计算机科学
相(物质)
深度学习
连贯性(哲学赌博策略)
弹性成像
光学
人工智能
卷积神经网络
卷积(计算机科学)
领域(数学)
光学相干层析成像
人工神经网络
模式识别(心理学)
物理
数学
声学
统计
超声波
量子力学
纯数学
作者
Bo Dong,Naixing Huang,Yulei Bai,Shengli Xie
出处
期刊:Optics Letters
[The Optical Society]
日期:2021-11-23
卷期号:46 (23): 5914-5914
被引量:3
摘要
In this Letter, a deep-learning-based approach is proposed for estimating the strain field distributions in phase-sensitive optical coherence elastography. The method first uses the simulated wrapped phase maps and corresponding phase-gradient maps to train the strain estimation convolution neural network (CNN) and then employs the trained CNN to calculate the strain fields from measured phase-difference maps. Two specimens with different deformations, one with homogeneous and the other with heterogeneous, were measured for validation. The strain field distributions of the specimens estimated by different approaches were compared. The results indicate that the proposed deep-learning-based approach features much better performance than the popular vector method, enhancing the SNR of the strain results by 21.6 dB.
科研通智能强力驱动
Strongly Powered by AbleSci AI