深度学习迭代重建算法优化儿童头颅CT图像噪声和图像纹理的可行性  

Feasibility of Deep Learning Algorithm to Optimize the Noise and Texture of Children′s Head CT

作　　者：田宏伟[1] 彭芸[1] 刘道永[1] 李昊岩 刘勇[1] 洪天予 孙记航[1] TIAN Hongwei;PENG Yun;LIU Daoyong;LI Haoyan;LIU Yong;HONG Tianyu;SUN Jihang(Imaging Center,Beijing Children′s Hospital,Capital Medical University,National Center for Children′s Health,Beijing 100045,China)

机构地区：[1]首都医科大学附属北京儿童医院影像中心,北京100045

出　　处：《中国医学影像学杂志》2024年第2期193-198,共6页Chinese Journal of Medical Imaging

摘　　要：目的评价深度学习迭代重建(DLIR)算法与常规自适应迭代重建(ASIR-V)算法对儿童头颅外伤CT图像噪声和图像纹理的优化程度及图像显示效果的差异。资料与方法回顾性选取2020年12月7—11日首都医科大学附属北京儿童医院影像中心80例儿童头颅CT,扫描方案为低辐射剂量轴扫,电压120 kV,电流150~220 mA。将得到的原始数据重建为5 mm厚层与0.625 mm薄层的脑窗、骨窗图像,分别重建为50%ASIR-V、高权重DLIR图像(DL-H),共8组图像。应用4分制主观评价脑沟脑室、脑灰白质与颅骨显示情况,并统计各组图像的病变数量;客观评价测量基底节层面的灰质和白质的CT值和噪声值,并计算对比噪声比,同时在同层面测量模糊程度指数,比较两种图像重建方法的差异。结果相较于50%ASIR-V图像,2种层厚的DL-H均可以提升脑沟脑室、脑实质显示能力(W=5.5~22.2,P均<0.05),5 mm的50%ASIR-V与0.625 mm的DL-H图像脑沟脑室、脑实质显示能力差异无统计学意义(W=0.9、2.0,P=0.32、0.05)。骨质显示能力方面,所有图像均可以达到满分4.0分。5 mm的50%ASIR-V与DL-H图像均可以在80例患者中发现共35处病变,包括出血病变12处,颅内积气1处,骨折9处,头皮软组织肿胀13处。客观评分方面,DL-H图像噪声低于50%ASIR-V图像(t=21.4~35.7,P均<0.05),0.625 mm的DL-H与5 mm的50%ASIR-V图像噪声及对比噪声比差异无统计学意义(t=1.7~2.2,P均≥0.05)。模糊程度指数显示DL-H优于50%ASIR-V图像(t=6.1、10.0,P均<0.05),0.625 mm的DL-H与5 mm的50%ASIR-V模糊程度指数差异无统计学意义(t=2.6,P=0.28)。结论DLIR可以降低图像噪声,改善图像纹理,整体提升儿童头颅外伤CT图像质量,0.625 mm的DL-H图像质量接近5 mm的50%ASIR-V图像,可以达到诊断要求,使进一步降低儿童头颅外伤的辐射剂量成为可能。Purpose To evaluate the image quality improvement of deep learning iterative reconstruction(DLIR)on pediatric head CT images of head injury and to evaluate the performance of DLIR and conventional adaptive statistical iterative reconstruction-veo(ASIR-V)of noise and image texture of CT image in children′s head trauma.Materials and Methods A total of 80 cases in Beijing Children′s Hospital,Capital Medical University from December 7th to 11th 2020 of children′s head low-dose CT were retrospectively selected.Scan voltage was 120 kV.Scan current was 150-220 mA.The raw data were reconstructed into 5 mm thick slice and 0.625 mm thin slice brain window and bone window images.50%ASIR-V and high weight DLIR images(DL-H)were reconstructed,respectively.A 4-point system was used to subjectively evaluate the display of sulcus,brain matter and bone.The number of lesions in each group was counted.The CT value and image noise values of gray matter and white matter were measured,and the contrast to noise ratio was calculated,then measured the blur metric index was measured in the same slice.The differences between the two image reconstruction methods were compared.Results Compared to 50%ASIR-V images,DL-H significantly improved the display ability of the sulcus and ventricles,as well as the display ability of the brain parenchyma(W=5.5-22.2,all P<0.05)in both slice thickness.There was no statistically significant difference in the display ability of the sulcus and ventricles between 5 mm 50%ASIR-V and 0.625 mm DL-H images(W=0.9,2.0,P=0.32,0.05,respectively).In terms of bone display ability,all images could achieve a maximum score of 4.0.A total of 35 lesions were found in 80 patients via 5 mm 50%ASIR-V and DL-H images,including 12 hemorrhagic lesions,1 intracranial gas,9 fractures,and 13 soft tissue swelling.In terms of objective evaluation,the noise level of DL-H images was significantly lower than that of 50%ASIR-V images(t=21.4-35.7,all P<0.05),and there was no statistically significant difference in noise and contrast n

关 键 词：体层摄影术 X线计算机 头颅 儿童 低剂量 深度学习 

分 类 号：R816.1[医药卫生—放射医学] R445.3[医药卫生—临床医学]