International Journal of Computer Assisted Radiology and Surgery
Ultrasound-based liver tracking utilizing a hybrid template/optical
· Wa Cheung
· Stuart K. Roberts
· Sunita Chauhan
Received: 26 November 2017 / Accepted: 26 April 2018
© CARS 2018
Purpose With the ongoing shift toward reduced invasiveness in many surgical procedures, methods for tracking moving
targets within the body become vital. Non-invasive treatment methods such as stereotactic radiation therapy and high intensity
focused ultrasound, in particular, rely on the accurate localization of targets throughout treatment to ensure optimal treatment
provision. This work aims at developing a robust, accurate and fast method for target tracking based on ultrasound images.
Methods A method for tracking of targets in real-time ultrasound image data was developed, based on the combination of
template matching, dense optical ﬂow and image intensity information. A weighting map is generated from each of these
approaches which are then normalized, weighted and combined, with the weighted mean position then calculated to predict
the current position. The approach was evaluated on the Challenge for Liver Ultrasound Tracking 2015 dataset, consisting of
a total of 24 training and 39 test datasets with a total of 53 and 85 annotated targets throughout the liver, respectively.
Results The proposed method was implemented in MATLAB and achieved an accuracy of 0.80 ± 0.80 (95%: 1.91) mm
and 0.74 ± 1.03 (95%: 1.85) mm on the training and test data, respectively. Tracking frequencies of between 8 and 36 fps
(mean of 22 fps) were observed, largely dependent on the size of the region of interest. The achieved results represent an
improvement in mean accuracy of approximately 0.3 mm over the reported methods in existing literature.
Conclusions This work describes an accurate and robust method for the tracking of points of interest within 2D ultrasound
data, based on a combination of multi-template matching, dense optical ﬂow and relative image intensity information.
Keywords Motion compensation · Tracking · Accuracy · Optical Flow · Template Matching · Ultrasound
Many surgical procedures are undergoing a signiﬁcant shift
toward reduced invasiveness, whether toward laparoscopic
and endoscopic minimally invasive techniques, image guided
needle-based tissue ablation or totally non-invasive meth-
Electronic supplementary material The online version of this article
(https://doi.org/10.1007/s11548-018-1780-0) contains supplementary
material, which is available to authorized users.
Department of Mechanical and Aerospace Engineering,
Monash University, Lab 298, New Horizon Building,
Wellington Rd, Clayton, Melbourne, VIC 3800, Australia
Department of Radiology, The Alfred, Commercial Road,
Department of Gastroenterology, The Alfred, Commercial
Road, Melbourne, Australia
ods such as high intensity focused ultrasound (HIFU) [1,2]
or stereotactic body radiation therapy (SBRT) [3,4]. How-
ever, for thoracic and abdominal procedures the motion of
the organs during the performance of these non-invasive
approaches introduces a number of challenges, not least
that accurate provision of treatment relies on the ability of
the treatment device to accurately locate and track the tar-
get within the body without direct visualization of the site.
Many approaches have been proposed toward this end; exter-
nal markers (either natural anatomical features or attached
artiﬁcial markers) can be tracked with high accuracy uti-
lizing commonly available stereo tracking cameras, with the
motion of the internal organs inferred from the tracked exter-
nal motion through modeling or nonlinear correlation .
The use of external tracking information has also been uti-
lized for gating, based on the assumption that the target is
at some known position when the external marker conﬁg-
uration matches that of the initial conﬁguration. However,
these external tracking methods have several drawbacks. In