一项研究使用深度学习图像重建来提高极低剂量对比增强腹部 CT 对肝病变患者的图像质量。
A study of using a deep learning image reconstruction to improve the image quality of extremely low-dose contrast-enhanced abdominal CT for patients with hepatic lesions.
机构信息
Department of Radiology, the First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, Shaanxi province, PR China.
GE Healthcare, Computed Tomography Research Center, Beijing, China.
出版信息
Br J Radiol. 2021 Feb 1;94(1118):20201086. doi: 10.1259/bjr.20201086. Epub 2020 Dec 11.
OBJECTIVE
To investigate the feasibility of using deep learning image reconstruction (DLIR) to significantly reduce radiation dose and improve image quality in contrast-enhanced abdominal CT.
METHODS
This was a prospective study. 40 patients with hepatic lesions underwent abdominal CT using routine dose (120kV, noise index (NI) setting of 11 with automatic tube current modulation) in the arterial-phase (AP) and portal-phase (PP), and low dose (NI = 24) in the delayed-phase (DP). All images were reconstructed at 1.25 mm thickness using ASIR-V at 50% strength. In addition, images in DP were reconstructed using DLIR in high setting (DLIR-H). The CT value and standard deviation (SD) of hepatic parenchyma, spleen, paraspinal muscle and lesion were measured. The overall image quality includes subjective noise, sharpness, artifacts and diagnostic confidence were assessed by two radiologists blindly using a 5-point scale (1, unacceptable and 5, excellent). Dose between AP and DP was compared, and image quality among different reconstructions were compared using SPSS20.0.
RESULTS
Compared to AP, DP significantly reduced radiation dose by 76% (0.76 ± 0.09 mSv 3.18 ± 0.48 mSv), DLIR-H DP images had lower image noise (14.08 ± 2.89 HU 16.67 ± 3.74 HU, < 0.001) but similar overall image quality score as the ASIR-V50% AP images (3.88 ± 0.34 4.05 ± 0.44, > 0.05). For the DP images, DLIR-H significantly reduced image noise in hepatic parenchyma, spleen, muscle and lesion to (14.77 ± 2.61 HU, 14.26 ± 2.67 HU, 14.08 ± 2.89 HU and 16.25 ± 4.42 HU) from (24.95 ± 4.32 HU, 25.42 ± 4.99 HU, 23.99 ± 5.26 HU and 27.01 ± 7.11) with ASIR-V50%, respectively (all < 0.001) and improved image quality score (3.88 ± 0.34 2.87 ± 0.53; < 0.05).
CONCLUSION
DLIR-H significantly reduces image noise and generates images with clinically acceptable quality and diagnostic confidence with 76% dose reduction.
ADVANCES IN KNOWLEDGE
(1) DLIR-H yielded a significantly lower image noise, higher CNR and higher overall image quality score and diagnostic confidence than the ASIR-V50% under low signal conditions. (2) Our study demonstrated that at 76% lower radiation dose, the DLIR-H DP images had similar overall image quality to the routine-dose ASIR-V50% AP images.
目的
探讨深度学习图像重建（DLIR）在降低对比增强腹部 CT 辐射剂量、提高图像质量方面的可行性。
方法
这是一项前瞻性研究。40 例肝病变患者行腹部 CT 检查，采用常规剂量（120kV，噪声指数（NI）设置为 11，自动管电流调制）行动脉期（AP）和门静脉期（PP）扫描，低剂量（NI=24）行延迟期（DP）扫描。所有图像均采用 1.25mm 层厚的 ASIR-V 以 50%的强度重建。此外，在 DP 中使用高设置（DLIR-H）进行 DLIR 重建。测量肝实质、脾脏、椎旁肌和病变的 CT 值和标准差（SD）。两名放射科医生采用 5 分制（1，不可接受和 5，优秀）对主观噪声、清晰度、伪影和诊断信心等整体图像质量进行盲法评估。使用 SPSS20.0 比较 AP 和 DP 之间的剂量，以及不同重建之间的图像质量。
结果
与 AP 相比，DP 显著降低了 76%的辐射剂量（0.76±0.09mSv 3.18±0.48mSv），DLIR-H DP 图像的图像噪声更低（14.08±2.89HU 16.67±3.74HU，<0.001），但与 ASIR-V50%AP 图像的整体图像质量评分（3.88±0.34 4.05±0.44，>0.05）相似。对于 DP 图像，DLIR-H 显著降低了肝实质、脾脏、肌肉和病变的图像噪声，分别为（14.77±2.61HU、14.26±2.67HU、14.08±2.89HU 和 16.25±4.42HU）和（24.95±4.32HU、25.42±4.99HU、23.99±5.26HU 和 27.01±7.11HU），分别与 ASIR-V50%相比（均<0.001），并提高了图像质量评分（3.88±0.34 2.87±0.53；<0.05）。
结论
DLIR-H 可显著降低图像噪声，在降低 76%辐射剂量的情况下生成具有临床可接受质量和诊断信心的图像。
知识的进步
（1）在低信号条件下，DLIR-H 生成的图像噪声明显更低、CNR 更高、整体图像质量评分和诊断信心更高。（2）本研究表明，在降低 76%的辐射剂量时，DLIR-H DP 图像的整体图像质量与常规剂量 ASIR-V50%AP 图像相似。
Zotero 插件