| 0 | 0 | 8 |
| 下载次数 | 被引频次 | 阅读次数 |
目的 探讨深度学习重建算法（DLIR）在超低剂量CT(ULDCT)条件下对慢性阻塞性肺疾病（COPD）患者肺气肿定量分析的准确性及图像质量的影响。方法 前瞻性纳入我院COPD患者80例。所有患者均接受肺功能、标准剂量CT(SDCT)和ULDCT扫描。SDCT采用滤波反投影（FBP）重建，ULDCT分别采用FBP、自适应统计迭代重建-V(ASIR-V)30%、60%、90%以及低、中、高强度深度学习重建（DLIR-L、DLIR-M、DLIR-H），共获得8组图像。将图像导入CT影像辅助检测软件进行分析，测量全肺容积（LV）、肺气肿指数（EI）、平均肺密度（MLD）、肺密度第15百分位数（PD15）。测量气管和肺动脉噪声[标准差（SD）]，由两名医师采用5分制对图像质量进行主观评分。比较各组间定量参数、图像噪声及主观评分的差异，记录SDCT与ULDCT的辐射剂量。采用Spearman相关分析评估各组图像EI与肺功能指标的相关性。结果 ULDCT的有效辐射剂量为（0.25±0.15）mSv，较SDCT降低约93.62%(P<0.001)。各组图像的LV和MLD无统计学差异（P>0.05）。ULDCT-ASIRV90%组和ULDCT-DLIR-M组的EI及PD15与SDCT-FBP组相似，差异无统计学意义（均P>0.05）。在ULDCT各组中，DLIR-M组的EI与第1秒用力呼气容积与用力肺活量比值和第1秒用力呼气容积占预计值百分比的相关性最好，且与SDCT-FBP组最接近。ULDCT-ASIR-V90%组和ULDCT-DLIR-M组的肺动脉噪声与SDCT-FBP组比较无统计学差异（P=1.000）。ULDCT-DLIR-M组和ULDCT-DLIR-H组的主观评分与SDCT-FBP组比较，差异无统计学意义（均P=1.00）。Bland-Altman分析显示，ULDCT-DLIR-M与SDCT-FBP组间对EI和PD15测量一致性较好。结论 ULDCT结合DLIR-M重建可用于COPD患者的肺气肿定量分析，其定量准确性及图像质量与SDCT-FBP相当，且能大幅度降低辐射剂量。
Abstract：Objective To investigate the accuracy of quantitative emphysema analysis and image quality using deep learning image reconstruction(DLIR)of ultra-low-dose chest CT(ULDCT)in patients with chronic obstructive pulmonary disease(COPD).Methods Eighty patients with COPD were prospectively enrolled and underwent pulmonary function testing, standard-dose chest CT(SDCT), and ULDCT. The SDCT images were reconstructed with filtered back projection(FBP). The ULDCT images were reconstructed using FBP, adaptive statistical iterative reconstruction-V(ASIR-V)at 30%, 60%, and 90%, as well as low-(DLIRL), medium-(DLIR-M), and high-strength(DLIR-H) DLIR. A total of 8 sets of images were obtained. The images were analyzed using computer-aided detection software. The lung volume(LV), emphysema index(EI), mean lung density(MLD), and 15th percentile of lung density(PD15)were measured. The image noise(standard deviation, SD)in the trachea and pulmonary artery was measured. Two radiologists independently scored the image quality using a 5-point scale. Quantitative parameters, image noise,and subjective scores as well as the radiation doses between SDCT and ULDCT were compared. Spearman correlation analysis was used to evaluate the correlation between the EI and pulmonary function testing parameters including forced expiratory volume in 1 second(FEV1)and forced vital capacity(FVC)across image sets. Results The effective radiation dose of ULDCT[(0.25 ± 0.15 mSv)]was 93.62% and significantly lower than that of SDCT(P<0.001). No significant differences were observed in the LV or MLD among all groups(P>0.05). The EI and PD15 values in the ULDCT-ASIR-V90% and ULDCT-DLIR-M groups were not significantly different from those in the SDCT-FBP group(both P>0.05). Among all ULDCT groups, the DLIR-M group showed the strongest correlations between EI and FEV1:FVC ratio as well as between EI and FEV1 as a percentage of predicted value, with correlation coefficients closest to those of the SDCT-FBP group. Pulmonary artery noise in the ULDCT-ASIR-V90% and ULDCT-DLIR-M groups showed no significant difference compared with the SDCT-FBP group(P=1.000). Subjective scores of the ULDCT-DLIR-M and ULDCT-DLIR-H groups were also not significantly different from that of SDCT-FBP group(both P=1.00). Bland-Altman analysis demonstrated good agreement in measuring EI and PD15 between the ULDCT-DLIR-M and SDCT-FBP groups. Conclusion In patients with COPD,the ULDCT combined with DLIR-M reconstruction for quantitative emphysema analysis is accurate and has lower radiation dose and similar image quality compared to those of SDCT-FBP.
[1]AgustíA, Celli B R, Criner G J, et al. Global Initiative for Chronic Obstructive Lung Disease 2023 Report:GOLD executive summary[J]. Eur Respir J, 2023,61(4):2300239.
[2]中华医学会,中华医学会杂志社,中华医学会全科医学分会,等.中国慢性阻塞性肺疾病基层诊疗与管理指南（2024年）[J].中华全科医师杂志, 2024,23(6):578-602.
[3]Wiedbrauck D, Karczewski M, Schoenberg S O, et al. Artificial intelligence-based emphysema quantification in routine chest computed tomography:correlation with spirometry and visual emphysema grading[J]. J Comput Assist Tomogr , 2024 , 48(3):388-393.
[4]Zou J H, Sun T, Song X H, et al. Distributions and trends of the global burden of COPD attributable to risk factors by SDI,age, and sex from 1990 to 2019:a systematic analysis of GBD2019 data[J]. Respir Res, 2022,23(1):90.
[5]阴玮灵,沈敏,牛媛,等.双气相定量CT的肺空气体积比值对吸烟者慢性阻塞性肺病的诊断价值[J].影像诊断与介入放射学, 2023,32(1):43-48.
[6]Labaki W W, Xia M, Murray S, et al. Quantitative emphysema on low-dose CT Imaging of the chest and risk of lung cancer and airflow obstruction:an analysis of the National Lung Screening Trial[J]. Chest, 2021,159(5):1812-1820.
[7]Du Y H, Sidorenkov G, Heuvelmans M A, et al. Costeffectiveness of lung cancer screening with low-dose computed tomography in heavy smokers:a microsimulation modelling study[J]. Eur J Cancer, 2020,135:121-129.
[8]Amundson W H, Swanson E J, Petersen A, et al. Quantification of perinodular emphysema in high-risk patients offers no benefit in lung nodule risk-stratification of malignancy potential[J]. J Thorac Imaging, 2020,35(2):108-114.
[9]Bosch de Basea M, Thierry-Chef I, Harbron R, et al. Risk of hematological malignancies from CT radiation exposure in children, adolescents and young adults[J]. Nat Med, 2023,29(12):3111-3119.
[10]Prasad K N, Cole W C, Haase G M. Radiation protection in humans:extending the concept of as low as reasonably achievable(ALARA)from dose to biological damage[J]. Br J Radiol, 2004,77(914):97-99.
[11]Wisselink H J, Pelgrim G J, Rook M, et al. Ultra-low-dose CT combined with noise reduction techniques for quantification of emphysema in COPD patients:an intra-individual comparison study with standard-dose CT[J]. Eur J Radiol, 2021,138:109646.
[12]Yeom J A, Kim K U, Hwang M, et al. Emphysema quantification using ultra-low-dose chest CT:efficacy of deep learning-based image reconstruction[J]. Medicina(Kaunas), 2022,58(7):939.
[13]Wisselink H J, Pelgrim G J, Rook M, et al. Potential for dose reduction in CT emphysema densitometry with post-scan noise reduction:a phantom study[J]. Br J Radiol, 2020,93(1105):20181019.
[14]Hata A, Yanagawa M, Kikuchi N, et al. Pulmonary emphysema quantification on ultra-low-dose computed tomography using model-based iterative reconstruction with or without lung setting[J]. J Comput Assist Tomogr, 2018,42(5):760-766.
[15]Kim C, Lee K Y, Shin C, et al. Comparison of filtered back projection, hybrid iterative reconstruction, model-based iterative reconstruction, and virtual monoenergetic reconstruction images at both low-and standard-dose settings in measurement of emphysema volume and airway wall thickness:a CT phantom study[J]. Korean J Radiol, 2018,19(4):809-817.
[16]Kim J H, Yoon H J, Lee E, et al. Validation of deep-learning image reconstruction for low-dose chest computed tomography scan:emphasis on image quality and noise[J]. Korean J Radiol,2021,22(1):131-138.
[17]Jiang B B, Li N Y, Shi X M, et al. Deep learning reconstruction shows better lung nodule detection for ultra-low-dose chest CT[J]. Radiology, 2022,303(1):202-212.
[18]Lynch D A, Al-Qaisi M A. Quantitative computed tomography in chronic obstructive pulmonary disease[J]. J Thorac Imaging,2013,28(5):284-290.
[19]Trattner S, Halliburton S, Thompson C M, et al. Cardiacspecific conversion factors to estimate radiation effective dose from dose-length product in computed tomography[J]. JACC Cardiovasc Imaging, 2018,11(1):64-74.
[20]Madani A, Zanen J, de Maertelaer V, et al. Pulmonary emphysema:objective quantification at multi-detector row CT:comparison with macroscopic and microscopic morphometry[J].Radiology, 2006,238(3):1036-1043.
[21]Ostridge K, Wilkinson T M. Present and future utility of computed tomography scanning in the assessment and management of COPD[J]. Eur Respir J, 2016,48(1):216-228.
[22]Bakker J T, Klooster K, Vliegenthart R, et al. Measuring pulmonary function in COPD using quantitative chest computed tomography analysis[J]. Eur Respir Rev, 2021,30(161):210031.
[23]Johannessen A, Skorge T D, Bottai M, et al. Mortality by level of emphysema and airway wall thickness[J]. Am J Respir Crit Care Med, 2013,187(6):602-608.
[24]Perisinakis K, Seimenis I, Tzedakis A, et al. Radiation burden and associated cancer risk for a typical population to be screened for lung cancer with low-dose CT:a phantom study[J]. Eur Radiol, 2018,28(10):4370-4378.
[25]den Harder A M, de Boer E, Lagerweij S J, et al. Emphysema quantification using chest CT:influence of radiation dose reduction and reconstruction technique[J]. Eur Radiol Exp ,2018,2(1):30.
[26]Geyer L L, Schoepf U J, Meinel F G, et al. State of the art:iterative CT reconstruction techniques[J]. Radiology, 2015,276(2):339-357.
[27]Martin S P, Gariani J, Hachulla A L, et al. Impact of iterative reconstructions on objective and subjective emphysema assessment with computed tomography:a prospective study[J].Eur Radiol, 2017,27(7):2950-2956.
[28]Messerli M, Ottilinger T, Warschkow R, et al. Emphysema quantification and lung volumetry in chest X-ray equivalent ultralow dose CT:intra-individual comparison with standard dose CT[J]. Eur J Radiol, 2017,91:1-9.
[29]Hochhegger B, Irion K L, Marchiori E, et al. Reconstruction algorithms influence the follow-up variability in the longitudinal CT emphysema index measurements[J]. Korean J Radiol, 2011 ,12(2):169-175.
[30]Pompe E, Strand M, van Rikxoort E M, et al. Five-year progression of emphysema and air trapping at CT in smokers with and those without chronic obstructive pulmonary disease:results from the COPDGene study[J]. Radiology, 2020,295(1):218-226.
基本信息:
中图分类号:R563.9;R816.4
引用信息:
[1]马光明,谭辉,樊秋菊,等.深度学习重建对慢性阻塞性肺疾病患者超低剂量CT肺气肿定量分析的影响[J].影像诊断与介入放射学,2026,35(05):358-366.
基金信息:
陕西省重点研发计划项目（2026SF-YBXM-512）; 陕西中医药大学附属医院“岐黄名医”人才能力提升工程项目（260774）
2026-10-25
2026-10-25