUANTITATIVE IMAGING IN MEDICINE AND SURGERY},
   title = {Deep-learning-based reconstruction of T2-weighted magnetic resonance imaging of the prostate accelerated by compressed sensing provides improved image quality at half the acquisition time},
   url = {https://qims.amegroups.org/article/view/123434/html},
   volume = {14},
   year = {2024}
}

TY  - JOUR
ID  - 2417619
AU  - Jurka, Martin - Macova, Iva - Wagnerova, Monika - Capoun, Otakar - Jakubicek, Roman - Ouředníček, Petr - Lambert, Lukas - Burgetova, Andrea
PY  - 2024
TI  - Deep-learning-based reconstruction of T2-weighted magnetic resonance imaging of the prostate accelerated by compressed sensing provides improved image quality at half the acquisition time
JF  - QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
VL  - 14
IS  - 5
SP  - 3534-3544
EP  - 3534-3544
PB  - AME PUBL CO
SN  - 22234292
KW  - Magnetic resonance imaging (MRI)
KW  - prostate cancer
KW  - artificial intelligence (AI)
KW  - image reconstruction
UR  - https://qims.amegroups.org/article/view/123434/html
N2  - Background: Deep-learning-based reconstruction (DLR) improves the quality of magnetic resonance (MR) images which allows faster acquisitions. The aim of this study was to compare the image quality of standard and accelerated T2 weighted turbo-spin-echo (TSE) images of the prostate reconstructed with and without DLR and to find associations between perceived image quality and calculated image characteristics. Methods: In a cohort of 47 prospectively enrolled consecutive patients referred for bi-parametric prostate magnetic resonance imaging (MRI), two T2-TSE acquisitions in the transverse plane were acquired on a 3T scanner-a standard T2-TSE sequence and a short sequence accelerated by a factor of two using compressed sensing (CS). The images were reconstructed with and without DLR in super-resolution mode. The image quality was rated in six domains. Signal-to-noise ratio (SNR), and image sharpness were measured. Results: The mean acquisition time was 281 +/- 23 s for the standard and 140 +/- 12 s for the short acquisition (P<0.0001). DLR images had higher sharpness compared to non-DLR (P<0.001). Short and short-DLR had lower SNR than the standard and standard-DLR (P<0.001). The perceived image quality of short-DLR was rated better in all categories compared to the standard sequence (P<0.001 to P=0.004). All domains of subjective evaluation were correlated with measured image sharpness (P<0.001). Conclusions: T2-TSE acquisition of the prostate accelerated using CS combined with DLR reconstruction provides images with increased sharpness that have a superior quality as perceived by human readers compared to standard T2-TSE. The perceived image quality is correlated with measured image contrast.
ER  -

JURKA, Martin, Iva MACOVA, Monika WAGNEROVA, Otakar CAPOUN, Roman JAKUBICEK, Petr OUŘEDNÍČEK, Lukas LAMBERT a Andrea BURGETOVA. Deep-learning-based reconstruction of T2-weighted magnetic resonance imaging of the prostate accelerated by compressed sensing provides improved image quality at half the acquisition time. \textit{QUANTITATIVE IMAGING IN MEDICINE AND SURGERY}. SHATIN: AME PUBL CO, 2024, roč.~14, č.~5, s.~3534-3544. ISSN~2223-4292. Dostupné z: https://dx.doi.org/10.21037/qims-23-1488.

Podrobný výpis o publikaci