Low-dose PET image noise reduction using deep learning: Application to cardiac viability FDG imaging in patients with ischemic heart disease
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Low-dose PET image noise reduction using deep learning : Application to cardiac viability FDG imaging in patients with ischemic heart disease. / Ladefoged, Claes Nøhr; Hasbak, Philip; Hornnes, Charlotte; Højgaard, Liselotte; Andersen, Flemming Littrup.
I: Physics in Medicine and Biology, Bind 66, Nr. 5, 054003, 2021.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Low-dose PET image noise reduction using deep learning
T2 - Application to cardiac viability FDG imaging in patients with ischemic heart disease
AU - Ladefoged, Claes Nøhr
AU - Hasbak, Philip
AU - Hornnes, Charlotte
AU - Højgaard, Liselotte
AU - Andersen, Flemming Littrup
N1 - Publisher Copyright: © 2021 Institute of Physics and Engineering in Medicine.
PY - 2021
Y1 - 2021
N2 - Introduction. Cardiac [18F]FDG-PET is widely used for viability testing in patients with chronic ischemic heart disease. Guidelines recommend injection of 200-350 MBq [18F]FDG, however, a reduction of radiation exposure has become increasingly important, but might come at the cost of reduced diagnostic accuracy due to the increased noise in the images. We aimed to explore the use of a common deep learning (DL) network for noise reduction in low-dose PET images, and to validate its accuracy using the clinical quantitative metrics used to determine cardiac viability in patients with ischemic heart disease. Methods. We included 168 patients imaged with cardiac [18F]FDG-PET/CT. We simulated a reduced dose by keeping counts at thresholds 1% and 10%. 3D U-net with five blocks was trained to de-noise full PET volumes (128 × 128 × 111). The low-dose and de-noised images were compared in Corridor4DM to the full-dose PET images. We used the default segmentation of the left ventricle to extract the quantitative metrics end-diastolic volume (EDV), end-systolic volume (ESV), and left ventricular ejection fraction (LVEF) from the gated images, and FDG defect extent from the static images. Results. Our de-noising models were able to recover the PET signal for both the static and gated images in either dose-reduction. For the 1% low-dose images, the error is most pronounced for EDV and ESV, where the average underestimation is 25%. No bias was observed using the proposed DL de-noising method. De-noising minimized the outliers found for the 1% and 10% low-dose measurements of LVEF and extent. Accuracy of differential diagnosis based on LVEF threshold was highly improved after de-noising. Conclusion. A significant dose reduction can be achieved for cardiac [18F]FDG images used for viability testing in patients with ischemic heart disease without significant loss of diagnostic accuracy when using our DL model for noise reduction. Both 1% and 10% dose reductions are possible with clinically quantitative metrics comparable to that obtained with a full dose.
AB - Introduction. Cardiac [18F]FDG-PET is widely used for viability testing in patients with chronic ischemic heart disease. Guidelines recommend injection of 200-350 MBq [18F]FDG, however, a reduction of radiation exposure has become increasingly important, but might come at the cost of reduced diagnostic accuracy due to the increased noise in the images. We aimed to explore the use of a common deep learning (DL) network for noise reduction in low-dose PET images, and to validate its accuracy using the clinical quantitative metrics used to determine cardiac viability in patients with ischemic heart disease. Methods. We included 168 patients imaged with cardiac [18F]FDG-PET/CT. We simulated a reduced dose by keeping counts at thresholds 1% and 10%. 3D U-net with five blocks was trained to de-noise full PET volumes (128 × 128 × 111). The low-dose and de-noised images were compared in Corridor4DM to the full-dose PET images. We used the default segmentation of the left ventricle to extract the quantitative metrics end-diastolic volume (EDV), end-systolic volume (ESV), and left ventricular ejection fraction (LVEF) from the gated images, and FDG defect extent from the static images. Results. Our de-noising models were able to recover the PET signal for both the static and gated images in either dose-reduction. For the 1% low-dose images, the error is most pronounced for EDV and ESV, where the average underestimation is 25%. No bias was observed using the proposed DL de-noising method. De-noising minimized the outliers found for the 1% and 10% low-dose measurements of LVEF and extent. Accuracy of differential diagnosis based on LVEF threshold was highly improved after de-noising. Conclusion. A significant dose reduction can be achieved for cardiac [18F]FDG images used for viability testing in patients with ischemic heart disease without significant loss of diagnostic accuracy when using our DL model for noise reduction. Both 1% and 10% dose reductions are possible with clinically quantitative metrics comparable to that obtained with a full dose.
KW - Cardiac viability
KW - Convolutional neural network
KW - Deep learning
KW - Low-dose
KW - Pet/ct
UR - http://www.scopus.com/inward/record.url?scp=85101820934&partnerID=8YFLogxK
U2 - 10.1088/1361-6560/abe225
DO - 10.1088/1361-6560/abe225
M3 - Journal article
C2 - 33524958
AN - SCOPUS:85101820934
VL - 66
JO - Physics in Medicine and Biology
JF - Physics in Medicine and Biology
SN - 0031-9155
IS - 5
M1 - 054003
ER -
ID: 303058473