新一代基于模型的迭代重建在低剂量上腹部CT中的应用

Application of new model-based iterative reconstruction in low-dose upper abdominal CT

目的比较自适应统计迭代重建(ASIR)、常规基于模型的迭代重建(MBIRc)、新一代基于模型的迭代重建(MBIRn)中优化低密度对比设置的MBIRNR403种算法对低剂量上腹部CT图像质量的影响。方法采用CT扫描静止状态下水模,比较0.625 mm层厚时滤波反投影算法(FBP)、ASIR、MBIRc和MBIRNR40的空间分辨率和密度分辨率。1年内接受2次腹部增强CT扫描受检者60例,初次检查采用常规辐射剂量(噪声指数=10)扫描,FBP重建。复查时采用低辐射剂量方案(噪声指数=20)扫描,分别采用标准算法ASIR、MBIRc和MBIRNR40三种方法重建为0.625 mm层厚的图像后进行对比分析。测量皮下脂肪、背部肌肉、肝脾实质CT值和噪声,计算以皮下脂肪为背景的肝脾实质CNR,采用单因素方差分析比较各重建算法噪声和CNR。由2名放射科医师以常规剂量FBP重建为基础,采用半定量目测评分法盲法进行噪声和细节结构、病变边缘清晰度评分,比较主观评分差异,评价观察者间一致性。结果体模研究提示MBIRc空间分辨率最高,MBIRNR40密度分辨率最高。临床研究显示初次检查剂量长度乘积(DLP)为(368.03±146.25)mGy·cm,有效剂量(ED)为(5.52±2.19)mSv;复查时DLP为(93.18±41.21)mGy.cm,ED为(1.40±0.62)mSv,分别下降约74.68%和74.64%。MBIRNR40重建图像肌肉、脂肪噪声低于MBIRc、ASIR重建和常规剂量FBP重建(P均<0.05)。MBIRNR40重建图像肝脾CNR大于MBIRc、ASIR重建和常规剂量FBP重建(P均<0.05)。2名放射科医师主观评分一致性优良。低剂量MBIRNR40主观图像噪声最低、显示上腹部细节结构和病变边缘特征最清晰,优于MBIRc,MBIRc优于常规剂量FBP,低剂量ASIR最差,差异均有统计学意义(P均<0.05)。结论减少辐射剂量约75%低剂量上腹部成像时,MBIR重建图像质量优于ASIR、MBIRc重建图像及常规剂量FBP图像。

Objective To compare the effect on image quality of low-dose upper abdominal CT reconstructed with the new version of model-based iterative reconstruction （MBIRn） focused on low-contrast resolution （MBIRNR40）, conventional model-based iterative reconstruction （MBIRc）, adaptive statistical iterative reconstruction （ASIR） and routine-dose CT reconstructed with filtered back projection （FBP）. Methods Water plantom at rest was scanned with CT, and spatial resolution and density resolution were compared among FBP, ASIR, MBIRc, and MBIRNR40. Sixty patients with 2 times CT in the upper abdomen within a year were enrolled. The initial examination was acquired at a standard radiation dose （noise index[NI] of 10 HU） and reconstructed with the conventional FBP algorithm. The follow-up scan was acquired at a low-dose （NI=20 HU） and reconstructed with the standard ASIR, MBIRc and MBIRNR40. All images were obtained with 0.625 mm slice thickness. CT values and noise of fat, muscle as well as the liver and kidney parenchyma were measured and CNR of liver and kidney parenchyma using the fat SD as background image noise were calculated. Two radiologists independently graded images for noise, sharpness of details of structures and lesion. The quantitative image quality scores of different reconstructions were analyzed with one-way ANOVA using FBP reconstruction as reference of standard. The degree of interobserver consistency was evaluated using Kappa test. Results The phantom study revealed the highest spatial resolution with MBIRc and highest density resolution with MBIRNR40 among all reconstructions. The dose-length product and radiation dose for the first inspection was （93.18±41.21）mGy·cm, （1.40±0.62）mSv, respectively, and were （368.03±146.25）mGy·cm, （5.52±2.19）mSv for the second inspection, representing an approximate overall dose reduction of 74.68% and 74.64%. The mean image noise of muscle and fat for MBIRNR40 was significantly lower than that of MBIR, ASIR and FBP（P 〈 0.05）. The mean CNR values of liver and spleen for MBIRNR40 were significantly higher than that of ASIR, MBIRc and FBP （P 〈 0.05）. Two radiologists had a good subjective score consistency. Low-dose MBIRNR40 subjective image noise was the lowest, showing the most detailed on the upper abdominal detail structure and lesion edge, better than MBIRc, MBIRc was superior to routine-dose FBP, low dose ASIR was worst, the difference was statistically significant （P 〈 0.05）. Conclusion With 75% dose reduction in upper abdominal CT, the MBIRNR40 can provide well objective and subjective image quality than MBIRc and ASIR40, and the routine-dose FBP.