Faster super-resolution ultrasound imaging with a deep learning model for tissue decluttering and contrast agent localization.
Faster super-resolution ultrasound imaging with a deep learning model for tissue decluttering and contrast agent localization.
复制标题
利用深度学习模型实现更快的超分辨率超声成像，用于组织清理和造影剂定位。
DOI：
10.1088/2057-1976/ac2f71
复制
发表时间：
2021-10-25
影响因子：
1.4
通讯作者：
Hoyt K
中科院分区：
文献类型：
--
作者：
Brown KG;Waggener SC;Redfern AD;Hoyt K
超分辨率超声（SR-US）成像允许可视化微血管结构小到直径几十微米。然而，由于超声（US）采集时间超过屏气时间，以及需要大量的离线计算，在临床环境中的使用一直受到阻碍。深度学习技术在模拟微泡（MB）造影剂检测和定位这两个计算更密集的步骤方面已被证明是有效的。与传统方法相比，深度网络的性能提高了两个数量级以上，此外，该网络还可以定位重叠的mb。分离重叠mb的能力允许使用更高的造影剂浓度，并减少美国图像采集时间。本文提出了一种全卷积神经网络（CNN）架构，用于在单个模型中执行MB检测和定位操作。该网络被称为SRUSnet，基于MobileNetV3架构，针对3d输入数据、最小收敛时间和使用灵活回归头的高分辨率数据输出进行了修改。此外，我们建议将线性b模式US成像与非线性对比脉冲序列（CPS）相结合，这已被证明可以提高MB检测并进一步缩短US图像采集时间。该网络使用计算机数据进行训练，并在体外模拟组织流动模型数据和大鼠后肢体内数据（N = 3）上进行测试。使用L11-4v线性阵列换能器，使用可编程美国系统（Vantage 256, Verasonics Inc., Kirkland， WA）收集图像。该网络在计算机数据上的检测准确率超过99.9%。平均定位精度小于像素分辨率（即λ/8）。对于128 × 128像素的图像，Nvidia GeForce 2080Ti GPU的平均处理时间为64.5 ms。
Super-resolution ultrasound (SR-US) imaging allows visualization of microvascular structures as small as tens of micrometers in diameter. However, use in the clinical setting has been impeded in part by ultrasound (US) acquisition times exceeding a breath-hold and by the need for extensive offline computation. Deep learning techniques have been shown to be effective in modeling the two more computationally intensive steps of microbubble (MB) contrast agent detection and localization. Performance gains by deep networks over conventional methods are more than two orders of magnitude and in addition the networks can localize overlapping MBs. The ability to separate overlapping MBs allows use of higher contrast agent concentrations and reduces US image acquisition time. Herein we propose a fully convolutional neural network (CNN) architecture to perform the operations of MB detection as well as localization in a single model. Termed SRUSnet, the network is based on the MobileNetV3 architecture modified for 3-D input data, minimal convergence time, and high-resolution data output using a flexible regression head. Also, we propose to combine linear B-mode US imaging and nonlinear contrast pulse sequencing (CPS) which has been shown to increase MB detection and further reduce the US image acquisition time. The network was trained with in silico data and tested on in vitro data from a tissue-mimicking flow phantom, and on in vivo data from the rat hind limb (N = 3). Images were collected with a programmable US system (Vantage 256, Verasonics Inc., Kirkland, WA) using an L11-4v linear array transducer. The network exceeded 99.9% detection accuracy on in silico data. The average localization accuracy was smaller than the resolution of a pixel (i.e. λ/8). The average processing time on a Nvidia GeForce 2080Ti GPU was 64.5 ms for a 128 × 128-pixel image.
登录
查看更多内容
DOI：
10.3390/diagnostics10121055
发表时间：
2020-12-06
期刊：
Diagnostics (Basel, Switzerland)
影响因子：
--
作者：
Fujioka T;Mori M;Kubota K;Oyama J;Yamaga E;Yashima Y;Katsuta L;Nomura K;Nara M;Oda G;Nakagawa T;Kitazume Y;Tateishi U
通讯作者：
Tateishi U
影响因子：
2.9
作者：
Christensen-Jeffries K;Couture O;Dayton PA;Eldar YC;Hynynen K;Kiessling F;O'Reilly M;Pinton GF;Schmitz G;Tang MX;Tanter M;van Sloun RJG
通讯作者：
van Sloun RJG
影响因子：
10.6
作者：
Demene, Charlie;Deffieux, Thomas;Tanter, Mickael
通讯作者：
Tanter, Mickael
DOI：
10.1109/tpami.2018.2858826
发表时间：
2020-02-01
影响因子：
23.6
作者：
Lin, Tsung-Yi;Goyal, Priya;Dollar, Piotr
通讯作者：
Dollar, Piotr
影响因子：
2.9
作者：
Averkiou, Michalakis A.;Bruce, Matthew F.;Burns, Peter N.
通讯作者：
Burns, Peter N.