低管电流低管电压扫描联合人工智能重建技术在胸部肋骨骨折中的应用  

Application of low tube current and low tube voltage scanning combined with artificial intelligence reconstruction technology in chest rib fracture

作　　者：李锦田 左卫[2] LI Jintian;ZUO Wei(Department of Radiology,Guangdong Second Provincial Hospital,Guangzhou,Guangdong 510000,China;Department of Imaging,Guangdong Second Provincial Hospital,Guangzhou,Guangdong 510000,China)

机构地区：[1]广东省第二人民医院放射科,广东广州510000 [2]广东省第二人民医院影像科,广东广州510000

出　　处：《影像研究与医学应用》2023年第10期54-56,共3页Journal of Imaging Research and Medical Applications

摘　　要：目的:探究低管电流低管电压扫描联合人工智能重建技术在观察胸部肋骨骨折中的可行性。方法:将72例因胸部外伤于广东省第二人民医院行低管电流低管电压胸部CT平扫检查的患者使用数字随机法分为三组,A组(n=24)采用230mAs管电流,100kV管电压进行扫描,B组(n=21)、C组(n=27)采用100mAs管电流,80kV管电压进行扫描,A组、B组使用滤波反投影法,C组采用人工智能重建算法。记录三组患者图像噪声,信噪比(signal-to-noise ratio,SNR),对比信噪比(contrast-to-noise ration,CNR),剂量长度乘积(dose length product,DLP),容积剂量指数(volume computed tomography dose index,CTDIvol),有效剂量(effective dose,ED)以及图像评分。结果:A、B两组胸部CT图像噪声、ED、SNR、CNR、DLP、CTDIv o l、图像评分差异均具有统计学意义(P<0.01)。A、C两组DLP、CTDI_(vol)、ED差异具有统计学意义(P<0.01),A、C两组胸部CT图像噪声、SNR、CNR、图像评分差异均不具有统计学意义(P>0.05)。结论:人工智能重建技术在外伤患者胸部CT成像中可明显改善图像质量,在减少辐射剂量的同时能满足肋骨骨折的诊断观察。Objective To explore the feasibility of low tube current and low tube voltage scanning combined with artificial intelligence reconstruction technology in the observation of chest rib fracture.Methods 72 patients who underwent plain CT examination of chest with low tube current and low tube voltage in Guangdong Second Provincial Hospital due to chest trauma were divided into three groups by digital random method.Group A(n=24)adopted 230mAs tube current and 100 kV tube voltage for scanning,while Group B(n=21)and Group C(n=27)adopted 100 mAs tube current and 80 kV tube voltage for scanning.Filtering backprojection method was used in Groups A and B,and artificial intelligence reconstruction algorithm was used in Group C.Image noise,signal-to-noise ratio(SNR),contrast-to-noise ratio(CNR),dose length product(DLP),volume computed tomography dose index(CTDI_(vol)),effective dose(ED),and image scores were recorded for three groups of patients.Results The chest CT image noise,ED,SNR,CNR,DLP,CTDIvol,and image score in groups A and B were statistically significant(P<0.01).DLP,CTDIvol,and ED in the groups A and C were statistically significant(P<0.01),while the noise,SNR,CNR,and image score in the chest CT images in the groups A and C were not statistically significant(P>0.05).Conclusion Industrial and intelligent reconstruction technology can significantly improve the image quality of chest CT imaging of trauma patients,and meet the requirements of diagnosis and observation of rib fracture while reducing the radiation dose.

关 键 词：低辐射剂量 图像质量 人工智能 

分 类 号：R445.3[医药卫生—影像医学与核医学]