Department of Medical Imaging, CHU Nîmes, Univ Montpellier, Nîmes Medical Imaging Group, EA 2992, Bd. Prof Robert Debré, 30029, Nîmes Cedex 9, France.
University Lyon, INSA-Lyon, University Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS UMR 5220, U1206, F-69621, 7 Avenue Jean Capelle O, 69100, Villeurbanne, France.
Eur Radiol. 2023 Jan;33(1):699-710. doi: 10.1007/s00330-022-09003-y. Epub 2022 Jul 21.
To assess the impact of a new artificial intelligence deep-learning reconstruction (Precise Image; AI-DLR) algorithm on image quality against a hybrid iterative reconstruction (IR) algorithm in abdominal CT for different clinical indications.
Acquisitions on phantoms were performed at 5 dose levels (CTDI: 13/11/9/6/1.8 mGy). Raw data were reconstructed using level 4 of iDose (i4) and 3 levels of AI-DLR (Smoother/Smooth/Standard). Noise power spectrum (NPS), task-based transfer function (TTF) and detectability index (d') were computed: d' modelled detection of a liver metastasis (LM) and hepatocellular carcinoma at portal (HCCp) and arterial (HCCa) phases. Image quality was subjectively assessed on an anthropomorphic phantom by 2 radiologists.
From Standard to Smoother levels, noise magnitude and average NPS spatial frequency decreased and the detectability (d') of all simulated lesions increased. For both inserts, TTF values were similar for all three AI-DLR levels from 13 to 6 mGy but decreased from Standard to Smoother levels at 1.8 mGy. Compared to the i4 used in clinical practice, d' values were higher using the Smoother and Smooth levels and close for the Standard level. For all dose levels, except at 1.8 mGy, radiologists considered images satisfactory for clinical use for the 3 levels of AI-DLR, but rated images too smooth using the Smoother level.
Use of the Smooth and Smoother levels of AI-DLR reduces the image noise and improves the detectability of lesions and spatial resolution for standard and low-dose levels. Using the Smooth level is apparently the best compromise between the lowest dose level and adequate image quality.
• Evaluation of the impact of a new artificial intelligence deep-learning reconstruction (AI-DLR) on image quality and dose compared to a hybrid iterative reconstruction (IR) algorithm. • The Smooth and Smoother levels of AI-DLR reduced the image noise and improved the detectability of lesions and spatial resolution for standard and low-dose levels. • The Smooth level seems the best compromise between the lowest dose level and adequate image quality.
评估一种新的人工智能深度学习重建（Precise Image；AI-DLR）算法在腹部 CT 不同临床适应证下对图像质量的影响，与混合迭代重建（IR）算法进行对比。
在 5 个剂量水平（CTDI：13/11/9/6/1.8 mGy）下对体模进行采集。使用 iDose 第 4 级（i4）和 3 个 AI-DLR 级别（Smoother/Smooth/Standard）重建原始数据。计算噪声功率谱（NPS）、基于任务的传递函数（TTF）和可检测性指数（d'）：d' 用于模拟肝转移（LM）和门脉期（HCCp）和动脉期（HCCa）肝癌的检测。两名放射科医生对拟人化体模进行主观评估图像质量。
从 Standard 到 Smoother 级别，噪声幅度和平均 NPS 空间频率降低，所有模拟病变的可检测性（d'）增加。对于两个插件，在 13 至 6 mGy 时，所有三个 AI-DLR 水平的 TTF 值相似，但在 1.8 mGy 时从 Standard 降低到 Smoother 级别。与临床实践中使用的 i4 相比，在所有剂量水平下，Smoother 和 Smooth 水平的 d' 值更高，而 Standard 水平接近。除了 1.8 mGy 之外，对于所有剂量水平，放射科医生认为 3 个 AI-DLR 水平的图像都可用于临床使用，但认为使用 Smoother 水平时图像过于平滑。
使用 AI-DLR 的 Smooth 和 Smoother 水平可降低图像噪声并提高标准和低剂量水平的病变检测率和空间分辨率。使用 Smooth 水平显然是在最低剂量水平和足够的图像质量之间的最佳折衷方案。
评估一种新的人工智能深度学习重建（AI-DLR）对图像质量和剂量的影响，与混合迭代重建（IR）算法进行对比。
AI-DLR 的 Smooth 和 Smoother 水平可降低图像噪声并提高标准和低剂量水平的病变检测率和空间分辨率。
Smooth 水平似乎是在最低剂量水平和足够的图像质量之间的最佳折衷方案。
