Deep Learning De-Noising Improves CT Perfusion Image Quality in the Setting of Lower Contrast Dosing: A Feasibility Study.

Journal

AJNR. American journal of neuroradiology
ISSN: 1936-959X
Titre abrégé: AJNR Am J Neuroradiol
Pays: United States
ID NLM: 8003708

Informations de publication

Date de publication:
06 Jun 2024
Historique:
received: 01 04 2024
accepted: 24 05 2024
medline: 7 6 2024
pubmed: 7 6 2024
entrez: 6 6 2024
Statut: aheadofprint

Résumé

Considering recent iodinated contrast media (ICM) shortages, this study compared reduced ICM and standard dose CTP acquisitions, and the impact of deep learning (DL)-denoising on CTP image quality in preclinical and clinical studies. Twelve swine underwent 9 CTP exams each, performed at combinations of 3 different X-ray (37, 67, and 127mAs) and ICM doses (10, 15, and 20mL). Clinical CTP acquisitions performed before and during the ICM shortage and protocol change (from 40 mL to 30 mL) were retrospectively included. Eleven patients with reduced ICM dose and 11 propensity-score-matched controls with standard ICM dose were included. A Residual Encoder-Decoder Convolutional-Neural-Network (RED-CNN) was trained for CTP denoising using K-space-Weighted Image Average (KWIA) filtered CTP images as the target. The standard, RED-CNN denoised, and KWIA noise-filtered images for animal and human studies were compared for quantitative SNR and qualitative image evaluation. The SNR of animal CTP images decreased with reductions in ICM and mAs doses. Contrast dose reduction had a greater effect on SNR than mAs reduction. Noise-filtering by KWIA and RED-CNN denoising progressively improved SNR of CTP maps, with RED-CNN resulting in the highest SNR. The SNR of clinical CTP images was generally lower with reduced ICM dose, which was improved by KWIA and RED-CNN denoising (p<0.05). Qualitative readings consistently rated RED-CNN denoised CTP as best quality, followed by KWIA and then standard CTP images. DL-denoising can improve image quality for low ICM CTP protocols, and could approximate standard ICM dose CTP, in addition to potentially improving image quality for low mAs acquisitions. ICM=iodinated contrast media; DL=deep learning; KWIA=k-space weighted image average; LCD=low-contrast dose; SCD=standard contrast dose; RED-CNN=Residual Encoder-Decoder Convolutional Neural Network; PSNR=Peak Signal to Noise Ratio; RMSE=Root Mean Squared Error; SSIM=Structural Similarity Index.

Sections du résumé

BACKGROUND AND PURPOSE OBJECTIVE
Considering recent iodinated contrast media (ICM) shortages, this study compared reduced ICM and standard dose CTP acquisitions, and the impact of deep learning (DL)-denoising on CTP image quality in preclinical and clinical studies.
MATERIALS AND METHODS METHODS
Twelve swine underwent 9 CTP exams each, performed at combinations of 3 different X-ray (37, 67, and 127mAs) and ICM doses (10, 15, and 20mL). Clinical CTP acquisitions performed before and during the ICM shortage and protocol change (from 40 mL to 30 mL) were retrospectively included. Eleven patients with reduced ICM dose and 11 propensity-score-matched controls with standard ICM dose were included. A Residual Encoder-Decoder Convolutional-Neural-Network (RED-CNN) was trained for CTP denoising using K-space-Weighted Image Average (KWIA) filtered CTP images as the target. The standard, RED-CNN denoised, and KWIA noise-filtered images for animal and human studies were compared for quantitative SNR and qualitative image evaluation.
RESULTS RESULTS
The SNR of animal CTP images decreased with reductions in ICM and mAs doses. Contrast dose reduction had a greater effect on SNR than mAs reduction. Noise-filtering by KWIA and RED-CNN denoising progressively improved SNR of CTP maps, with RED-CNN resulting in the highest SNR. The SNR of clinical CTP images was generally lower with reduced ICM dose, which was improved by KWIA and RED-CNN denoising (p<0.05). Qualitative readings consistently rated RED-CNN denoised CTP as best quality, followed by KWIA and then standard CTP images.
CONCLUSIONS CONCLUSIONS
DL-denoising can improve image quality for low ICM CTP protocols, and could approximate standard ICM dose CTP, in addition to potentially improving image quality for low mAs acquisitions.
ABBREVIATIONS BACKGROUND
ICM=iodinated contrast media; DL=deep learning; KWIA=k-space weighted image average; LCD=low-contrast dose; SCD=standard contrast dose; RED-CNN=Residual Encoder-Decoder Convolutional Neural Network; PSNR=Peak Signal to Noise Ratio; RMSE=Root Mean Squared Error; SSIM=Structural Similarity Index.

Identifiants

DOI: 10.3174/ajnr.A8367 PMID: 38844370
pubmed: 38844370
pii: ajnr.A8367
doi: 10.3174/ajnr.A8367
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

© 2024 by American Journal of Neuroradiology.

Auteurs

Mahmud Mossa-Basha (M)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Chengcheng Zhu (C)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Tanya Pandhi (T)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Steve Mendoza (S)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Javid Azadbakht (J)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Ahmed Safwat (A)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Dean Homen (D)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Carlos Zamora (C)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Dinesh Kumar Gnanasekaran (DK)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Ruiyue Peng (R)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Steven Cen (S)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Vinay Duddalwar (V)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Jeffry R Alger (JR)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Danny J J Wang (DJJ)

From the Department of Radiology of University of Washington School of Medicine, Seattle, WA, USA (M.M.B., C.Z., A.S.), Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (T.P., S.M., D.K.S., D.J.J.W.), Tabesh Radiology and Sonography, Tehran, Iran (J.A.), University of North Carolina Department of Radiology, Chapel Hill, NC, USA (D.H., C.Z.), Hura Imaging Inc., Los Angeles, CA, USA (R.P., J.R.A.), Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA (S.C., V.D., D.J.J.W.).

Classifications MeSH