Your browser doesn't support javascript.
US-Net: A lightweight network for simultaneous speckle suppression and texture enhancement in ultrasound images.
Monkam, Patrice; Lu, Wenkai; Jin, Songbai; Shan, Wenjun; Wu, Jing; Zhou, Xiang; Tang, Bo; Zhao, Hua; Zhang, Hongmin; Ding, Xin; Chen, Huan; Su, Longxiang.
  • Monkam P; Department of Automation, Tsinghua University, Beijing, China; Beijing National Research Center for Information Science and Technology (BNRist), China. Electronic address: patrice123china1@gmail.com.
  • Lu W; Department of Automation, Tsinghua University, Beijing, China; Beijing National Research Center for Information Science and Technology (BNRist), China. Electronic address: lwkmf@mail.tsinghua.edu.cn.
  • Jin S; Department of Automation, Tsinghua University, Beijing, China; Beijing National Research Center for Information Science and Technology (BNRist), China. Electronic address: jinsongbai980112@163.com.
  • Shan W; Department of Automation, Tsinghua University, Beijing, China; Beijing National Research Center for Information Science and Technology (BNRist), China. Electronic address: swj19@mails.tsinghua.edu.cn.
  • Wu J; Department of Automation, Tsinghua University, Beijing, China; Beijing National Research Center for Information Science and Technology (BNRist), China. Electronic address: wujing.data@foxmail.com.
  • Zhou X; Department of Critical Care Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, China. Electronic address: zx_pumc@163.com.
  • Tang B; Department of Critical Care Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, China. Electronic address: mitchell_tang@163.com.
  • Zhao H; Department of Critical Care Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, China. Electronic address: hua0822zhao@sohu.com.
  • Zhang H; Department of Critical Care Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, China. Electronic address: ozohom@163.com.
  • Ding X; Department of Critical Care Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, China. Electronic address: starrydx@163.com.
  • Chen H; Department of Critical Care Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, China. Electronic address: thethechen@163.com.
  • Su L; Department of Critical Care Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing 100730, China. Electronic address: slx77@163.com.
Comput Biol Med ; 152: 106385, 2023 01.
Article in English | MEDLINE | ID: covidwho-2130528
ABSTRACT

BACKGROUND:

Numerous traditional filtering approaches and deep learning-based methods have been proposed to improve the quality of ultrasound (US) image data. However, their results tend to suffer from over-smoothing and loss of texture and fine details. Moreover, they perform poorly on images with different degradation levels and mainly focus on speckle reduction, even though texture and fine detail enhancement are of crucial importance in clinical diagnosis.

METHODS:

We propose an end-to-end framework termed US-Net for simultaneous speckle suppression and texture enhancement in US images. The architecture of US-Net is inspired by U-Net, whereby a feature refinement attention block (FRAB) is introduced to enable an effective learning of multi-level and multi-contextual representative features. Specifically, FRAB aims to emphasize high-frequency image information, which helps boost the restoration and preservation of fine-grained and textural details. Furthermore, our proposed US-Net is trained essentially with real US image data, whereby real US images embedded with simulated multi-level speckle noise are used as an auxiliary training set.

RESULTS:

Extensive quantitative and qualitative experiments indicate that although trained with only one US image data type, our proposed US-Net is capable of restoring images acquired from different body parts and scanning settings with different degradation levels, while exhibiting favorable performance against state-of-the-art image enhancement approaches. Furthermore, utilizing our proposed US-Net as a pre-processing stage for COVID-19 diagnosis results in a gain of 3.6% in diagnostic accuracy.

CONCLUSIONS:

The proposed framework can help improve the accuracy of ultrasound diagnosis.
Subject(s)
Keywords

Full text: Available Collection: International databases Database: MEDLINE Main subject: COVID-19 Testing / COVID-19 Type of study: Diagnostic study / Prognostic study / Qualitative research Limits: Humans Language: English Journal: Comput Biol Med Year: 2023 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: COVID-19 Testing / COVID-19 Type of study: Diagnostic study / Prognostic study / Qualitative research Limits: Humans Language: English Journal: Comput Biol Med Year: 2023 Document Type: Article