超声波表面回声检测的三维卷积神经网络
Mario Muñoz1,2, Adrián Rubio1,2, Marcelo Larrea1
1Institute for Physical and Information Technologies, Spanish National Research Council, 28006 Madrid, Spain.
Sensors (Basel, Switzerland)
|August 28, 2025
概括
DeepEcho3D是一个新的3D卷积神经网络 (CNN),可以准确地检测超声波成像中的表面回声. 这种先进的方法显著降低了飞行时间 (TOF) 估计的异常值,提高了非破坏性测试 (NDT) 和医学成像的准确性.
科学领域:
- 超声波物理和信号处理
- 在成像中使用人工智能
- 非破坏性检测 (NDT) 和医学诊断
背景情况:
- 超声波阵列成像依赖于准确的飞行时间 (TOF) 测量以获得焦点定律.
- 表面回声对于TOF的确定至关重要,但传统的检测方法对噪声敏感.
- 需要强大的技术来克服传统值跨越和峰值搜索算法的局限性.
研究的目的:
- 在超声波全矩阵捕获 (FMC) 数据中开发和评估深度3D卷积神经网络 (CNN).
- 根据已建立的TOF估计方法评估拟议的CNN模型的性能.
- 展示人工智能在提高超声波成像准确性的潜力.
主要方法:
- 一个名为DeepEcho3D的深度3DCNN被设计用于表面的回声检测.
- 在CNN的训练中使用了FMC的超声波信号,
- 精确的探测器定位由机器人臂设置确保,并使用理论TOF生成标记数据.
主要成果:
- 深度回声3D模型显示与地面真实TOF值的高度对齐.
- 与传统方法相比,CNN显著降低了多达98%的TOF估计值.
- 这种方法在杂的超声波环境中显示出优越的稳定性.
结论:
- DeepEcho3D为超声波成像中的表面回声检测提供了一个高度准确和强大的解决方案.
- 由人工智能驱动的方法显著改善了TOF估计,有利于NDT和医学成像应用.
- 这项研究强调了深度学习在超声波数据分析和解释方面的有效性.
相关概念视频
Imaging Studies II: Ultrasonography
53
IntroductionUltrasonography, or renal ultrasound, is a noninvasive medical imaging technique that uses high-frequency sound waves to visualize the kidneys, ureters, bladder, and surrounding tissues.Indications for Urinary System UltrasonographyUrinary system ultrasonography is indicated in various clinical scenarios, such as:Kidney Stones (Urolithiasis): To detect and monitor the size and presence of kidney or urinary tract stones.Hydronephrosis: To assess the dilation of the renal pelvis and...
53
Ultrasonography
5.8K
Ultrasonography is an imaging technique that uses high-frequency sound waves to visualize the body's internal structures. It is a non-invasive and safe procedure that does not involve the use of ionizing radiation, making it widely used in various medical fields. Ultrasonography is used to study heart function, blood flow in the neck or extremities, certain conditions such as gallbladder disease, and fetal growth and development.
During an ultrasonography procedure, a handheld device called...
During an ultrasonography procedure, a handheld device called...
5.8K


