摘要
目的探讨人工智能(Artificial Intelligence,AI)自动定位联合自动管电压推荐技术在医患无接触式胸部低剂量CT(Low-Dose CT,LDCT)检查的应用价值。方法收集2022年12月6日至12月9日于我院行胸部LDCT检查的患者136例。实验组68例,采用智能患者摆位,定位框自适应,自动管电压推荐技术;对照组68例,采用传统人工摆位,手动勾画定位框,管电压120 kV。比较两组图像定位像长度、螺旋扫描长度、定位像Z轴偏移、螺旋扫描Z轴偏移、Y轴偏移、X轴偏移、重建视野、肺实质和降主动脉的信噪比(Signal to Noise Ratio,SNR)与对比噪声比(Contrast to Noise Ratio,CNR)、图像主观评分、检查用时和有效辐射剂量(Effective Dose,ED)等指标。结果实验组定位像长度、螺旋扫描长度、定位像Z轴偏移、螺旋扫描Z轴偏移、Y轴偏移和重建视野均小于对照组,差异均有统计学意义(P<0.05)。两组图像气管隆嵴层面肺实质和降主动脉的SNR、CNR以及主观评分差异均无统计学意义(P>0.05)。实验组的平均ED[(1.88±0.26)mSv]较对照组[(2.03±0.25)mSv]低,差异具有统计学意义(P<0.05)。结论AI自动定位联合自动管电压推荐技术应用于胸部LDCT检查中,可在保证图像质量的前提下实现医患无接触式检查,减小交叉感染风险,有助于减小定位偏移,降低患者的辐射剂量,具有更高的工作效率及临床应用价值。
Objective To explore the application value of artificial intelligence(AI)automatic positioning combined with automatic tube voltage recommendation technology in non-contact examination of chest low-dose CT(LDCT).Methods A total of 136 patients who underwent chest LDCT examination in our hospital from December 6 to December 9,2022 were collected.The experimental group of 68 patients,intelligent patient positioning,automatic positioning frame and automatic tube voltage recommendation technology were used;The control group of 68 patients,conventional manual positioning,manual delineation of the positioning frame and tube voltage 120 kV were used.The length of the scout scan,the length of the helical scan,the Z-axis deviation of the scout scan,the Z-axis deviation of the helical scan,the Y-axis deviation,the X-axis deviation,the reconstruction field of view,the signal to noise ratio(SNR),contrast to noise ratio(CNR)of lung parenchyma and descending aorta,image subjective score,examination time and effective dose(ED)were compared between the two groups.Results The length of the scout scan,the length of the helical scan,the Z-axis deviation of the scout scan,the Z-axis deviation of the helical scan,the Y-axis deviation and the reconstruction field of view in the experimental group were all smaller than those in the control group,and the difference was statistically significant(P<0.05).There were no statistically significant differences in SNR,CNR and subjective score of lung parenchyma and descending aorta at the plane of tracheal carina between the two groups of images(P>0.05).The average ED of the experimental group[(1.88±0.26)mSv]was lower than that of the control group[(2.03±0.25)mSv],and the difference was statistically significant(P<0.05).Conclusion The application of AI automatic positioning combined with automatic tube voltage technology in examination of chest LDCT can avoid doctor-patient contact and reduce the risk of cross-infection.This method can ensure the image quality,help to reduce the positioning d
作者
杨泽铖
宋凤祥
沈杰
施楠楠
单飞
YANG Zecheng;SONG Fengxiang;SHEN Jie;SHI Nannan;SHAN Fei(Department of Radiology,Shanghai Public Health Clinical Center,Fudan University,Shanghai 201508,China)
出处
《中国医疗设备》
2023年第11期86-91,共6页
China Medical Devices
基金
科技创新2030—“新一代人工智能”重大项目(2021ZD0111103)
上海市卫生健康委员会科研课题面上项目(202140084)
上海市公共卫生体系建设三年行动计划重点学科建设项目(GWV-10.1-XK09)。
关键词
人工智能
胸部低剂量CT
自动管电压
辐射剂量
artificial intelligence
chest low-dose CT
automatic tube voltage
radiation dose
