Multimodal wavelet embedding representation for data combination (MaWERiC): integrating magnetic resonance imaging and spectroscopy for prostate cancer detection
- 30 September 2011
- journal article
- research article
- Published by Wiley in NMR in Biomedicine
- Vol. 25 (4), 607-619
- https://doi.org/10.1002/nbm.1777
Abstract
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 T2 weighted MRI (T2w 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 T2w MRI, (ii) dimensionality reduction to individually project wavelet features from MRS and T2w 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 T2w 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 T2w meta‐classifier (mean AUC, μ = 0.89 ± 0.02) significantly outperformed (i) a T2w MRI (using wavelet texture features) classifier (μ = 0.55 ± 0.02), (ii) a MRS (using metabolite ratios) classifier (μ = 0.77 ± 0.03), (iii) a decision fusion classifier obtained by combining individual T2w MRI and MRS classifier outputs (μ = 0.85 ± 0.03), and (iv) a data combination method involving a combination of metabolic MRS and MR signal intensity features (μ = 0.66 ± 0.02). Copyright © 2011 John Wiley & Sons, Ltd.Keywords
This publication has 70 references indexed in Scilit:
- Prostate Cancer: Value of Multiparametric MR Imaging at 3 T for Detection—Histopathologifc CorrelationRadiology, 2010
- Effect of feature extraction for brain tumor classification based on short echo time 1H MR spectraMagnetic Resonance in Medicine, 2008
- Multiparametric magnetic resonance imaging in prostate cancer: present and futureCurrent Opinion in Urology, 2008
- Automated estimation of tumor probability in prostate magnetic resonance spectroscopic imaging: Pattern recognition vs quantificationMagnetic Resonance in Medicine, 2006
- Localization of Prostate Cancer Using 3T MRIJournal of Computer Assisted Tomography, 2006
- Combination of feature-reduced MR spectroscopic and MR imaging data for improved brain tumor classificationNMR in Biomedicine, 2005
- Classification of brain tumours using short echo time 1H MR spectraJournal of Magnetic Resonance, 2004
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- Improved water and lipid suppression for 3D PRESS CSI using rf band selective inversion with gradient dephasing (basing)Magnetic Resonance in Medicine, 1997
- Support-vector networksMachine Learning, 1995