Hindawi

BioMed Research International

Volume 2017, Article ID 1278329, 2 pages
https://doi.org/10.1155/2017/1278329

Editorial
Machine Learning in Multimodal Medical Imaging

Yong Xia,1 Zexuan Ji,2 Andrey Krylov,3 Hang Chang,4 and Weidong Cai5
1
Shaanxi Key Lab of Speech & Image Information Processing (SAIIP), School of Computer Science,
Northwestern Polytechnical University, Xi’an 710072, China
2
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
3
Faculty of Computational Mathematics & Cybernetics, Lomonosov Moscow State University, Moscow, Russia
4
Berkeley Biomedical Data Science Center (BBDS), Biological Systems and Engineering Division,
Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
5
Biomedical and Multimedia Information Technology (BMIT) Research Group, School of Information Technologies,
University of Sydney, Sydney, NSW 2006, Australia

Correspondence should be addressed to Yong Xia; yxia@nwpu.edu.cn

Received 15 February 2017; Accepted 16 February 2017; Published 5 March 2017

Copyright © 2017 Yong Xia et al. This is an open access article distributed under the Creative Commons Attribution License, which
permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Machine learning techniques have been increasingly applied Shan proposes a nonparametric Bayesian model to estimate
in the medical imaging field for developing computer-aided the response functions in dynamic medical imaging, in which
diagnosis and prognosis models. Multimodal medical imag- the nonparametric Bayesian priors are designed to favor
ing can provide us with separate yet complementary structure desirable properties of the functions and used to improve the
and function information of a patient study and hence estimation of response functions.
has transformed the way we study living bodies. Therefore, In “Two-Layer Tight Frame Sparsifying Model for Com-
using machine learning techniques to deal with multimodal pressed Sensing Magnetic Resonance Imaging,” S. Wang et
medical images is much more challenging due to the diver- al. propose a two-layer tight frame sparsifying model for
sity of biophysical-biochemical mechanisms. In these years, compressed sensing magnetic resonance imaging (MRI) by
researchers mainly adapt modern machine learning and sparsifying the image with a product of a fixed tight frame and
pattern recognition techniques such as supervised, unsuper- an adaptively learned tight frame, which is solved by a three-
vised, semisupervised, and deep learning to solve multimodal level Bregman numerical algorithm and enables accurate
medical imaging related problems. MRI reconstruction from highly undersampled data with
To record the ideas of talents and gather more contri- efficiency.
butions to these fields, this special issue was launched and In “Many is Better than One: An Integration of Multiple
supported by this journal. This special issue focuses on the Simple Strategies for Accurate Lung Segmentation in CT
new imaging modalities/methodologies and new machine Images,” Z. Shi et al. present a novel computerized tomog-
learning algorithms/applications for the further development raphy (CT) lung image segmentation method by integrating
in the multimodal medical imaging field, which will provide multiple strategies, including the guided filter to smooth the
opportunities for academics and industrial professionals to image, the optimized threshold to get binary image, region-
discuss the latest issues and progresses in the area of multi- growing strategy to extract thorax regions, and random walk
modal medical imaging. The papers contained in this special algorithm to segment lung regions and to get the state-of-the-
issue address the development and application of medical art segmentation accuracy.
image segmentation, registration, fusion, classification, image In “Pulmonary Nodule Detection Model Based on SVM
restoration, image retrieval, and computer-aided diagnosis. and CT Image Feature-Level Fusion with Rough Sets,” T.
In “Estimation of Response Functions Based on Varia- Zhou et al. present a pulmonary nodules detection algorithm
tional Bayes Algorithm in Dynamic Images Sequences,” B. based on support vector machine (SVM) and CT image
2 BioMed Research International

feature-level fusion with rough sets to improve the detection papers highlights the direction of related studies. This special
accuracy of pulmonary nodules in CT image. Both the unrea- issue illustrates the important role that machine learning
sonable feature structure and the nontightness of feature techniques play in the multimodal medical imaging fields.
representation are taken into consideration in this pulmonary
nodules detection algorithm. Acknowledgments
In “Multigrid Nonlocal Gaussian Mixture Model for Seg-
mentation of Brain Tissues in Magnetic Resonance Images,” We would like to express our appreciation to all the authors
Y. Chen et al. propose a novel segmentation method based for their informative contributions and the reviewers for their
on the regional and nonlocal information to overcome the scientific contribution and support in making this special
impact of image intensity inhomogeneities and noise in issue possible.
human brain magnetic resonance images.
Yong Xia
In “DTI Image Registration under Probabilistic Fiber
Zexuan Ji
Bundles Tractography Learning,” Z. Guo et al. propose a
Andrey Krylov
diffusion tensor imaging (DTI) image registration method
Hang Chang
under probabilistic fiber bundles tractography learning,
Weidong Cai
where the residual error model is modified with finite sample
set and the calculated deformation field is then registered on
the DTI images.
In “Automated Segmentation of Coronary Arteries based
on Statistical Region Growing and Heuristic Decision
Method,” Y. Tian et al. propose a fully automated coronary
artery segmentation from cardiac data volume based on a
statistics region growing together with a heuristic decision to
further help cardiovascular radiologists detect and quantify
stenosis.
In “Rapid Retrieval of Lung Nodule CT Images Based
on Hashing and Pruning Methods,” L. Pan et al. propose a
new retrieval framework based on a hashing method for lung
nodule CT images, which can translate high-dimensional
image features into a compact hash code to greatly reduce
the retrieval time and memory space. Moreover, a pruning-
based decision rule is utilized in this algorithm to improve its
retrieval precision.
In “The Classification of Tongue Colors with Standard-
ized Acquisition and ICC Profile Correction in Traditional
Chinese Medicine,” Z. Qi et al. design a tongue color classi-
fication approach using a standardized tongue image acquisi-
tion process, color correction, and several machine learning
techniques for tongue inspection-based diagnosis in tradi-
tional Chinese medicine.
In “Diagnostic Method of Diabetes Based on Support
Vector Machine and Tongue Images,” J. Zhang et al. develop
a SVM-based diagnostic method for diabetes using stan-
dardized tongue images. This work shows the potential of
applying digitalized tongue images, which are usually used in
traditional Chinese medicine, to the diagnosis of diabetes.
In “A Computer-Aided Analysis Method of SPECT Brain
Images for Quantitative Treatment Monitoring: Performance
Evaluations and Clinical Applications,” X. Zheng et al.
introduce and validate a computer-aided analysis method
to achieve the quantitative treatment monitoring based
on single-photon emission computed tomography (SPECT)
images, which can provide a convenient solution to generate
a parametric image and derive the quantitative indexes from
the longitudinal SPECT brain images for treatment monitor-
ing.
The papers in this special issue provide a useful message
of machine learning techniques in dealing with multimodal
medical images. This unique and informative collection of
 MEDIATORS of

INFLAMMATION

The Scientific Gastroenterology Journal of

World Journal
Hindawi Publishing Corporation
Research and Practice
Hindawi Publishing Corporation
Hindawi Publishing Corporation
Diabetes Research
Hindawi Publishing Corporation
Disease Markers
Hindawi Publishing Corporation
http://www.hindawi.com Volume 2014
http://www.hindawi.com Volume 2014 http://www.hindawi.com Volume 2014 http://www.hindawi.com Volume 2014 http://www.hindawi.com Volume 2014

Journal of International Journal of

Immunology Research
Hindawi Publishing Corporation
Endocrinology
Hindawi Publishing Corporation
http://www.hindawi.com Volume 2014 http://www.hindawi.com Volume 2014

Submit your manuscripts at

https://www.hindawi.com

BioMed
PPAR Research
Hindawi Publishing Corporation
Research International
Hindawi Publishing Corporation
http://www.hindawi.com Volume 2014 http://www.hindawi.com Volume 2014

Journal of
Obesity

Evidence-Based
Journal of Stem Cells Complementary and Journal of
Ophthalmology
Hindawi Publishing Corporation
International
Hindawi Publishing Corporation
Alternative Medicine
Hindawi Publishing Corporation Hindawi Publishing Corporation
Oncology
Hindawi Publishing Corporation
http://www.hindawi.com Volume 2014 http://www.hindawi.com Volume 2014 http://www.hindawi.com Volume 2014 http://www.hindawi.com Volume 2014 http://www.hindawi.com Volume 2014

Parkinson’s
Disease

Computational and
Mathematical Methods
in Medicine
Behavioural
Neurology
AIDS
Research and Treatment
Oxidative Medicine and
Cellular Longevity
Hindawi Publishing Corporation Hindawi Publishing Corporation Hindawi Publishing Corporation Hindawi Publishing Corporation Hindawi Publishing Corporation
http://www.hindawi.com Volume 2014 http://www.hindawi.com Volume 2014 http://www.hindawi.com Volume 2014 http://www.hindawi.com Volume 2014 http://www.hindawi.com Volume 2014