|
INDEXED BY
 
CONFERENCE TO BE HELD IN
Tokyo, Japan
SPONSORED BY
SUPPORTED BY
|
KEYNOTE
SPEAKER OF ICBET 2021
Keynote Speaker I
Prof. Walter Herzog
University of Calgary, Canada
Dr. Herzog did his undergraduate training
in Physical Education at the Federal Technical Institute in
Zurich, Switzerland (1979), completed his doctoral research
in Biomechanics at the University of Iowa (USA) in 1985, and
completed postdoctoral fellowships in Neuroscience and
Biomechanics in Calgary, Canada in 1987. Currently, Dr.
Herzog is a Professor of Biomechanics with appointments in
Kinesiology, Medicine, Engineering, and Veterinary Medicine,
holds the Canada Research Chair for Cellular and Molecular
Biomechanics, and is appointed the Killam Memorial Chair for
Inter-Disciplinary Research at the University of Calgary.
His research interests are in musculoskeletal biomechanics
with emphasis on mechanisms of muscle contraction focusing
on the role of the structural protein titin, and the
biomechanics of joints focusing on mechanisms of onset and
progression of osteoarthritis. Dr. Herzog is the recipient
of the Borelli Award from the American Society of
Biomechanics, the Career Award from the Canadian Society for
Biomechanics, the Dyson Award from the International Society
of Biomechanics in Sports, the Muybridge Award from the
International Society of Biomechanics, and recently received
the Killam Prize in Engineering from the Canada Council for
the Arts for his contributions to Biomedical research. He is
the past president of the International, American and
Canadian Societies for Biomechanics. He was inducted into
the Royal Society of Canada in 2013.
Speech Title: "Recent Observations on the
Molecular Mechanisms of Muscle Contraction"
Abstract: Eccentric muscle contractions
are not well captured by the cross-bridge theory of muscle
contraction. Specifically, the permanent extra force
obtained after stretching an active muscle cannot be
explained with current thinking. We discovered that aside
from the contractile proteins, actin and myosin, the
filamentous protein titin is also involved in active force
regulation. Using genetic modifications of titin, anti-body
labeling of titin within myofibrils, and first ever
mechanical measurements on mechanically isolated sarcomeres,
we identified how titin functions in situ in skeletal and
cardiac muscles. We found that elongation of titin in active
and passive muscle differ. In passive muscle, the entire
filament is elongating upon muscle stretching, while in
active muscle only the distal elements elongate; the
proximal segments remain at a constant length. Furthermore,
genetic deletion of the N2A segment changes titin’s in situ
function dramatically. Finally, titin works similarly in
cardiac and skeletal muscle, despite vastly different
isoforms and reports in the literature to the contrary. We
conclude that titin is responsible for the extra permanent
force following elongation of active muscles in cardiac and
skeletal tissues and suggest that titin does this by binding
its proximal segments to actin upon muscle activation.
Keynote Speaker II
Prof. Irene Yu-Hua Gu
Chalmers University of Technology, Sweden
Dr. Irene Yu-Hua Gu received Ph.D. degree
in electrical engineering from Eindhoven University of
Technology, Eindhoven, The Netherlands, in 1992. From 1992
to 1996, she was Research Fellow at Philips Research
Institute IPO, Eindhoven, The Netherlands, post dr. at
Staffordshire University, Staffordshire, U.K., and Lecturer
at the University of Birmingham, Birmingham, U.K. Since
1996, she has been with the Department of Electrical
Engineering (previous name: Department of Signals and
Systems), Chalmers University of Technology, Gothenburg,
Sweden, where she has been a Professor since 2004. Her
research interests include statistical image and video
processing, video object tracking and recognition, machine
learning and deep learning, and signal processing with
applications. During the last several years her main
research has been focused on biomedical image analysis and
deep learning. Dr. Gu was an Associate Editor for IEEE
Transactions on Systems, Man, and Cybernetics, Part A:
Systems and Humans, and Part B: Cybernetics from 2000 to
2005, and Associate Editor for EURASIP Journal on Advances
in Signal Processing from 2005 to 2016, Editorial Board of
the Journal of Ambient Intelligence and Smart Environments
from 2011 to 2019. She was elected as the Chair of the IEEE
Swedish Signal Processing Chapter from 2001 to 2004. She is
a senior member of IEEE. She has coauthored over 200 papers,
and has been ranked as the top 50 scientists in the field of
Computer Science and Electronics in Sweden in the 6th
Edition of 2020 ranking by Guide2Research team.
Speech Title: "Deep Learning Methods for
Assisting Medical Diagnosis of Neurological Diseases: Some
Methods, Possibilities and Challenges"
Abstract: Recent developments in imaging
technology have revolutionized healthcare. Medical images
are widely used for diagnosis and therapy monitoring with
significant impact on patient treatment outcome. Despite
these advances, routine clinical MRI data interpretation is
still performed mostly by human experts. There has been an
impressive progress in deep learning, however, deep
learning-assisted medical diagnosis of neurological diseases
remains a challenged research area. In this talk, we will
describe several deep learning methods on MR images. These
methods show great potentials, for example, in
computer-assisted diagnosis of Alzheimer’s disease, or
prediction of brain tumor molecular subtypes without biopsy.
We also discuss common challenges when dealing with medical
datasets, for example, combination of several small medical
datasets, incomplete MRI data of individual patients, or,
partly annotated training datasets. These issues may impact
the training process, leading to low generalization
performance on the test data. We then describe several
possible solutions to these challenging issues, including
domain mapping for combining small training datasets, MRI
data augmentation for generating missing data and fake
patients’ data. Finally, we demonstrate that these methods
are rather effective and may offer great potentials for
future research in this area.
INVITED
SPEAKER
To be added.
|
