Pathology study for blood vessel of ocular fundus images by photoacoustic tomography

doi:10.1109/ULTSYM.2018.8579931

	Pathology study for blood vessel of ocular fundus images by photoacoustic tomography
	Jiayao Zhang 1; Kai Deng 2; Bin Chen1 ; Hengrong Lan1 ; Meng Zhou1 ; Fei Gao1
	2018-10
会议录名称	2018 IEEE INTERNATIONAL ULTRASONICS SYMPOSIUM (IUS)
ISSN	1948-5719
卷号	2018-January
页码	1-4
发表状态	已发表
DOI	10.1109/ULTSYM.2018.8579931
摘要	In the entire diabetic population, the total number of patients with diabetic retinopathy is more than 50%, and the longer diabetes, the higher the incidence of retinopathy and the rate of blindness. Besides, the blood vessel of ocular fundus is the only blood vessel that can be directly observed, which has excellent application value in medical diagnostics. Photoacoustic Tomography (PAT) is an emerging technique that can obtain high-resolution 3D in-vivo images of optical absorption by sensing laser-generated ultrasound. Therefore, in this paper, we applied U-net neural network for the segmentation of blood vessel of ocular fundus images that opens up new methods for fundus medical image processing. Then we use 2D Time Reversal photoacoustic simulation based on k-WAVE MATLAB toolbox to convert the fundus segmentation of blood vessel images into photoacoustic images. Finally, we use the ResNet Network for the diagnosis of diabetes, in which the input data are the healthy and patient photoacoustic images of the fundus segmentation of blood vessel. We achieved 85% accuracy with 158 training samples. These results demonstrate the power of using deep learning for the analysis of diabetes through the fundus segmentation photoacoustic images of the blood vessel.
关键词	Economic indicators
会议地点	Kobe
会议日期	22-25 Oct. 2018
URL	查看原文
收录类别	EI ; CPCI ; CPCI-S
出版者	IEEE Computer Society
EI入藏号	20191006591611
EI主题词	Deep learning ; Diagnosis ; Eye protection ; Image segmentation ; Light absorption ; MATLAB ; Medical imaging ; Optical data processing ; Photoacoustic effect ; Tomography ; Ultrasonic applications
EI分类号	Biological Materials and Tissue Engineering:461.2 ; Medicine and Pharmacology:461.6 ; Data Processing and Image Processing:723.2 ; Light/Optics:741.1 ; Imaging Techniques:746 ; Ultrasonic Applications:753.3 ; Accidents and Accident Prevention:914.1 ; Mathematics:921
原始文献类型	Conferences
来源库	IEEE
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/29603
专题	信息科学与技术学院_本科生信息科学与技术学院_PI研究组_高飞组信息科学与技术学院_硕士生信息科学与技术学院_博士生
作者单位	1.School of Information Science and Technology, ShanghaiTech University, The Hybrid Imaging System Laboratory, Shanghai, China 2.Beijing University of Posts and Telecommunications, The Pattern Recognition and Intelligent System Laboratory, Beijing, China
第一作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Jiayao Zhang,Kai Deng,Bin Chen,et al. Pathology study for blood vessel of ocular fundus images by photoacoustic tomography[C]:IEEE Computer Society,2018:1-4.