PMID- 21960175
OWN - NLM
STAT- MEDLINE
DCOM- 20120806
LR  - 20211020
IS  - 1099-1492 (Electronic)
IS  - 0952-3480 (Print)
IS  - 0952-3480 (Linking)
VI  - 25
IP  - 4
DP  - 2012 Apr
TI  - Multimodal wavelet embedding representation for data combination (MaWERiC): 
      integrating magnetic resonance imaging and spectroscopy for prostate cancer 
      detection.
PG  - 607-19
LID - 10.1002/nbm.1777 [doi]
AB  - Recently, both Magnetic Resonance (MR) Imaging (MRI) and Spectroscopy (MRS) have 
      emerged as promising tools for detection of prostate cancer (CaP). However, due 
      to the inherent dimensionality differences in MR imaging and spectral 
      information, quantitative integration of T(2) weighted MRI (T(2)w MRI) and MRS 
      for improved CaP detection has been a major challenge. In this paper, we present 
      a novel computerized decision support system called multimodal wavelet embedding 
      representation for data combination (MaWERiC) that employs, (i) wavelet theory to 
      extract 171 Haar wavelet features from MRS and 54 Gabor features from T(2)w MRI, 
      (ii) dimensionality reduction to individually project wavelet features from MRS 
      and T(2)w MRI into a common reduced Eigen vector space, and (iii), a random 
      forest classifier for automated prostate cancer detection on a per voxel basis 
      from combined 1.5 T in vivo MRI and MRS. A total of 36 1.5 T endorectal in vivo 
      T(2)w MRI and MRS patient studies were evaluated per voxel by MaWERiC using a 
      three-fold cross validation approach over 25 iterations. Ground truth for 
      evaluation of results was obtained by an expert radiologist annotations of 
      prostate cancer on a per voxel basis who compared each MRI section with 
      corresponding ex vivo wholemount histology sections with the disease extent 
      mapped out on histology. Results suggest that MaWERiC based MRS T(2)w 
      meta-classifier (mean AUC, mu = 0.89 +/- 0.02) significantly outperformed (i) a 
      T(2)w MRI (using wavelet texture features) classifier (mu = 0.55 +/- 0.02), (ii) a 
      MRS (using metabolite ratios) classifier (mu = 0.77 +/- 0.03), (iii) a decision 
      fusion classifier obtained by combining individual T(2)w MRI and MRS classifier 
      outputs (mu = 0.85 +/- 0.03), and (iv) a data combination method involving a 
      combination of metabolic MRS and MR signal intensity features (mu = 0.66 +/- 0.02).
CI  - Copyright (c) 2011 John Wiley & Sons, Ltd.
FAU - Tiwari, P
AU  - Tiwari P
AD  - Department of Biomedical Engineering, Rutgers University, Piscataway, NJ, USA.
FAU - Viswanath, S
AU  - Viswanath S
FAU - Kurhanewicz, J
AU  - Kurhanewicz J
FAU - Sridhar, A
AU  - Sridhar A
FAU - Madabhushi, A
AU  - Madabhushi A
LA  - eng
GR  - R01 CA136535-03/CA/NCI NIH HHS/United States
GR  - R03 CA143991-02/CA/NCI NIH HHS/United States
GR  - R03 CA143991/CA/NCI NIH HHS/United States
GR  - R01 CA136535/CA/NCI NIH HHS/United States
GR  - R21 CA127186/CA/NCI NIH HHS/United States
GR  - R01CA136535-01/CA/NCI NIH HHS/United States
GR  - R01CA140772 01/CA/NCI NIH HHS/United States
GR  - R03CA143991-01/CA/NCI NIH HHS/United States
GR  - R43 EB015199-01/EB/NIBIB NIH HHS/United States
GR  - R01 CA140772/CA/NCI NIH HHS/United States
GR  - R21CA127186 01/CA/NCI NIH HHS/United States
GR  - R01 CA140772-02/CA/NCI NIH HHS/United States
GR  - R01 CA137207/CA/NCI NIH HHS/United States
PT  - Journal Article
PT  - Research Support, N.I.H., Extramural
PT  - Research Support, Non-U.S. Gov't
PT  - Research Support, U.S. Gov't, Non-P.H.S.
DEP - 20110930
PL  - England
TA  - NMR Biomed
JT  - NMR in biomedicine
JID - 8915233
RN  - 0 (Biomarkers, Tumor)
SB  - IM
MH  - Aged
MH  - Aged, 80 and over
MH  - Biomarkers, Tumor/*analysis
MH  - Diagnosis, Computer-Assisted/*methods
MH  - Humans
MH  - Magnetic Resonance Imaging/*methods
MH  - Magnetic Resonance Spectroscopy/*methods
MH  - Male
MH  - Middle Aged
MH  - Pattern Recognition, Automated/methods
MH  - Prostatic Neoplasms/*diagnosis/*metabolism
MH  - Reproducibility of Results
MH  - Sensitivity and Specificity
MH  - Systems Integration
MH  - *Wavelet Analysis
PMC - PMC3298634
MID - NIHMS338146
EDAT- 2011/10/01 06:00
MHDA- 2012/08/07 06:00
PMCR- 2013/04/01
CRDT- 2011/10/01 06:00
PHST- 2011/03/01 00:00 [received]
PHST- 2011/06/28 00:00 [revised]
PHST- 2011/06/29 00:00 [accepted]
PHST- 2011/10/01 06:00 [entrez]
PHST- 2011/10/01 06:00 [pubmed]
PHST- 2012/08/07 06:00 [medline]
PHST- 2013/04/01 00:00 [pmc-release]
AID - 10.1002/nbm.1777 [doi]
PST - ppublish
SO  - NMR Biomed. 2012 Apr;25(4):607-19. doi: 10.1002/nbm.1777. Epub 2011 Sep 30.