当前位置: X-MOL 学术Ultrasound Med. Biol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
3-D H-Scan Ultrasound Imaging and Use of a Convolutional Neural Network for Scatterer Size Estimation.
Ultrasound in Medicine & Biology ( IF 2.4 ) Pub Date : 2020-07-09 , DOI: 10.1016/j.ultrasmedbio.2020.06.001
Haowei Tai 1 , Mawia Khairalseed 2 , Kenneth Hoyt 3
Affiliation  

H-Scan ultrasound (US) is a new imaging technology that estimates the relative size of acoustic scattering objects and structures. The purpose of this study was to introduce a three-dimensional (3-D) H-scan US imaging approach for scatterer size estimation in volume space. Using a programmable research scanner (Vantage 256, Verasonics Inc, Kirkland, WA, USA) equipped with a custom volumetric imaging transducer (4 DL7, Vermon, Tours, France), raw radiofrequency (RF) data was collected for offline processing to generate H-scan US volumes. A deep convolutional neural network (CNN) was modified and used to achieve voxel mapping from the input H-scan US image to underlying scatterer size. Preliminary studies were conducted using homogeneous gelatin-based tissue-mimicking phantom materials embedded with acoustic scatterers of varying size (15 to 250 μm) and concentrations (0.1 to 1%). Two additional phantoms were embedded with 63 or 125 µm-sized microspheres and used to test CNN estimation accuracy. In vitro results indicate that 3-D H-scan US imaging can visualize the spatial distribution of acoustic scatterers of varying size at different concentrations (R2 > 0.85, p < 0.03). The result of scatterer size estimation reveals that a CNN can achieve an average mapping accuracy of 93.3%. Overall, our preliminary in vitro findings reveal that 3-D H-scan US imaging allows the visualization of tissue scatterer patterns and incorporation of a CNN can be used to help estimate size of the acoustic scattering objects.



中文翻译:

3-D H-Scan 超声成像和使用卷积神经网络进行散射体尺寸估计。

H-Scan 超声 (US) 是一种新的成像技术,可估计声散射物体和结构的相对大小。本研究的目的是介绍一种三维 (3-D) H 扫描 US 成像方法,用于估计体积空间中的散射体大小。使用配备定制体积成像换能器(4 DL7,Vermon,Tours,France)的可编程研究扫描仪(Vantage 256,Verasonics Inc,Kirkland,法国),收集原始射频(RF)数据用于离线处理以生成 H - 扫描美国卷。一个深度卷积神经网络 (CNN) 被修改并用于实现从输入 H 扫描 US 图像到底层散射体大小的体素映射。使用嵌入不同大小(15 至 250 μm)和浓度(0.1 至 1%)的声散射体的均质明胶基组织模拟体模材料进行了初步研究。两个额外的体模嵌入了 63 或 125 µm 大小的微球,用于测试 CNN 估计精度。体外结果表明,3-D H-scan US 成像可以可视化不同浓度下不同大小的声散射体的空间分布 ( R 2 > 0.85, p < 0.03)。散射体大小估计的结果表明,CNN 可以达到 93.3% 的平均映射精度。总体而言,我们的初步体外研究结果表明,3-D H 扫描 US 成像允许组织散射模式的可视化,并且可以使用 CNN 来帮助估计声学散射对象的大小。

更新日期:2020-09-01
down
wechat
bug