深度学习重建在儿童脑外伤低剂量颅脑CT扫描中的应用研究  

A study on application of deep learning reconstruction in low-dose brain CT in children with craniocerebral trauma

作　　者：魏伟安 易婷 马秋红[1] 董骁 金科[1] Wei Weian;Yi Ting;Ma Qiuhong;Dong Xiao;Jin Ke(Department of Radiology,Hunan Children′s Hospital,Changsha 410007,China)

机构地区：[1]湖南省儿童医院放射科,长沙410007

出　　处：《中华放射学杂志》2022年第11期1195-1201,共7页Chinese Journal of Radiology

摘　　要：目的探讨深度学习重建(DLR)在儿童低剂量脑外伤CT扫描中的应用价值。方法回顾性分析2020年6月至2021年2月湖南省儿童医院51例脑外伤合并脑出血患儿的低剂量颅脑CT图像, 分别重建成5 mm和1.25 mm两组图像, 每组图像根据不同算法重建6个亚组图像, 分别为3组多模型自适应性迭代重建(ASIR-V)(迭代权重为0、50%、100%)和3组DLR[重建级别为低(L)、中(M)、高(H)]图像。图像质量客观评价参数包括背侧丘脑(灰质)、额叶白质、出血灶的CT值、信噪比(SNR)和灰白质、出血灶对比噪声比(CNR), 以及背景噪声(SD)、颅底伪影SD。主观评价为对图像质量采用5分法进行评分。采用随机区组方差分析和Friedman秩和检验比较DLR与ASIR-V图像的客观参数和主观图像质量评分的差异。采用配对样本t检验和相关样本秩和检验对1.25 mm层厚DLR-H与5 mm层厚ASIR-V50%图像的客观参数和主观评分进行比较。结果 51例患儿颅脑CT的CT容积剂量指数、剂量长度乘积和体型特异性剂量估算值分别为17.7(11.9, 21.1)mGy、248.4(142.2, 338.1)mGy·cm和(15.7±2.8)mGy。同一层厚的DLR与ASIR-V之间的CT值差异有统计学意义(P<0.05)。SNR和CNR随着ASIR-V或DLR的级别升高而逐渐增高, SD随着ASIR-V或DLR的级别升高而逐渐降低, 总体差异均有统计学意义(P均<0.05)。其中, DLR客观参数均优于ASIR-V50%, DLR-H和ASIR-V100%的图像背景SD最低且两者差异无统计学意义, 薄层DLR-H的白质SNR、灰质SNR和灰白质CNR值均优于ASIR-V100%, 差异有统计学意义。随着层厚降低, 图像质量评分下降, 但薄层DLR图像平均主观评分均>3分, 而ASIR-V图像平均主观评分均<3分, 不能满足诊断需求。1.25 mm层厚DLR-H图像的背景和伪影噪声SD均高于5 mm层厚ASIR-V50%图像(t=2.96、2.83, P=0.005、0.007), 其余客观参数和主观评分差异均无统计学意义(P均>0.05)。结论在儿童脑外伤低剂量颅脑CT中, DLR能提高图像�Objective To explore the application value of deep learning reconstruction(DLR)in low-dose brain CT imaging in children with craniocerebral trauma.Methods The CT data of 51 children with craniocerebral trauma complicated with intracerebral hemorrhage who received low dose brain CT were retrospectively collected in Hunan Children′s Hospital between June 2020 and February 2021.All images were reconstructed at 1.25 mm and 5 mm slice thickness utilizing two reconstruction algorithms and divided into six subgroups:ASIR-V with three different blending ratios(0,50%,100%),and DLR with three different reconstruction strengths[low(L),media(M)and high(H)].The objective parameters including CT value,signal to noise ratio(SNR)and contrast to noise ratio(CNR)of dorsal thalamus(grey matter),white matter of frontal lobe and hemorrhagic lesion,as well as basicranial artifact noise(SD)and background SD were measured and calculated.Subjective evaluation was performed with a 5-point scale scoring.Objective parameters and subjective scores were compared among different groups using randomized block analysis of variance and Friedman test,respectively.The objective and subjective differences between 1.25 mm DLR-H and ASIR-V50%images were analyzed using paired samples t-test and correlated sample rank sum test.Results The average CT dose index volume,dose length product and size-specific dose estimate of head CT were 17.7(11.9,21.1)mGy,248.4(142.2,338.1)mGy·cm and(15.7±2.8)mGy.With the same thickness,the difference of CT values between the DLR and ASIR-V groups were stastistically significant(P<0.05).The subjective scores of DLR groups were significantly better than those of ASIR-V;the higher was the reconstruction grade of ASIR-V and DLR,the higher SNR and CNR values and the lower SD value were obtained for each structure(all P<0.05).DLR images showed better objective parameters than ASIR-V50%images.Background SD was lowest on DLR-H and ASIR-V100%images,with no significant difference found between these two groups.Using 1.25 mm thi

关 键 词：儿童 颅脑损伤 体层摄影术 X线计算机 深度学习重建 

分 类 号：R726.5[医药卫生—儿科] R816.1[医药卫生—临床医学]