智能产科超声

(1)用户差异大是产前超声诊断面临的主要挑战。其中，标准切面的获取质量以及后续生物学参数的测量精度是导致用户差异的主要原因之一。为降低产前超声诊断用户差异，提高临床诊断效率，我们首次提出基于人工智能技术实现标准切面定位及生物参数测量的自动化，基于随机森林、卷积神经网络、循环神经网络等方法，实现了标准切面自动定位的通用方法框架、切面质量的自动监控以及多种生物学参数的高精度自动测量。

  传统的超声图像中的生物参数测量高度依赖于二维切面的质量以及手动测量的技巧，存在效率低、胎儿发育估计误差较大等问题，我们基于深度学习框架，开展三维计算超声方法研究，首次实现了早孕期三维超声图像中胎儿、绒毛膜腔及胎盘的协同分割，为后续建立容积生物学参数体系奠定了方法基础。

Fetal standard plane detection based on knowledge transfer and RNN

(2)相关方向老师：汪天富、倪东、雷柏英

(3)相关文章：

[1] Li, J., Wang, Y.*, Lei, B., Cheng, J. Z., Qin, J., Wang, T., Li, S.*, Ni, D.* (2017). Automatic Fetal Head Circumference Measurement in Ultrasound using Random Forest and Fast Ellipse Fitting. IEEE Journal of Biomedical and Health Informatics. （中科院二区）

[2] Hao Chen, Lingyun Wu, Qi Dou, Jing Qin, Shengli Li, Jie-Zhi Cheng*, Dong Ni*, and Pheng-Ann Heng, " Ultrasound Standard Plane Detection Using a Composite Neural Network Framework," in IEEE Transactions on Cybernetics , Vol. 47, No. 6, pp. 1576 – 1586, March 2017. (SCI, 中科院一区)

[3] L. Wu; J. Z. Cheng; S. Li; B. Lei; T. Wang; D. Ni*, "FUIQA: Fetal Ultrasound Image Quality Assessment With Deep Convolutional Networks," in IEEE Transactions on Cybernetics , Vol. 47, No. 5, pp. 1336 – 1349, March 2017. (SCI, 中科院一区)

[4] Dong Ni, Xing Ji, Min Wu, Wenlei Wang, Xiaoshuang Deng, Zhongyi Hu, Tianfu Wang, Dinggang Shen, Jie-Zhi Cheng,*, Huifang Wang,*, Automatic Cystocele Severity Grading in Transperineal Ultrasound by Random Forest Regression. Pattern Recognition, 63: 551-560, 2017.03. (SCI, 中科院二区)

[5] Chen Hao, Ni Dong*, Qin Jing*, Li Shengli, Yang Xin, Wang Tianfu, Heng Pheng-Ann. Standard Plane Localization in Fetal Ultrasound via Domain Transferred Deep Neural Networks, Biomedical and Health Informatics, IEEE Journal of Biomedical and Health Informatics , 2015, 19(5): 1627-1636. （SCI，中科院二区）

[6] Lei, Baiying, Ee-Leng Tan, Siping Chen, Liu Zhuo, Shengli Li, Dong Ni*, and Tianfu Wang*. "Automatic Recognition of Fetal Facial Standard Plane in Ultrasound Image via Fisher Vector." Plos One, (2015): e0121838. （SCI，中科院二区）

[7] Dong Ni, Xin Yang, Xin Chen, Chien-Ting Chin, Siping Chen, Pheng Ann Heng, Shengli Li, Jing Qin, Tianfu Wang, Standard Plane Localization in Ultrasound by Radial Component Model and Selective Search, Ultrasound in Medicine & Biology, 2014, 40(11): 2728-2742. (SCI) （SCI，中科院二区）2.494

[8] Yang, X., Yu, L., Li, S., Wang, X., Wang, Ni, D.* Qin, J., Pheng-Ann Heng. (2017). Towards Automatic Semantic Segmentation in Volumetric Ultrasound. Medical Image Computing and Computer Assisted Intervention − MICCAI 2017.

[9] Lingyun Wu, Xin Yang, Shengli Li, Tianfu Wang, Pheng-Ann Heng, Dong Ni*，Cascaded Fully Convolutional Networks for Automatic Prenatal Ultrasound Image Segmentation，in: Proceedings of 2017 IEEE International Symposium on Biomedical Imaging(ISBI 2017), Melbourne, Australia, 2017, Apr 18-21©IEEE.

[10]Dong Ni, Xing Ji, Yaozong Gao, Jie-Zhi Cheng, Huifang Wang, Jing Qin, Baiying Lei, Tianfu Wang, Guorong Wu, and Dinggang Shen. Automatic Cystocele Severity Grading in Ultrasound by Spatio-Temporal Regression[C] Med Image Comput Comput Assist Interv. 2016 October ; 9901: 247–255. doi: 10.1007/978-3-319-46723-8_29

[11] Yang Xin, Ni Dong *, Qin Jing, Li Shengli, Wang Tianfu, Chen Siping. Standard plane localization in ultrasound by radial component, ISBI 2014: 1180-1183.