TY - JOUR
T1 - Retrospective study of deep learning to reduce noise in non-contrast head CT images
AU - Wong, Kelvin K.
AU - Cummock, Jonathon S.
AU - He, Yunjie
AU - Ghosh, Rahul
AU - Volpi, John J.
AU - Wong, Stephen T.C.
N1 - Funding Information:
This work was supported by the T.T. & W.F. Chao Foundation , Houston, TX and the John S Dunn Research Foundation , Houston, TX (S.T.C.W).
Publisher Copyright:
© 2021 The Authors
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2021/12
Y1 - 2021/12
N2 - Purpose: Presented herein is a novel CT denoising method uses a skip residual encoder-decoder framework with group convolutions and a novel loss function to improve the subjective and objective image quality for improved disease detection in patients with acute ischemic stroke (AIS). Materials and methods: In this retrospective study, confirmed AIS patients with full-dose NCCT head scans were randomly selected from a stroke registry between 2016 and 2020. 325 patients (67 ± 15 years, 176 men) were included. 18 patients each with 4–7 NCCTs performed within 5-day timeframe (83 total scans) were used for model training; 307 patients each with 1–4 NCCTs performed within 5-day timeframe (380 total scans) were used for hold-out testing. In the training group, a mean CT was created from the patient's co-registered scans for each input CT to train a rotation-reflection equivariant U-Net with skip and residual connections, as well as a group convolutional neural network (SRED-GCNN) using a custom loss function to remove image noise. Denoising performance was compared to the standard Block-matching and 3D filtering (BM3D) method and RED-CNN quantitatively and visually. Signal-to-noise ratio (SNR) and contrast-to-noise (CNR) were measured in manually drawn regions-of-interest in grey matter (GM), white matter (WM) and deep grey matter (DG). Visual comparison and impact on spatial resolution were assessed through phantom images. Results: SRED-GCNN reduced the original CT image noise significantly better than BM3D, with SNR improvements in GM, WM, and DG by 2.47x, 2.83x, and 2.64x respectively and CNR improvements in DG/WM and GM/WM by 2.30x and 2.16x respectively. Compared to the proposed SRED-GCNN, RED-CNN reduces noise effectively though the results are visibly blurred. Scans denoised by the SRED-GCNN are shown to be visually clearer with preserved anatomy. Conclusion: The proposed SRED-GCNN model significantly reduces image noise and improves signal-to-noise and contrast-to-noise ratios in 380 unseen head NCCT cases.
AB - Purpose: Presented herein is a novel CT denoising method uses a skip residual encoder-decoder framework with group convolutions and a novel loss function to improve the subjective and objective image quality for improved disease detection in patients with acute ischemic stroke (AIS). Materials and methods: In this retrospective study, confirmed AIS patients with full-dose NCCT head scans were randomly selected from a stroke registry between 2016 and 2020. 325 patients (67 ± 15 years, 176 men) were included. 18 patients each with 4–7 NCCTs performed within 5-day timeframe (83 total scans) were used for model training; 307 patients each with 1–4 NCCTs performed within 5-day timeframe (380 total scans) were used for hold-out testing. In the training group, a mean CT was created from the patient's co-registered scans for each input CT to train a rotation-reflection equivariant U-Net with skip and residual connections, as well as a group convolutional neural network (SRED-GCNN) using a custom loss function to remove image noise. Denoising performance was compared to the standard Block-matching and 3D filtering (BM3D) method and RED-CNN quantitatively and visually. Signal-to-noise ratio (SNR) and contrast-to-noise (CNR) were measured in manually drawn regions-of-interest in grey matter (GM), white matter (WM) and deep grey matter (DG). Visual comparison and impact on spatial resolution were assessed through phantom images. Results: SRED-GCNN reduced the original CT image noise significantly better than BM3D, with SNR improvements in GM, WM, and DG by 2.47x, 2.83x, and 2.64x respectively and CNR improvements in DG/WM and GM/WM by 2.30x and 2.16x respectively. Compared to the proposed SRED-GCNN, RED-CNN reduces noise effectively though the results are visibly blurred. Scans denoised by the SRED-GCNN are shown to be visually clearer with preserved anatomy. Conclusion: The proposed SRED-GCNN model significantly reduces image noise and improves signal-to-noise and contrast-to-noise ratios in 380 unseen head NCCT cases.
KW - Acute ischemic stroke
KW - CT denoising
KW - Deep learning
KW - Non-contrast head CT
UR - http://www.scopus.com/inward/record.url?scp=85116880171&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85116880171&partnerID=8YFLogxK
U2 - 10.1016/j.compmedimag.2021.101996
DO - 10.1016/j.compmedimag.2021.101996
M3 - Article
C2 - 34637998
AN - SCOPUS:85116880171
SN - 0895-6111
VL - 94
JO - Computerized Medical Imaging and Graphics
JF - Computerized Medical Imaging and Graphics
M1 - 101996
ER -