[1]胡鹏辉,王娜,王毅,等.基于全卷积神经网络的肛提肌裂孔智能识别[J].深圳大学学报理工版,2018,35(3):316-323.[doi:10.3724/SP.J.1249.2018.03316]
 HU Penghui,WANG Na,WANG Yi,et al.Automatic recognition of levator hiatus based on fully convolutional neural networks[J].Journal of Shenzhen University Science and Engineering,2018,35(3):316-323.[doi:10.3724/SP.J.1249.2018.03316]
点击复制

基于全卷积神经网络的肛提肌裂孔智能识别()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第35卷
期数:
2018年第3期
页码:
316-323
栏目:
电子与信息科学
出版日期:
2018-05-15

文章信息/Info

Title:
Automatic recognition of levator hiatus based on fully convolutional neural networks
文章编号:
201803011
作者:
胡鹏辉1王娜1王毅1王慧芳2汪天富1倪东1
1) 深圳大学医学部生物医学工程学院,广东省生物医学信息检测与超声成像重点实验室,医学超声关键技术国家地方联合工程实验室,广东深圳518060
2) 深圳大学第一附属医院,深圳市第二人民医院超声科,广东深圳518035
Author(s):
HU Penghui1 WANG Na1 WANG Yi1 WANG Huifang2 WANG Tianfu1 and NI Dong1
1) School of Biomedical Engineering, Health Science Center, Shenzhen University, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Shenzhen 518060, Guangdong Province, P.R.China
2) Department of Ultrasound, Shenzhen No.2 People’s Hospital, The First Affiliated Hospital of Shenzhen University, Shenzhen 518035, Guangdong Province, P.R.China
关键词:
生物医学工程女性盆底功能障碍性疾病肛提肌裂孔图像分割卷积神经网络自动上下文模型条件随机场
Keywords:
biomedical engineering female pelvic floor dysfunction (FPFD) levator hiatus segmentation deep convolutional neural networks auto-context conditional random fields
分类号:
R 318; TP 751
DOI:
10.3724/SP.J.1249.2018.03316
文献标志码:
A
摘要:
提出一种智能识别肛提肌裂孔的方法,利用端到端的编码器-解码器结构全卷积神经网络,结合自动上下文模型思想,分割出人体盆底超声图像中肛提肌裂孔,采用全连接条件随机场加强边缘约束,对分割结果实现精细化处理,实现肛提肌裂孔的智能识别.通过对372张盆底超声图像进行智能识别,并与医生手动标注结果对比,两者重合率达到95.16%,优于传统卷积神经网络模型,证实基于上下文及条件随机场的神经网络方法能有效识别肛提肌裂孔,具有重要临床应用价值.
Abstract:
We propose a novel deep learning based method to recognize the levator hiatus. The levator hiatus is segmented from the pelvic floor ultrasonic image by using the encoder-decoder architecture of full convolutional neural networks and combining with the auto-context model in an end-to-end manner. The full connection of conditional random fields is used to strengthen the edge constraint in order to refine the segmentation results.The experimental results on 372 pelvic floor ultrasonic images show that the dice ratio of our automatic recognition, compared with the labels of doctors, reaches about 95.16%. The results demonstrate that the proposed method provides more accurate segmentation than the state-of-the-art methods and have a potential clinical value.

参考文献/References:

[1] DIETZ H P, SIMPSON J M. Levator trauma is associated with pelvic organ prolapse[J]. Bjog: An International Journal of Obstetrics & Gynaecology, 2008, 115(8): 979-984.
[2] DELANCEY J O, MORGAN D M, FENNER D E, et al. Comparison of levator ani muscle defects and function in women with and without pelvic organ prolapse[J]. Obstetrics & Gynecology, 2007, 109(2 Pt 1): 295-302.
[3] SINGH K, JAKAB M, REID W M N, et al. Three-dimensional magnetic resonance imaging assessment of levator ani morphologic features in different grades of prolapse[J]. American Journal of Obstetrics & Gynecology, 2003, 188(4): 910-915.
[4] DIETZ H P, SHEK C, DE L J, et al. Ballooning of the levator hiatus[J]. Ultrasound in Obstetrics & Gynecology the Official Journal of the International Society of Ultrasound in Obstetrics & Gynecology, 2008, 31(6): 676.
[5] YING Tao, LI Qiu, XU Lian, et al. Three-dimensional ultrasound appearance of pelvic floor in nulliparous women and pelvic organ prolapse women[J]. International Journal of Medical Sciences, 2012, 9(10): 894-900.
[6] SINDHWANI N, BARBOSA D, ALESSANDRINI M, et al. Semi-automatic outlining of levator hiatus[J]. Ultrasound in Obstetrics & Gynecology, 2016, 48(1): 98.
[7] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]// International Conference on Neural Information Processing Systems. North Miami Beach, USA: Curran Associates Inc, 2012: 1097-1105.
[8] SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(4): 640-651.
[9] BADRINARAYANAN V, KENDALL A, CIPOLLA R. SegNet: a deep convolutional encoder-decoder architecture for scene segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, PP(99):1.
[10] CHEN Hao, ZHENG Yefeng, PARK J H, et al. Iterative multi-domain regularized deep learning for anatomical structure detection and segmentation from ultrasound images[C]// Intemational Conference on Medical Jmage Computing and Computer-assisted Jntervention. Athens:[s.n.] 2016: 487-495.
[11] TU Zhuowen. Auto-context and its application to high-level vision tasks[C]// IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]: IEEE, 2008: 1-8.
[12] XU Bing, WANG Naiyan, CHEN Tianqi, et al. Empirical evaluation of rectified activations in convolutional network[EB/OL]. (2015-05-05). https://arxiv.org/abs/1505.00853.
[13] ZHU Jun, CHEN Xianjie, YUILLE A L. DeePM: a deep part-based model for object detection and semantic part localization[EB/OL]. (2015-11-23).[2016-01-26]. https://arxiv.org/abs/1511.07131
[14] GAO Yaozong, WANG Li, SHAO Yeqin, et al. Learning distance transform for boundary detection and deformable in CT prostate images[M]// Machine Learning in Medical Imaging. Heidelber, Germany: Springer International Publishing, 2014, 8679: 93-100.
[15] QIAN Chunjun, WANG Li, YOUSUF A, et al. In vivo MRI based prostate cancer identification with random forests and auto-context model[C]// International Workshop on Machine Learning in Medical Imaging. Heidelber, Germany: Springer International Publishing, 2014: 314-322.
[16] LIU Ziwei, LI Xiaoxiao, LUO Ping, et al. Semantic image segmentation via deep parsing network[C]// IEEE International Conference on Computer Vision. New York, USA: Computer Society, 2015: 1377-1385.
[17] LAFFERTY J D, MCCALLUM A, PEREIRA F C N. Conditional random fields: probabilistic models for segmenting and labeling sequence data[C]// Proceedings of the Eighteenth International Conference on Machine Learning. San Francisco, USA: Morgan Kaufmann Publishers Inc, 2001: 282-289.
[18] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 40(4): 834-848.
[19] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Semantic image segmentation with deep convolutional nets and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848.
[20] CHANDRA S, KOKKINOS I. Fast, exact and multi-scale inference for semantic image segmentation with deep Gaussian CRFs[C]// European Conference on Computer Vision. Heidelber, Germany: Springer International Publishing, 2016: 402-418.
[21] DONAHUE J, JIA Yangqing, VINYALS O, et al. DeCAF: a deep convolutional activation feature for generic visual recognition[C]// Proceedings of the 31st International Conference on Machine Learning. Beijing: JMLR.org, 2014: 32 (1) 1-647
[22] RAZAVIAN A S, AZIZPOUR H, SULLIVAN J, et al. CNN features off-the-shelf: an astounding baseline for recognition[C]// IEEE Conference on Computer Vision and Pattern Recognition Workshops. Columbus, USA: IEEE, 2014: 512-519.
[23] YOSINSKI J,CLUNE J,BENGIO Y,et al.How transferable are features in deep neural networks?[EB/OL].(2014-11-06). https://arxiv.org/abs/1411.1792
[24] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[J]. Computer Science,2014, 8693: 740-755.
[25] HUANG Qian, DOM B. Quantitative methods of evaluating image segmentation[C]// Proceedings of the International Conference on Image Processing. Washington DC, USA: IEEE Computer Society, 1995: 3: 3053.
[26] TAHA A A, HANBURY A. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool[J]. BMC Medical Imaging, 2015, 15(1): 29.
[27] CHANG H H, ZHUANG A H, VALENTINO D J, et al. Performance measure characterization for evaluating neuroimage segmentation algorithms[J]. Neuroimage, 2009, 47(1): 122.
[28] BADRINARAYANAN V, KENDALL A, CIPOLLA R. SegNet: a deep convolutional encoder-decoder architecture for scene segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495.

相似文献/References:

[1]潘晓畅,冯乃章,陈思平.二维Savitzky-Golay数字差分器剪切波弹性成像方法[J].深圳大学学报理工版,2018,35(1):22.[doi:10.3724/SP.J.1249.2018.01022]
 PAN Xiaochang,FENG Naizhang,et al.A shear wave elastography method based on 2D Savitzky-Golay digital differentiator[J].Journal of Shenzhen University Science and Engineering,2018,35(3):22.[doi:10.3724/SP.J.1249.2018.01022]
[2]刘刚,钱建庭,李先明,等.X射线光声成像的信号检测与仿真[J].深圳大学学报理工版,2018,35(3):324.[doi:10.3724/SP.J.1249.2018.03324]
 LIU Gang,CHIN C T,LI Xianming,et al.Simulation and experimental detection of X-ray photo-acoustic[J].Journal of Shenzhen University Science and Engineering,2018,35(3):324.[doi:10.3724/SP.J.1249.2018.03324]
[3]南嘉格列,李锐,王海霞,等.基于深度学习的肝包虫病超声图像分型研究[J].深圳大学学报理工版,2019,36(6):702.[doi:10.3724/SP.J.1249.2019.06702]
 NANJIA Gelie,LI Rui,WANG Haixia,et al.Ultrasound image classification for hepatic echinococcosis using deep learning[J].Journal of Shenzhen University Science and Engineering,2019,36(3):702.[doi:10.3724/SP.J.1249.2019.06702]
[4]蒋超,林静,黄鹏.新型近红外花菁类光声探针用于肼检测[J].深圳大学学报理工版,2020,37(1):33.[doi:10.3724/SP.J.1249.2020.01033]
 JIANG Chao,LIN Jing,and HUANG Peng.Novel near-infrared cyanine-based photoacoustic probe for hydrazine detection[J].Journal of Shenzhen University Science and Engineering,2020,37(3):33.[doi:10.3724/SP.J.1249.2020.01033]

备注/Memo

备注/Memo:
Received:2017-12-07;Accepted:2018-03-06
Foundation:National Natural Science Foundation of China (61571304, 61701312, 81571758, 81771922)
Corresponding author:Associated professor NI Dong. E-mail: nidong@szu.edu.cn
Citation:HU Penghui, WANG Na, WANG Yi, et al. Automatic recognition of levator hiatus based on fully convolutional neural networks[J]. Journal of Shenzhen University Science and Engineering, 2018, 35(3): 316-323.(in Chinese)
基金项目:国家自然科学基金资助项目(61571304, 61701312, 81571758, 81771922)
作者简介:胡鹏辉(1992—),男,深圳大学硕士研究生.研究方向:医学图像分析.E-mail:515102745@qq.com
引文:胡鹏辉,王娜,王毅,等.基于全卷积神经网络的肛提肌裂孔智能识别[J]. 深圳大学学报理工版,2018,35(3):316-323.
更新日期/Last Update: 2018-04-28