Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Evaluation of a deep learning magnetic resonance imaging reconstruction method for synthetic computed tomography generation in prostate radiotherapy

Olsson, Lars E. LU orcid ; af Wetterstedt, Sacha LU ; Scherman, Jonas ; Gunnlaugsson, Adalsteinn LU ; Persson, Emilia LU and Jamtheim Gustafsson, Christian LU (2024) In Physics and imaging in radiation oncology 29.
Abstract

Background and Purpose: In magnetic resonance imaging (MRI) only radiotherapy computed tomography (CT) is excluded. The method relies entirely on synthetic CT images generated from MRI. This study evaluates the compatibility of a commercial synthetic CT (sCT) with an accelerated commercial deep learning reconstruction (DLR) in MRI-only prostate radiotherapy. Materials and Methods: For a group of 24 patients (cohort 1) the effects of DLR were studied in isolation. MRI data were reconstructed conventionally and with DLR from identical k-space data, and sCTs were generated for both reconstructions. The sCT quality, Hounsfield Unit (HU) and dosimetric impact were investigated. In another group of 15 patients (cohort 2) effects on sCT... (More)

Background and Purpose: In magnetic resonance imaging (MRI) only radiotherapy computed tomography (CT) is excluded. The method relies entirely on synthetic CT images generated from MRI. This study evaluates the compatibility of a commercial synthetic CT (sCT) with an accelerated commercial deep learning reconstruction (DLR) in MRI-only prostate radiotherapy. Materials and Methods: For a group of 24 patients (cohort 1) the effects of DLR were studied in isolation. MRI data were reconstructed conventionally and with DLR from identical k-space data, and sCTs were generated for both reconstructions. The sCT quality, Hounsfield Unit (HU) and dosimetric impact were investigated. In another group of 15 patients (cohort 2) effects on sCT generation using accelerated MRI acquisition (40 % time reduction) reconstructed with DLR were investigated. Results: sCT images from both cohorts, generated from DLR MRI data, were of clinically expected image quality. The mean dose differences for targets and organs at risks in cohort 1 were <0.06 Gy, corresponding to a 0.1 % prescribed dose difference. Similar dose differences were observed in cohort 2. Gamma pass rates for cohort 1 were 100 % for criteria 3 %/3mm, 2 %/2mm and 1 %/1mm for all dose levels. Mean error and mean absolute error inside the body, between sCTs, averaged over all cohort 1 subjects, were −1.1 ± 0.6 [−2.4 0.2] and 2.9 ± 0.4 [2.3 3.9] HU, respectively. Conclusions: DLR was suitable for sCT generation with clinically negligible differences in HU and calculated dose compared to the conventional MRI reconstruction method. For sCT generation DLR enables scan time reduction, without compromised sCT quality.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Deep learning reconstruction, MRI, Prostate cancer, Radiotherapy, Synthetic CT
in
Physics and imaging in radiation oncology
volume
29
article number
100557
publisher
Elsevier
external identifiers
  • pmid:38414521
  • scopus:85185909591
ISSN
2405-6316
DOI
10.1016/j.phro.2024.100557
language
English
LU publication?
yes
id
e7dd4ddc-626c-474d-b594-fd974057919d
date added to LUP
2024-03-18 12:24:37
date last changed
2024-04-15 09:42:51
@article{e7dd4ddc-626c-474d-b594-fd974057919d,
  abstract     = {{<p>Background and Purpose: In magnetic resonance imaging (MRI) only radiotherapy computed tomography (CT) is excluded. The method relies entirely on synthetic CT images generated from MRI. This study evaluates the compatibility of a commercial synthetic CT (sCT) with an accelerated commercial deep learning reconstruction (DLR) in MRI-only prostate radiotherapy. Materials and Methods: For a group of 24 patients (cohort 1) the effects of DLR were studied in isolation. MRI data were reconstructed conventionally and with DLR from identical k-space data, and sCTs were generated for both reconstructions. The sCT quality, Hounsfield Unit (HU) and dosimetric impact were investigated. In another group of 15 patients (cohort 2) effects on sCT generation using accelerated MRI acquisition (40 % time reduction) reconstructed with DLR were investigated. Results: sCT images from both cohorts, generated from DLR MRI data, were of clinically expected image quality. The mean dose differences for targets and organs at risks in cohort 1 were &lt;0.06 Gy, corresponding to a 0.1 % prescribed dose difference. Similar dose differences were observed in cohort 2. Gamma pass rates for cohort 1 were 100 % for criteria 3 %/3mm, 2 %/2mm and 1 %/1mm for all dose levels. Mean error and mean absolute error inside the body, between sCTs, averaged over all cohort 1 subjects, were −1.1 ± 0.6 [−2.4 0.2] and 2.9 ± 0.4 [2.3 3.9] HU, respectively. Conclusions: DLR was suitable for sCT generation with clinically negligible differences in HU and calculated dose compared to the conventional MRI reconstruction method. For sCT generation DLR enables scan time reduction, without compromised sCT quality.</p>}},
  author       = {{Olsson, Lars E. and af Wetterstedt, Sacha and Scherman, Jonas and Gunnlaugsson, Adalsteinn and Persson, Emilia and Jamtheim Gustafsson, Christian}},
  issn         = {{2405-6316}},
  keywords     = {{Deep learning reconstruction; MRI; Prostate cancer; Radiotherapy; Synthetic CT}},
  language     = {{eng}},
  publisher    = {{Elsevier}},
  series       = {{Physics and imaging in radiation oncology}},
  title        = {{Evaluation of a deep learning magnetic resonance imaging reconstruction method for synthetic computed tomography generation in prostate radiotherapy}},
  url          = {{http://dx.doi.org/10.1016/j.phro.2024.100557}},
  doi          = {{10.1016/j.phro.2024.100557}},
  volume       = {{29}},
  year         = {{2024}},
}