Deep learning image reconstruction algorithm for carotid dual-energy computed tomography angiography: evaluation of image quality and diagnostic performance

Abstract

Objectives To evaluate image quality and diagnostic performance of carotid dual-energy computed tomography angiography (DECTA) using deep learning image reconstruction (DLIR) compared with images using adaptive statistical iterative reconstruction-Veo (ASIR-V). Methods Carotid DECTA datasets of 28 consecutive patients were reconstructed at 50 keV using DLIR at low, medium, and high levels (DLIR-L, DLIR-M, and DLIR-H) and 80% ASIR-V algorithms. Mean attenuation, image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) at different levels of arteries were measured and calculated. Image quality for noise and texture, depiction of arteries, and diagnostic performance toward carotid plaques were assessed subjectively by two radiologists. Quantitative and qualitative parameters were compared between the ASIR-V, DLIR-L, DLIR-M, and DLIR-H groups. Results The image noise at aorta and common carotid artery, SNR, and CNR at all level arteries of DLIR-H images were significantly higher than those of ASIR-V images (p = 0.000–0.040). The quantitative analysis of DLIR-L and DLIR-M showed comparable denoise capability with ASIR-V. The overall image quality (p = 0.000) and image noise (p = 0.000–0.014) were significantly better in the DLIR-M and DLIR-H images. The image texture was improved by DLR at all level compared to ASIR-V images (p = 0.000–0.008). Depictions of head and neck arteries and diagnostic performance were comparable between four groups (p > 0.05). Conclusions Compared with 80% ASIR-V, we recommend DLIR-H for clinical carotid DECTA reconstruction, which can significantly improve the image quality of carotid DECTA at 50 keV but maintain a desirable diagnostic performance and arterial depiction.

Systematic Review on Learning-Based Spectral CT

“…Xu et al [261] reached a similar conclusion, and particularly they found that 40 keV VMIs from DLIR poses better CNR and similar or improved image quality compared to 50 keV VMI from hybrid iterative reconstruction, suggesting that 40 keV VMI DLIR could be a new standard for routine low-keV VMI reconstruction. The study for carotid DECT angiography by Jiang et al [262] also supports the conclusion that DLIR improves the image quality and diagnostic performance of VMIs compared to hybrid iterative reconstruction. This superiority is further confirmed in DECT angiography with reduced iodine dose (200 mgI/kg) in terms of image quality and arterial depiction by Noda et al [243].…”

Application of deep learning image reconstruction-high algorithm in one-stop coronary and carotid-cerebrovascular CT angiography with low radiation and contrast doses

“…Till now, only a few studies have been done to explore the application CTA images of DLIR in carotid and cerebrovascular vessel under lower radiation and contrast dose settings. Also, these studies could not reach a further decrease in image noise compared with the standard-dose protocol with ASIR-V algorithm ( 20 , 38 ). Even if a mean subjective score of 4.18 in our study proved that our carotid and cerebrovascular images were able to meet the diagnostic criteria, further studies to validate its impact on diagnostic accuracy are warranted to confirm its efficacy.…”

“…The introduction of deep learning image reconstruction (DLIR) algorithm, incorporating a convolutional neural network, has brought new hope for decreasing image noise, and thus optimizing image quality with a more balanced spatial resolution for CTA ( 18 , 19 ). DLIR provides three selectable strength levels (low, medium and high), and DLIR-high (DLIR-H) has been proved to gain the highest ability for reducing image noise while maintaining spatial resolution of images reasonably well ( 20 - 22 ). In our recent study, compared with an adaptive statistical iterative reconstruction-V (ASIR-V) based protocol, the combination of DLIR-H algorithm and low tube voltage for coronary CTA demonstrated superiority in achieving higher image quality as well as significantly lower radiation and contrast dose ( 23 ).…”

CT image denoising methods for image quality improvement and radiation dose reduction

“… 150 , 151 with the remaining approaches including filter‐based methods as well as hybrid methods. 152 , 153 , 154 , 155 , 156 , 157 To be noted that some models are originally developed, 61 , 62 , 65 , 66 , 68 , 70 , 72 , 73 , 77 , 122 , 153 while some are developed by modifying original models through modifying loss functions, or layers, or extending original models to different domains. 60 , 63 , 64 , 69 , 71 , 72 , 74 , 75 , 76 , 78 , 82 , 84 , 102 , 121 , 123 , 124 , 125 , 147 , 150 , 151 , 152 , 155 , 158 …”