Evaluation of image quality of a deep learning image reconstruction algorithm

2019 ◽  
Author(s):  
Meghan Yue ◽  
Jie Tang ◽  
Brian E. Nett ◽  
Jiang Hsieh ◽  
Roy Nilsen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Reconstruction ◽  
Image Quality ◽  
Reconstruction Algorithm ◽  
Image Reconstruction Algorithm

scholarly journals Deep learning versus iterative image reconstruction algorithm for head CT in trauma

2022 ◽  
Author(s):  
Zlatan Alagic ◽  
Jacqueline Diaz Cardenas ◽  
Kolbeinn Halldorsson ◽  
Vitali Grozman ◽  
Stig Wallgren ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Reconstruction ◽  
Image Quality ◽  
Reconstruction Algorithm ◽  
Weighted Kappa ◽  
Trauma Patients ◽  
Reconstruction Algorithms ◽  
Head Ct ◽  
Image Reconstruction Algorithm ◽  
Experienced Reader

Abstract Purpose To compare the image quality between a deep learning–based image reconstruction algorithm (DLIR) and an adaptive statistical iterative reconstruction algorithm (ASiR-V) in noncontrast trauma head CT. Methods Head CT scans from 94 consecutive trauma patients were included. Images were reconstructed with ASiR-V 50% and the DLIR strengths: low (DLIR-L), medium (DLIR-M), and high (DLIR-H). The image quality was assessed quantitatively and qualitatively and compared between the different reconstruction algorithms. Inter-reader agreement was assessed by weighted kappa. Results DLIR-M and DLIR-H demonstrated lower image noise (p < 0.001 for all pairwise comparisons), higher SNR of up to 82.9% (p < 0.001), and higher CNR of up to 53.3% (p < 0.001) compared to ASiR-V. DLIR-H outperformed other DLIR strengths (p ranging from < 0.001 to 0.016). DLIR-M outperformed DLIR-L (p < 0.001) and ASiR-V (p < 0.001). The distribution of reader scores for DLIR-M and DLIR-H shifted towards higher scores compared to DLIR-L and ASiR-V. There was a tendency towards higher scores with increasing DLIR strengths. There were fewer non-diagnostic CT series for DLIR-M and DLIR-H compared to ASiR-V and DLIR-L. No images were graded as non-diagnostic for DLIR-H regarding intracranial hemorrhage. The inter-reader agreement was fair-good between the second most and the less experienced reader, poor-moderate between the most and the less experienced reader, and poor-fair between the most and the second most experienced reader. Conclusion The image quality of trauma head CT series reconstructed with DLIR outperformed those reconstructed with ASiR-V. In particular, DLIR-M and DLIR-H demonstrated significantly improved image quality and fewer non-diagnostic images. The improvement in qualitative image quality was greater for the second most and the less experienced readers compared to the most experienced reader.

Image quality and dose reduction opportunity of deep learning image reconstruction algorithm for CT: a phantom study

2020 ◽  
Vol 30 (7) ◽  
pp. 3951-3959 ◽  
Author(s):  
Joël Greffier ◽  
Aymeric Hamard ◽  
Fabricio Pereira ◽  
Corinne Barrau ◽  
Hugo Pasquier ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Reconstruction ◽  
Image Quality ◽  
Dose Reduction ◽  
Reconstruction Algorithm ◽  
Phantom Study ◽  
Image Reconstruction Algorithm

scholarly journals Plane wave ultrasound imaging using synthetic aperture image reconstruction techniques

2021 ◽  
Author(s):  
Dae-Myoung (Danny) Yang
Keyword(s):  
Image Reconstruction ◽  
Image Quality ◽  
Plane Wave ◽  
Ultrasound Imaging ◽  
Plane Waves ◽  
Reconstruction Algorithm ◽  
Synthetic Aperture ◽  
Depth Of Penetration ◽  
Image Reconstruction Techniques

Ultrasound imaging based on transmitting plane waves (PW) enables ultrafast imaging. Coherent PW compounding ultrasound imaging can reach the image quality of optimal multifocus image. In the image reconstruction, it was assumed that an infinite extent PWs was emitted. In this thesis, we propose a new image reconstruction algorithm – Synthetic-aperture plane-wave (SAPW) imaging – without using this assumption. The SAPW imaging was compared with the PWs imaging in numerical simulations and experimental measurements. The measured RF data in PW imaging was first decoded in the frequency domain using a pseudoinverse algorithm to estimate the RF data Then, SAPW RF data were used to reconstruct images through the standard synthetic transit aperture (STA) method. Main improvements in the image quality of the SAPW imaging in comparison with the PWs imaging are increases in the depth of penetration and the field of view when contrast-to-noise ratio (CNR) was used as a quantitative metric.

scholarly journals Plane wave ultrasound imaging using synthetic aperture image reconstruction techniques

2021 ◽  
Author(s):  
Dae-Myoung (Danny) Yang
Keyword(s):  
Image Reconstruction ◽  
Image Quality ◽  
Plane Wave ◽  
Ultrasound Imaging ◽  
Plane Waves ◽  
Reconstruction Algorithm ◽  
Synthetic Aperture ◽  
Depth Of Penetration ◽  
Image Reconstruction Techniques

Ultrasound imaging based on transmitting plane waves (PW) enables ultrafast imaging. Coherent PW compounding ultrasound imaging can reach the image quality of optimal multifocus image. In the image reconstruction, it was assumed that an infinite extent PWs was emitted. In this thesis, we propose a new image reconstruction algorithm – Synthetic-aperture plane-wave (SAPW) imaging – without using this assumption. The SAPW imaging was compared with the PWs imaging in numerical simulations and experimental measurements. The measured RF data in PW imaging was first decoded in the frequency domain using a pseudoinverse algorithm to estimate the RF data Then, SAPW RF data were used to reconstruct images through the standard synthetic transit aperture (STA) method. Main improvements in the image quality of the SAPW imaging in comparison with the PWs imaging are increases in the depth of penetration and the field of view when contrast-to-noise ratio (CNR) was used as a quantitative metric.

scholarly journals Development of a simple, portable, colorimetric arsenic sensor based on Molybdenum Blue Chemistry

2021 ◽  
Author(s):  
Nevetha Yogarajah
Keyword(s):  
Image Reconstruction ◽  
Image Quality ◽  
Ultrasound Imaging ◽  
Plane Waves ◽  
Reconstruction Algorithm ◽  
Depth Of Penetration ◽  
Molybdenum Blue ◽  
Ultrafast Imaging ◽  
Infinite Extent

Ultrasound imaging based on transmitting plane waves (PW) enables ultrafast imaging. Coherent PW compounding ultrasound imaging can reach the image quality of optimal multifocus image. In the image reconstruction, it was assumed that an infinite extent PWs was emitted. In this thesis, we propose a new image reconstruction algorithm – Synthetic-aperture plane-wave (SAPW) imaging – without using this assumption. The SAPW imaging was compared with the PWs imaging in numerical simulations and experimental measurements. The measured RF data in PW imaging was first decoded in the frequency domain using a pseudoinverse algorithm to estimate the RF data Then, SAPW RF data were used to reconstruct images through the standard synthetic transit aperture (STA) method. Main improvements in the image quality of the SAPW imaging in comparison with the PWs imaging are increases in the depth of penetration and the field of view when contrast-to-noise ratio (CNR) was used as a quantitative metric

Sign in / Sign up

Export Citation Format

Share Document