Automatic fascicle length estimation on muscle ultrasound images with an orientation sensitive segmentation

OUR OFFICES @CHENNAI/ TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE / BANGALORE / HYDRABAD
CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
IEEE SOFTWARE | EMBEDDED | MECHANICAL | ROBOTICS PROJECTS DEVELOPMENT
Visit: www.ecwaytechnologies.com | www.ecwayprojects.com Mail to: ecwaytechnologies@gmail.com
AUTOMATIC FASCICLE LENGTH ESTIMATION ON MUSCLE ULTRASOUND
IMAGES WITH AN ORIENTATION-SENSITIVE SEGMENTATION
By
A
PROJECT REPORT
Submitted to the Department of electronics &communication Engineering in the
FACULTY OF ENGINEERING & TECHNOLOGY
In partial fulfillment of the requirements for the award of the degree
Of
MASTER OF TECHNOLOGY
IN
ELECTRONICS &COMMUNICATION ENGINEERING
APRIL 2016

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
CERTIFICATE
Certified that this project report titled “Automatic Fascicle Length Estimation on Muscle
Ultrasound Images with an Orientation-Sensitive Segmentation” is the bonafide work of Mr.
_____________Who carried out the research under my supervision Certified further, that to the
best of my knowledge the work reported herein does not form part of any other project report or
dissertation on the basis of which a degree or award was conferred on an earlier occasion on this
or any other candidate.
Signature of the Guide Signature of the H.O.D
Name Name

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
DECLARATION
I hereby declare that the project work entitled “Automatic Fascicle Length Estimation on
Muscle Ultrasound Images with an Orientation-Sensitive Segmentation” Submitted to
BHARATHIDASAN UNIVERSITY in partial fulfillment of the requirement for the award of the
Degree of MASTER OF APPLIED ELECTRONICS is a record of original work done by me the
guidance of Prof.A.Vinayagam M.Sc., M.Phil., M.E., to the best of my knowledge, the work
reported here is not a part of any other thesis or work on the basis of which a degree or award was
conferred on an earlier occasion to me or any other candidate.
(Student Name)
(Reg.No)
Place:
Date:

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
ACKNOWLEDGEMENT
I am extremely glad to present my project “Automatic Fascicle Length Estimation on Muscle
Ultrasound Images with an Orientation-Sensitive Segmentation” which is a part of my
curriculum of third semester Master of Science in Computer science. I take this opportunity to
express my sincere gratitude to those who helped me in bringing out this project work.
I would like to express my Director,Dr. K. ANANDAN, M.A.(Eco.), M.Ed., M.Phil.,(Edn.),
PGDCA., CGT., M.A.(Psy.)of who had given me an opportunity to undertake this project.
I am highly indebted to Co-OrdinatorProf. Muniappan Department of Physics and thank from
my deep heart for her valuable comments I received through my project.
I wish to express my deep sense of gratitude to my guide
Prof. A.Vinayagam M.Sc., M.Phil., M.E., for her immense help and encouragement for
successful completion of this project.
I also express my sincere thanks to the all the staff members of Computer science for their kind
advice.
And last, but not the least, I express my deep gratitude to my parents and friends for their
encouragement and support throughout the project.

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
ABSTRACT:
Fascicle length obtained by ultrasound imaging is one of the crucial muscle architecture
parameters for understanding the contraction mechanics and pathological conditions of muscles.
However, the lack of a reliable automatic measurement method restricts the application of fascicle
length for the analysis of muscle function, as frame-by-frame manual measurement is time-
consuming. In this study, we propose an automatic measurement method to preclude the influence
of non-fascicle components on the estimation of fascicle length by using motion estimation of
fascicle structures. Methods: The method starts with image segmentation using the cohesiveness
of fascicle orientation as a feature, obtaining the fascicle change by tracking manually marked
points on the fascicular path with the Lucas–Kanade optical flow algorithm applied on the
segmented image. Results: The performance of this method was evaluated on ultrasound images
of the gastrocnemius obtained from 7 healthy subjects (34.4 ± 5.0 years). Waveform similarity
between the manual and dynamic measurements was assessed by calculating the overall similarity
with the coefficient of multiple correlation (CMC). In vivo experiments demonstrated that fascicle
tracking with the orientation-sensitive segmentation (CMC = 0.97 ± 0.01) was more consistent
with the manual measurements than existing automatic methods (CMC = 0.87 ±0.10). Conclusion:
Our method was robust to the interference of non-fascicle components, resulting in a more reliable
measurement of fascicle length. Significance: The proposed method may facilitate further research
and applications related to real-time architectural change of muscles.

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
INTRODUCTION:
Muscle imaging is a promising field of research in understanding the biological and
bioelectrical characteristics of muscles, as well as assessing their function and pathological
conditions through the observation of muscle architectural change, since muscle activation is
closely related to its structure. Recently, sonomyography (SMG), representing the real-time
change of muscle architecture obtained using ultrasound imaging, has been proposed as a
noninvasive option to measure muscle activation under different contractions. It has been reported
that muscle architecture, primarily delineated by geometric layout of the fascicles within the
skeletal muscle, including fascicle length and pennation angle, is highly correlated with muscle
contraction. SMG has showed its potential in both diagnosis and rehabilitation assessment in vivo,
as a reliable research and clinical tool. It has been used to monitor treatment outcomes for patients
with motor problems, prepare rehabilitation plans for patients with surgical operations and control
powered prostheses.
Fascicle length is the most often used SMG parameter to quantify changes in the fascicle
geometry of muscle. Since the ability of muscle to generate force is largely determined by its
fascicle length, the change of fascicle length has been examined in response to contraction, aging
fatigue and physical training. Moreover, modulation of the fascicle-tendinous tissue interaction,
which occurs to make the movement more economic via effective utilization of tendinous tissue
elasticity for specific movement tasks, can also be estimated from changes of fascicle and tendon
length. This morphometric skeletal muscle parameter is therefore of great importance to
understanding the mechanism of muscle contraction. Although the manual measurement of
fascicle length was reported to be reproducible the method is time-consuming and subjective,
restricting the application of fascicle length in the dynamic analysis of muscle function, especially
when dealing with a sequence of ultrasound images. Since fascicles are usually non-uniformly
distributed as line-like structures in ultrasound images some automatic fascicle detection
approaches based on the Hough or Radon transforms have been proposed for estimating fascicle
length.
However, the fascicle structures are often obscured by speckle noise, making it difficult to
locate them accurately. Moreover, intramuscular blood vessels are also visible as line-like
structures in the fascicle region of some ultrasound images , resulting in incorrect measurements

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
of fascicle length. Motion between successive images has also been used to estimate fascicle length
by observing the continuous changes in the fascicle region. Under the assumption that
homogeneous affine transformations are applicable in the muscle region, Cronin, et al.
Estimated global affine transform parameters with the Lucas-Kanade optical flow
algorithm , by regarding a selected fascicle region as a whole patch to derive the changes in fascicle
length. Based on the assumption of straight fascicles, fascicle length was identified by calculating
the displacement of predefined points on the fascicular path using the global affine transform
parameters. In this approach, the accumulation of errors in tracking small regions of interest (ROI)
was avoided by estimating global movement over a large region. Nonetheless the non-fascicle
components of speckle noise that can violate the assumption of homogeneous affine
transformations were not taken into account which could lead to inaccurate estimation of fascicle
length in some images. Using the framework of Bayesian multiple hypotheses, the Kanade-Lucas-
Tomasi (KLT) feature trackers. combined with visible fascicle structures has also been proposed
to estimate changing fascicle shape .
About 200 non-overlapping square feature templates with a size 15×15 pixels, derived in
the fascicle region using multi-resolution active shape model training, were tracked using KLT
weighted by a multi-scale vessel enhancement map. This map was used to obtain global fascicle
displacements and changes of fascicle length with the particle filter, thus allowing recovery from
small tracking errors. However, the weight of non-fascicle components, such as visible
intramuscular blood vessels, was also increased in the calculation, possibly influencing the
estimation of fascicle length. Moreover, the time-consuming multi-resolution active shape model
segmentation and particle filter also restricted the application of this approach
In this study, under the assumption of homogeneous affine transformations, we propose an
automatic method for estimating the change of fascicle length in consecutive ultrasound images
by calculating global affine transform parameters over the effective fascicle region obtained with
an orientation-sensitive segmentation algorithm, in order to address the limitations of currently
available approaches. The orientation-sensitive segmentation algorithm was designed to segment
visible fascicle structures from the whole muscle region based on the observation of similar
orientations of fascicles in muscles.

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
CONCLUSION:
We have successfully developed a new approach using orientation-sensitive segmentation
for automatically estimating fascicle length in a series of ultrasound images utilizing prior
knowledge of the orientations of fascicles. The orientation-sensitive segmentation algorithm
precluded the influence of non-fascicle components on the calculation of affine transform
parameters, resulting in a more reliable measurement of fascicle length. The results obtained using
the proposed approach showed good agreement with those obtained by manual measurements. The
method therefore provides an alternative dynamic measurement of muscle activation with
ultrasound imaging to analyze muscle function in human motion analysis. Future studies with a
large group of subjects and other types of motion such as walking will be conducted to further
demonstrate the potential of this new method for full understanding of muscle activation. The
performance of the newly proposed method can also be further enhanced by using GPU
programming to achieve real-time application in future studies.

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
REFERENCES:
[1] V. M. Zatsiorsky, and B. I. Prilutsky, Biomechanics of Skeletal Muscles: Human Kinetics,
2012.
[2] Y. P. Zheng et al., “Sonomyography: Monitoring morphological changes of forearm muscles
in actions with the feasibility for the control of powered prosthesis,” Medical Engineering &
Physics, vol. 28, no. 5, pp. 405-415, Jun, 2006.
[3] A. A. Mohagheghi et al., “In vivo gastrocnemius muscle fascicle length in children with and
without diplegic cerebral palsy,” Developmental Medicine and Child Neurology, vol. 50, no. 1,
pp. 44-50, Jan, 2008.
[4] L. Barber et al., “Medial gastrocnemius muscle fascicle active torque-length and Achilles
tendon properties in young adults with spastic cerebral palsy,” Journal of Biomechanics, vol. 45,
no. 15, pp. 2526-2530, Oct, 2012.
[5] C. Suetta et al., “Resistance training induces qualitative changes in muscle morphology,
muscle architecture, and muscle function in elderly postoperative patients,” Journal of Applied
Physiology, vol. 105, no. 1, pp. 180-186, Jul, 2008.
[6] X. Chen et al., “Sonomyography (SMG) control for powered prosthetic hand: a study with
normal subjects.,” Ultrasound in Medicine and Biology, vol. 36, no. 7, pp. 1076-1088, Jul, 2010.
[7] J. Y. Guo et al., “Towards the application of one-dimensional sonomyography for powered
upper-limb prosthetic control using machine learning models,” Prosthetics and Orthotics
International, vol. 37, no. 1, pp. 43-49, Feb, 2013.

Automatic fascicle length estimation on muscle ultrasound images with an orientation sensitive segmentation

Recommended

Recommended

More Related Content

Recently uploaded

Recently uploaded (20)

Featured

Featured (20)

Automatic fascicle length estimation on muscle ultrasound images with an orientation sensitive segmentation