基于人工智能的三维超声自动断层成像提取11~13^(+6)周正常胎儿腭骨关键切面的初步研究  

Study of extracting key plane of 11-13^(+6)weeks normal fetal palate by three-dimensional ultrasound based on artificial intelligence

作　　者：潘文雄 张丹丹[1] 潘瑞娟 黄雨灏 邓世华 张元吉 郑马利 倪东[2] 李梅 熊奕 Pan Wenxiong;Zhang Dandan;Pan Ruijuan;Huang Yuhao;Deng Shihua;Zhang Yuanji;Zheng Mali;Ni Dong;Li Mei;Xiong Yi(Department of Ultrasound,Shenzhen Luohu People's Hospital,the Third Affiliated Hospital,Shenzhen University,Shenzhen 518020,China;National-Regional Key Technology Engineering Laboratory for Medical Ultrasound&Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging&School of Biomedical Engineering,Health Science Center,Shenzhen University,Shenzhen 518060,China;Department of Ultrasound,Shenzhen Union Hospital of Huazhong University of Science and Technology,Shenzhen 518052,China)

机构地区：[1]深圳大学第三附属医院深圳市罗湖区人民医院超声科,深圳518020 [2]深圳大学生物医学工程学院广东省生物医学信息检测和超声成像重点实验室,深圳518060 [3]华中科技大学协和深圳医院超声科,深圳518052

出　　处：《中华超声影像学杂志》2023年第3期227-233,共7页Chinese Journal of Ultrasonography

基　　金：广东省重点领域研发计划项目(2020B1111130002)。

摘　　要：目的探讨基于人工智能的11~13^(+6)周胎儿三维超声腭骨自动断层成像提取关键切面方法的可行性。方法选取于2020年5月至2021年4月于深圳市罗湖区人民医院超声科与华中科技大学协和深圳医院超声科进行孕11~13^(+6)周产前超声检查的胎儿容积数据235例,由超声医师A和B进行三维容积数据采集。所有数据由超声医师C进行离线标注。超声医师D对所有纳入数据进行断层成像操作,保存断层图像并记录耗时,获得医师组数据。标注后数据随机分为训练集与测试集进行模型迁移学习与测试,采取4-折交叉验证,记录模型输出的测试集图像及耗时,获得智能组数据。由1名高年资超声医师对两组数据图像进行图像分析。通过比较医师组与智能组所得鼻后三角切面(RTP)评分、RTP获取率、断层获取率、耗时差异,验证智能模型的可行性。结果①医师组与智能组RTP评分总体分布差异无统计学意义[5(5,6)分比5(5,6)分,Z=0.355,P=0.722],RTP获取率差异无统计学意义(78.72%比76.60%,χ^(2)=0.55,P=0.458)。两组获取RTP的一致性、相关性较高(Kappa=0.645,φ=0.646,均P<0.001)。②医师组有效层数为9(8,9)层,智能组为8(7,9)层,医师组断层获取率大于智能组(78.72%比68.51%,χ^(2)=12.52,P=0.001)。两组在获取断层的一致性与相关性中等(Kappa=0.503,φ=0.521,均P<0.001)。③智能组耗时明显短于医师组[1.50(1.23,1.75)s比26.94(22.28,30.48)s,Z=11.440,P<0.001]。结论本研究模型能快速准确地实现11~13^(+6)周胎儿腭骨关键切面提取与断层成像。Objective To explore the feasibility of extracting the key plane of the normal fetal palate on the 11-13^(+6) week from tomography ultrasonography imaging based on artificial intelligence.Methods The fetal volume datas of 235 cases of 11-13^(+6) week normal fetal were collected from the Department of Ultrasound in the Luohu District People's Hospital of Shenzhen and Huazhong University of Science and Technology Union Shenzhen Hospital from May 2020 to April 2021.The data acquisition was completed by sonographers A and B by using the GE Voluson E10 color Doppler ultrasound diagnostic instrument.All datas were marked offline by sonographer C.Tomographic imaging was performed on all included data by sonographer D,the tomographic images were saved and the time-consuming was recorded,and the datas of the sonographer group were obtained.The labeled data were randomly divided into the training set and test set for model transfer learning and testing.The 4-fold cross-validation was adopted to record the test set image output by the model and the time consumption to obtain the intelligent group data.A senior sonographer performed image analysis on the two groups of data images.The feasibility of the intelligent model was verified by comparing the score of the plane of retronasal triangle(RTP),the acquisition rate of RTP,the acquisition rate of the fault,and the time-consuming difference between the sonographer group and the intelligent group.Results①There was no significant difference in the overall distribution of RTP scores between the sonographer group and intelligent group[5(5,6)points vs 5(5,6)points,Z=0.355,P=0.722].The RTP acquisition rate of the sonographer group and intelligent group was not statistically significant(78.72%vs 76.60%,χ^(2)=0.55,P=0.458).The consistency and correlation of RTP obtained by the two groups were high(Kappa=0.645,φ=0.646,both P<0.001).②The effective layers of the sonographer group were 9(8,9)and the intelligent group was 8(7,9).The fault acquisition rate of the doctor group was hig

关 键 词：超声检查 三维 胎儿 腭骨 断层成像 人工智能 

分 类 号：R714.5[医药卫生—妇产科学] R445.1[医药卫生—临床医学]