Editorial Biomedical Signal and Image Processing for ...downloads.hindawi.com/journals/cmmm/2015/974592.pdfKayvanNajarian, 1 KevinR.Ward, 2 andShahramShirani 3 Department of Computational

EditorialBiomedical Signal and Image Processing forClinical Decision Support Systems 2014

Kayvan Najarian,1 Kevin R. Ward,2 and Shahram Shirani3

1Department of Computational Medicine and Bioinformatics and Department of Emergency Medicine,Michigan Center for Integrative Research in Critical Care, University of Michigan, Ann Arbor, MI, USA2Department of Emergency Medicine, Michigan Center for Integrative Research in Critical Care,University of Michigan, Ann Arbor, MI, USA3Department of Electrical and Computer Engineering, McMaster University, Hamilton, ON, Canada

Correspondence should be addressed to Kayvan Najarian; [email protected]

Received 6 April 2015; Accepted 6 April 2015

Copyright © 2015 Kayvan Najarian et al. This is an open access article distributed under the Creative Commons AttributionLicense, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properlycited.

Abundance of data produced by a growing number of newdiagnostic and monitoring devices has provided caregiverswith a large number of data streams to consider at the timeof clinical decision-making. One of the main challenges oftoday’s medicine is to analyze these tremendous amounts ofcomplex patient data in an increasing number of complexclinical decisions. Moreover, the human eye may not be ableto detect and interpret complex patterns hidden in variousclinical data, in particular when interpreting physiologic sig-nals and images. Considering the need to make rapid clinicaldecisions, typically in stressful environments, the urgency todevelop efficient quantitative approaches to analyze complexpatient data can be further recognized. Specifically, there isclear need for novel signal and image processing algorithmsthat can create recommendations and/or predictions forhealthcare providers, in a variety of clinical decision-making.The performance and capabilities of these quantitative meth-ods are expected to match the complexity and size of therapidly evolving imaging and measurement systems.

This special issue is the second of the series, intendedas an update on the current status of, and advances in,biomedical signal and image processing methods used forclinical decision support systems. The quantitative methodspresented in this issue cover a wide spectrum of algorithmicsolutions designed for a variety of clinical applications.

The paper by C. Feng et al. introduces an algorithm forcorrection of lung boundary in X-ray computed tomography

(CT) that utilizes split Bregmanmethod and geometric activecontour model (ASM). K. B. Kim et al. apply fuzzy ARTand image processing techniques to develop an automaticmethod to extract appendix in ultrasonography. S. Yazdani etal. present an automatic hybrid image segmentation methodthat integrates themodified statistical expectationmaximiza-tion (EM) method and the spatial information combinedwith support vector machines (SVMs) and apply that tosegmentation of brain MR images. Modified active contourmodels (ACMs) are used in the paper by Y. Huang andZ. Liu to segment and track lymphocytes in phase contrastmicroscopy (PCM) images. In an attempt to improve theendoscopic images, used in diagnosis of various gastrointesti-nal (GI) tract related diseases, M. S. Imtiaz and K. A. Wahidpresent a computational method that utilizes an adaptivesigmoid function and space-variant color reproduction forcolor enhancement. The performances of different methodsof feature reduction methods, combined with a variety ofclassifiers, in detection of malignant tumors in breast imagesare compared byA.Mert et al. In a paper byM. Sterling et al. acomputer-aided clinical decision support system is designedto predict the success of postcardioversion treatments amongpatients with persistent atrial fibrillation.

As more advanced imaging and monitoring systems aredeveloped andmore clinicalmeasurements become available,the quantitative algorithms need to be further improved toanalyze the resulting complex data. These algorithms are

Hindawi Publishing CorporationComputational and Mathematical Methods in MedicineVolume 2015, Article ID 974592, 2 pageshttp://dx.doi.org/10.1155/2015/974592

2 Computational and Mathematical Methods in Medicine

expected to help not only extract new hidden knowledgefrom complex patient data, but also provide rapid predictiverecommendations to assist healthcare providers in makingbetter andmore informeddecisions. In addition, it should notbe lost that these and other new computational approachesto data will actually better lead us to develop newmonitoringand image systems proactively. The papers presented in thisspecial issue outline some of the current computationalmethods in biomedical and signal analysis.

Kayvan NajarianKevin R. Ward

Shahram Shirani

Submit your manuscripts athttp://www.hindawi.com

Stem CellsInternational

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014


MEDIATORSINFLAMMATION

of


Behavioural Neurology

EndocrinologyInternational Journal of



Disease Markers


BioMed Research International

OncologyJournal of



Oxidative Medicine and Cellular Longevity


PPAR Research

The Scientific World JournalHindawi Publishing Corporation http://www.hindawi.com Volume 2014

Immunology ResearchHindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Journal of

ObesityJournal of



Computational and Mathematical Methods in Medicine

OphthalmologyJournal of


Diabetes ResearchJournal of



Research and TreatmentAIDS


Gastroenterology Research and Practice


Parkinson’s Disease

Evidence-Based Complementary and Alternative Medicine

Volume 2014Hindawi Publishing Corporationhttp://www.hindawi.com

Documents

Editorial Biomedical Signal and Image Processing for ...downloads.hindawi.com/journals/cmmm/2015/974592.pdfKayvanNajarian, 1 KevinR.Ward, 2 andShahramShirani 3 Department of Computational