Deep 3D convolutional neural networks for fast super-resolution ultrasound imaging

Katherine Brown, James Dormer, Baowei Fei, Kenneth Hoyt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Super-resolution ultrasound imaging (SR-US) is a new technique which breaks the diffraction limit and can help visualize microvascularity at a resolution of tens of microns. However, image processing methods for spatiotemporal filtering needed in SR-US for microvascular delineation, such as singular value decomposition (SVD), are computationally burdensome and must be performed off-line. The goal of this study was to evaluate a novel and fast method for spatiotemporal filtering to segment the microbubble (MB) contrast agent from the tissue signal with a trained 3D convolutional neural network (3DCNN). In vitro data was collected using a programmable ultrasound (US) imaging system (Vantage 256, Verasonics Inc, Kirkland, WA) equipped with an L11-4v linear array transducer and obtained from a tissue-mimicking vascular flow phantom at flow rates representative of microvascular conditions. SVD was used to detect MBs and label the data for training. Network performance was validated with a leave-one-out approach. The 3DCNN demonstrated a 22% higher sensitivity in MB detection than SVD on in vitro data. Further, in vivo 3DCNN results from a cancer-bearing murine model revealed a high level of detail in the SR-US image demonstrating the potential for transfer learning from a neural network trained with in vitro data. The preliminary performance of segmentation with the 3DCNN was encouraging for real-time SR-US imaging with computation time as low as 5 ms per frame.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2019
Subtitle of host publicationUltrasonic Imaging and Tomography
EditorsBrett C. Byram, Nicole V. Ruiter
PublisherSPIE
ISBN (Electronic)9781510625570
DOIs
Publication statusPublished - Jan 1 2019
EventMedical Imaging 2019: Ultrasonic Imaging and Tomography - San Diego, United States
Duration: Feb 17 2019Feb 18 2019

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume10955
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2019: Ultrasonic Imaging and Tomography
CountryUnited States
CitySan Diego
Period2/17/192/18/19

    Fingerprint

Keywords

  • Convolutional neural network
  • Image segmentation
  • Microbubble
  • Super-resolution ultrasound imaging

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Brown, K., Dormer, J., Fei, B., & Hoyt, K. (2019). Deep 3D convolutional neural networks for fast super-resolution ultrasound imaging. In B. C. Byram, & N. V. Ruiter (Eds.), Medical Imaging 2019: Ultrasonic Imaging and Tomography [1095502] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10955). SPIE. https://doi.org/10.1117/12.2511897