看过Super-resolution reconstruction of plane-wave ultrasound imagi
需积分: 0 172 浏览量
2022-08-03
15:44:02
上传
评论
收藏 2.48MB PDF 举报
Super-Resolution Reconstruction of Plane-Wave
Ultrasound Imaging Based on the Improved CNN Method
Zixia Zhou
1
, Yuanyuan Wang
1,2
(
✉
)
, Jinhua Yu
1,2
, Wei Guo
1
, and Zhenghan Fang
1
1
Department of Electronic Engineering, Fudan University, Shanghai, China
2
Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention
of Shanghai, Fudan University, Shanghai, China
Abstract. Plane wave imaging (PWI) can cover the entire image region by using
a single plane wave transmission. The time-saving imaging mode, however,
provides poor imaging resolution and contrast. It is highly demanded for the PWI
to compensate the weakness in the imaging quality while maintain the ultrafast
imaging speed. In this paper, we proposed a multi-scaled convolutional neural
network (CNN) model to improve the quality of the PWI. To further increase the
convergence rate and robustness of the CNN, a feedback system was added into
the iteration process of the stochastic parallel gradient descent (SPGD) optimi‐
zation. Three different types of data including the simulation, phantom and real
human data have been used in the experiment with each class containing 150 pairs
of data. The proposed method produced 52% improvement in the peak signal to
noise ratio (PSNR) and 4 times improvement in the structural similarity index
measurement (SSIM) compared with the original images. Moreover, the proposed
method not only guarantees the global convergence, but also improves the
converging rate with 15% reduction of the total elapsed time.
Keywords: Ultrasound imaging · Plane wave · Super-resolution reconstruction ·
Deep learning · Convolutional neural network (CNN) · Feedback system
1 Introduction
As an important ultrasound imaging mode, plane-wave imaging (PWI) can get the entire
imaging data by just one emission. This mode greatly reduces the number of emission
in the traditional line-by-line scanning and improves the imaging frame rate consider‐
ably. The PWI usually has high temporal resolution and is suitable for three-dimensional
real-time imaging. On the other hand, because of the unfocused plane-wave beam, the
PWI has the problems of high noise and low signal-to-noise ratio, resulting in the
degraded image resolution and contrast. The poor imaging quality of the PWI limits its
development and clinical usage. Many methods have been proposed to improve the
quality of the PWI while maintain its high temporal resolution. These methods can be
divided into two groups: the adaptive beamforming methods [1, 2] and super-resolution
reconstruction based on the post image processing [3, 4]. Different from beamforming
methods that work on the raw radio-frequency (RF) signals during the imaging process,
© Springer International Publishing AG 2018
J.M.R.S. Tavares and R.M. Natal Jorge (eds.), VipIMAGE 2017,
Lecture Notes in Computational Vision and Biomechanics 27,
DOI 10.1007/978-3-319-68195-5_12
评论0