TitleA hierarchical spectral clustering and nonlinear dimensionality reduction scheme for detection of prostate cancer from magnetic resonance spectroscopy (MRS)
Uniform TitleMedical physics
PublisherAmerican Association of Physicists in Medicine
NameTiwari, Pallavi (Author), Rosen, Mark (Author), Madabhushi, Anant (author), National Institutes of Health (U.S.), National Cancer Institute (U.S.),
Date Created2009
Subjectmagnetic resonance spectroscopy,
Magnetic resonance imaging,
computer-aided diagnosis,
Diagnostic imaging,
Prostate--Cancer,
nonlinear dimensionality reduction,
hierarchical clustering,
unsupervised classification
DescriptionIn this article the authors present a novel CAD scheme that integrates nonlinear dimensionality reduction (NLDR) with an unsupervised hierarchical clustering algorithm to automatically identify suspicious regions on the prostate using MRS and hence avoids the need to explicitly identify metabolite peaks.
NoteThe published version of this article is available at:
http://scitation.aip.org/getpdf/servlet/GetPDFServlet?filetype=pdf&id=MPHYA6000036000009003927000001&idtype=cvips&prog=normal
Notedoi:10.1118/1.3180955
NoteTiwari, Pallavi, Mark Rosen and Anant Madabhushi. A hierarchical spectral clustering and nonlinear dimensionality reduction scheme for detection of prostate cancer from magnetic resonance spectroscopy (MRS). Medical Physics 36(9):3927–3939, 2009
NoteThis work was made possible via grants from the Wallace H. Coulter Foundation, New Jersey Commission on Cancer Research, National Cancer Institute (Grant Nos. R01CA136535-01, ARRA-NCl-3 R21CA127186–02S1, R21CA127186–01, and R03CA128081-01), the Society for Imaging Informatics in Medicine (SIIM), The Cancer Institute of New Jersey, and the Life Science Commercialization Award from Rutgers University.
Genrearticles
Persistent URLhttp://hdl.rutgers.edu/1782.1/rucore30023100001.Manuscript.000057237
LanguageEnglish
CollectionMadabhushi Anant Collection
Organization NameRutgers, The State University of New Jersey
RightsThis object has been provided to the NJDH after a copyright, permissions, and usage rights evaluation. The object may be copyright protected. You may make use of the NJDH-held copyrighted information under a Creative Commons Attribution-NonCommercial 3.0 Unported license (see http://creativecommons.org/licenses/by-nc/3.0/). If undeclared, you may need to contact the rights holder for permission for further use. If you can provide further information on the rights or history of this work, or for guidance on attribution or citing this object, please check at http://www.njdigitalhighway.org/contact.php.