全卷积深度迁移网络的联合分割Joint Segmentation of Full Convolutional Deep Migration Network
李岩;刘俊;
摘要(Abstract)：
近年来,随着超声空化在医疗上的应用,超声空化治疗又重新回到了人们的视野,因其在处理血管阻塞方面的天然的优势,引起了广泛的讨论和研究。为实现准确的实时治疗,提出了一种基于全卷积网络(Fully Convolutional Networks,FCN)的超声血管分割方法。全卷积深度迁移分割网络(Full Convolutional deep Aggregation Migration Network,AMFCN)通过对全卷积网络使用对称网络连接,深度聚合模式以深度提取图像特征,并优化数据增强方式,添加迁移学习模型等方法,有效地利用已有数据进行数据拓展,缓解医学图像数据过少的影响。实验结果表明,该研究方法在超声血管图像上取得了较好的分割性能,能准确地分割出血管区域。
关键词(KeyWords)： 超声治疗;全卷积网络;深度聚合;小数据集;迁移学习
基金项目(Foundation): 国家自然科学基金青年科学基金（31600975,C1112）
作者(Author): 李岩;刘俊;
Email:
DOI:
参考文献(References)：
- [1] MOLL S.A clinical perspective of venous thromboembolism[J].Arteriosclerosis Thrombosis and Vascular Biology,2008,28(3):373-379.
- [2] ATAR S,ROSENSHEIN U.Perspectives on the role of ultrasonic devices in thrombolysis[J].Journal of Thrombosis and Thrombolysis,2004,17(2):107-114.
- [3] SIEGEL R.Noninvasive transcutaneous low frequency ultrasound enhances thrombolysis in peripheral and coronary arteries[J].Echocardiography,2001,18(3):247-257.
- [4] ROSENSCHEIN U,FURMAN V,KERNER E,et al.Ultrasound imaging-guided noninvasive ultrasound thrombolysis:Preclinical results[J].Circulation,2000,102:238-245.
- [5] MAXWELL A.Non-invasive thrombolysis induced by histotripsy pulsed cavitation ultrasound therapy[C]//Proceedings of 2008 IEEE International Ultrasonics Symposium Abstract Book,2008.
- [6]王志东，汪友生，董路，等.血管内超声图像初始轮廓提取算法的研究[J].计算机测量与控制，2014,22(5):1490-1492.
- [7] ZAKERI F S,SETAREHDAN S K,NOROUZI S.Automatic media-adventitia IVUS image segmentation based on sparse representation framework and dynamic directional active contour model[J].Computers in Biology and Medicine,2017,89:561-572.
- [8] SU S,HU Z,LIN Q,et al.An artificial neural network method for lumen and media-adventitia border detection in IVUS[J].Computerized Medical Imaging&Graphics the Official Journal of the Computerized Medical Imaging Society,2016,57:29.
- [9]袁绍锋，杨丰，徐琳，等.有条件生成对抗网络的IVUS图像内膜与中-外膜边界检测[J].中国生物医学工程学报，2019,38(2):146-156.
- [10] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2014,39(4):640-651.
- [11] RYT?LUOTO I,GITSAS A,PASANEN S,et al.Effect of film structure and morphology on the dielectric breakdown characteristics of cast and biaxially oriented polypropylene films[J].European Polymer Journal,2017,95:606-624.
- [12]汪友生，王雨婷，夏章涛，等.序列血管内超声图像的管腔内膜自动分割算法[J].图学学报，2019,40(1):173-180.
- [13] SIRACUSA V,INGRAO C.Correlation amongst gas barrier behaviour,temperature and thickness in BOPP films for food packaging usage:A lab-scale testing experience[J].Polymer Testing,2017,59:277-289.
- [14] YAO Xiaoli,MA Yuhong,ZHAO Changwen,et al.Correlation of Siox layer thickness and properties of BOPP/Siox composite films with spin coating process parameters[J].Chinese Journal of Polymer Science,2013,31(2):334-345.
- [15] RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolutional networks for biomedical image segmentation[C]//Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention,2015.
- [16] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:770-778.
- [17] LIU X,CAO J,FU T,et al.Semi-supervised automatic segmentation of layer and fluid region in retinal optical coherence tomography images using adversarial learning[J].IEEE Access,2019,7:3046.