[1]刘中华,余卫峰,吴秀明,等.基于实时目标检测网络的胎儿颜面部超声切面识别及应用[J].中国医学物理学杂志,2024,41(2):247-252.[doi:DOI:10.3969/j.issn.1005-202X.2024.02.019]
　LIU Zhonghua,YU Weifeng,et al.Fetal facial ultrasound plane recognition based on real-time object detection network and its application[J].Chinese Journal of Medical Physics,2024,41(2):247-252.[doi:DOI:10.3969/j.issn.1005-202X.2024.02.019]
点击复制

基于实时目标检测网络的胎儿颜面部超声切面识别及应用()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
41卷
期数:
2024年第2期
页码:
247-252
栏目:
医学人工智能
出版日期:
2024-03-13

文章信息/Info

Title:
Fetal facial ultrasound plane recognition based on real-time object detection network and its application
文章编号:
1005-202X（2024）02-0247-06
作者:
刘中华1; 2; 余卫峰1; 吴秀明1; 2; 薛浩2; 吕国荣3; 4; 王小莉5; 柳培忠2; 5
1.福建医科大学附属泉州第一医院超声科， 福建 泉州 362000； 2.华侨大学工学院， 福建 泉州 362000； 3.泉州医学高等专科学校母婴健康服务应用技术协同创新中心， 福建 泉州 362000； 4.福建医科大学附属第二医院超声科， 福建 泉州 362000； 5.华侨大学医学院， 福建 泉州 362000
Author(s):
LIU Zhonghua1;  2;  YU Weifeng1; WU Xiuming1;  2;  XUE Hao2;  L?Guorong3;  4;  WANG Xiaoli5;  LIU Peizhong2;  5
1. Department of Ultrasound, Quanzhou First Hospital Affiliated to Fujian Medical University, Quanzhou 362000, China 2. College of Engineering, Huaqiao University, Quanzhou 362000, China 3. Collaborative Innovation Center for Maternal and Infant Health Service Application Technology, Quanzhou Medical College, Quanzhou 362000, China 4. Department of Ultrasound, the Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, China 5. School of Medicine, Huaqiao University, Quanzhou 362000, China
关键词:
超声检查; 人工智能; 实时目标检测网络; 胎儿; 颜面部
Keywords:
Keywords: ultrasound examination artificial intelligence real-time object detection network fetal face
分类号:
R318；R445.1
DOI:
DOI:10.3969/j.issn.1005-202X.2024.02.019
文献标志码:
A
摘要:
目的：探讨基于实时目标检测网络的人工智能（AI）模型在胎儿颜面部超声检查中的应用价值。方法：以妊娠20～24周正常胎儿颜面部超声标准切面（FFUSP）图像为研究对象，构建基于实时目标检测网络的FFUSP识别模型，观察其对FFUSP及其解剖结构的识别精度；通过临床验证分析其对119例胎儿超声图像中FFUSP识别效能以评价其临床应用价值。结果：AI模型对胎儿颜面部结构识别的整体查准率为97.8%、查全率为98.5%、mAP@.5为98.1%、mAP@.5:.95为61.0%。在临床验证中，AI模型对颜面部解剖结构识别的敏感度、特异度、阳性预测值、阴性预测值及准确率分别为100.0%、98.5%、87.4%、100.0%、98.7%，与胎儿超声专家分类一致性强（k=0.925, P<0.001）；对3类标准切面图像的识别准确率为100%；动态视频检测平均速度为33.93帧/s。结论：基于实时目标检测网络的FFUSP识别模型性能优越，可应用于实时超声检查辅助诊断、教学及智能化质量评价。
Abstract:
Abstract: Objective To explore the role of an artificial intelligence (AI) model based on real-time object detection network in fetal facial ultrasound examination. Methods With the normal fetal facial ultrasound standard plane (FFUSP) at 20-24 weeks of gestation as the research object, a FFUSP recognition model based on real-time object detection network was constructed. The recognition accuracy of the model for FFUSP and the anatomical structures were analyzed, and the clinical value was evaluated by analyzing its performance in identifying FFUSP in 119 cases of fetal ultrasound images. Results The overall precision, recall rate, mAP@.5 and mAP@.5:.95 of the AI model were 97.8%, 98.5%, 98.1% and 61.0%, respectively. The clinical validation showed that the AI model had a sensitivity, specificity, positive predictive value, negative predictive value and accuracy of 100.0%, 98.5%, 87.4%, 100.0% and 98.7% for facial anatomy recognition, and the results were highly consistent with the classification of fetal ultrasound experts (k=0.925, P<0.001). The recognition accuracy of the model for 3 types of standard planes reached 100% and the average speed of dynamic video detection was 33.93 frames per second. Conclusion The FFUSP recognition model based on real-time object detection network exhibits excellent performance, and it can be applied to real-time ultrasound diagnosis, teaching and intelligent quality evaluation.

相似文献/References:

[1]王弈,李传富.人工智能方法在医学图像处理中的研究新进展[J].中国医学物理学杂志,2013,30(03):4138.[doi:10.3969/j.issn.1005-202X.2013.03.013]
[2]王亚,李永欣,黄文华.人类脑计划的研究进展[J].中国医学物理学杂志,2016,33(2):109.[doi:10.3969/j.issn.1005-202X.2016.02.001]
　[J].Chinese Journal of Medical Physics,2016,33(2):109.[doi:10.3969/j.issn.1005-202X.2016.02.001]
[3]祁红琳,胡先玲,李传明,等. 基于MRI纹理特征的早期肝癌术后复发预测[J].中国医学物理学杂志,2017,34(9):908.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.010]
　[J].Chinese Journal of Medical Physics,2017,34(2):908.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.010]
[4]纪春阳,徐秀林,王燕. 深度神经网络技术在肿瘤细胞识别中的应用[J].中国医学物理学杂志,2019,36(9):1113.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.022]
　JI Chunyang,XU Xiulin,WANG Yan. Application of deep neural network in tumor cell recognition[J].Chinese Journal of Medical Physics,2019,36(2):1113.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.022]
[5]王沛沛,李金凯,李彩虹,等.基于人工智能技术的危及器官自动勾画在胸部肿瘤中的应用[J].中国医学物理学杂志,2019,36(11):1346.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.019]
　WANG Peipei,LI Jinkai,LI Caihong,et al.Application of automatic organs-at-risk segmentation based on artificial intelligence technology in thoracic tumors[J].Chinese Journal of Medical Physics,2019,36(2):1346.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.019]
[6]卢展辉,陈婷,邓翼业,等.超声常规三切面与特殊切面法筛查唇腭裂胎儿的价值[J].中国医学物理学杂志,2020,37(3):322.[doi:DOI:10.3969/j.issn.1005-202X.2020.03.013]
　LU Zhanhui,CHEN Ting,DENG Yiye,et al.Application value of conventional 3 sections and special cross section in the ultrasonic screening of cleft lip and palate in fetuses[J].Chinese Journal of Medical Physics,2020,37(2):322.[doi:DOI:10.3969/j.issn.1005-202X.2020.03.013]
[7]莫梓华,高红霞,黄飚.人工智能在中枢神经系统疾病影像诊断中的应用进展[J].中国医学物理学杂志,2020,37(6):792.[doi:DOI:10.3969/j.issn.1005-202X.2020.06.025]
　MO Zihua,GAO Hongxia,et al.Application of artificial intelligence in imaging diagnosis of central nervous system diseases: a review[J].Chinese Journal of Medical Physics,2020,37(2):792.[doi:DOI:10.3969/j.issn.1005-202X.2020.06.025]
[8]刘思远,张丽军,刘雷.人工智能在抗击新型冠状病毒肺炎疫情中的应用[J].中国医学物理学杂志,2020,37(8):1076.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.026]
　LIU Siyuan,ZHANG Lijun,LIU Lei.Application of artificial intelligence in fighting against COVID-19 pandemic[J].Chinese Journal of Medical Physics,2020,37(2):1076.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.026]
[9]陈思佳,石丽婉,林勤.基于知识的放射治疗技术研究[J].中国医学物理学杂志,2020,37(11):1350.[doi:DOI:10.3969/j.issn.1005-202X.2020.11.002]
　CHEN Sijia,SHI Liwan,LIN Qin.Research on knowledge-based radiation therapy[J].Chinese Journal of Medical Physics,2020,37(2):1350.[doi:DOI:10.3969/j.issn.1005-202X.2020.11.002]
[10]陈子印,白艳春,徐巍,等.人工智能云技术在乳腺癌患者心脏亚结构自动勾画中的应用[J].中国医学物理学杂志,2020,37(12):1599.[doi:DOI:10.3969/j.issn.1005-202X.2020.12.024]
　CHEN Ziyin,BAI Yanchun,XU Wei,et al.Application of artificial intelligence cloud technology in auto-segmentation of cardiac substructure of breast cancer patients[J].Chinese Journal of Medical Physics,2020,37(2):1599.[doi:DOI:10.3969/j.issn.1005-202X.2020.12.024]
[11]刘中华,王小莉,吕国荣,等.人工智能自动识别胎儿颜面部超声标准切面的研究[J].中国医学物理学杂志,2021,38(12):1575.[doi:DOI:10.3969/j.issn.1005-202X.2021.12.021]
　LIU Zhonghua,WANG Xiaoli,et al.Automatic recognition of fetal facial ultrasound standard plane using artificial intelligence[J].Chinese Journal of Medical Physics,2021,38(2):1575.[doi:DOI:10.3969/j.issn.1005-202X.2021.12.021]

备注/Memo

备注/Memo:
【收稿日期】2023-10-26 【基金项目】福建省自然科学基金（2021J011404）；泉州市科技计划项目（2022NS057） 【作者简介】刘中华，硕士，副主任医师，研究方向：产科超声、介入超声、超声人工智能，E-mail: liuzhonghua2005@126.com 【通信作者】吴秀明，副主任医师，研究方向：妇产科超声，E-mail: wxming1981@163.com
更新日期/Last Update: 2024-02-27