Share Email Print

Proceedings Paper

Stabilized ultrasound imaging of a moving object using 2D B-mode images and convolutional neural network
Author(s): Tian Xie; Mahya Shahbazi; Yixuan Wu; Russell H. Taylor; Emad M. Boctor
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We present a co-robotic ultrasound imaging system that tracks lesions undergoing physiological motions, e.g., breathing, using 2D B-mode images. The approach embeds the in-plane and out-of-plane transformation estimation in a proportional joint velocity controller to minimize the 6-degree-of-freedom (DoF) transformation error. Specifically, we propose a new method to estimate the out-of-plane translation using a convolutional neural network based on speckle decorrelation. The network is trained on anatomically featureless gray-scale B-mode images and is generalized to different tissue phantoms. The tracking algorithm is validated in simulation with mimicked respiratory motions, which demonstrates the feasibility of stabilizing biopsy through ultrasound guidance.

Paper Details

Date Published: 16 March 2020
PDF: 11 pages
Proc. SPIE 11315, Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling, 113150C (16 March 2020); doi: 10.1117/12.2550198
Show Author Affiliations
Tian Xie, Johns Hopkins Univ. (United States)
Mahya Shahbazi, Johns Hopkins Univ. (United States)
Yixuan Wu, Johns Hopkins Univ. (United States)
Russell H. Taylor, Johns Hopkins Univ. (United States)
Emad M. Boctor, Johns Hopkins Univ. (United States)

Published in SPIE Proceedings Vol. 11315:
Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling
Baowei Fei; Cristian A. Linte, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?