Multimodal Wavelet Embedding Representation for data Combination (MaWERiC): Integrating Magnetic Resonance Imaging and Spectroscopy for Prostate Cancer Detection

Department of Biomedical Engineering, Rutgers University, Piscataway, NJ, USA.
NMR in Biomedicine (Impact Factor: 3.56). 04/2012; 25(4):607-19. DOI: 10.1002/nbm.1777
Source: PubMed

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 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, μ = 0.89 ± 0.02) significantly outperformed (i) a T(2)w 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 T(2)w 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).

Download full-text


Available from: Anant Madabhushi, Aug 26, 2015
  • Source
    • "For example, while metabolic concentrations of citrate, creatine , and choline present in MRS imaging have been shown to be linked to CaP presence and Gleason grade [4], the citrate and creatine peaks are often difficult to distinguish on MRS, resulting in inconsistent measurements by different observers [10]. In order to increase accuracy and reproducibility of CaP detection and grading on MP–MRI, researchers have turned to automated machine learning approaches to build integrated, fused classifiers that quantitatively combine multiple MRI parameters [11] [12] [13] [14] [15]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Although multiparametric (MP) MRI (MP-MRI) is a valuable tool for prostate cancer (CaP) diagnosis, considerable challenges remain in the ability to quantitatively combine different MRI parameters to train integrated, fused meta-classifiers for in vivo disease detection and characterization. To deal with the large number of MRI parameters, dimensionality reduction schemes such as principal component analysis (PCA) are needed to embed the data into a reduced subspace to facilitate classifier building. However, while features in the embedding space do not provide physical interpretability, direct feature selection in the high-dimensional space is encumbered by the curse of dimensionality. The goal of this work is to identify the most discriminating MP-MRI features for CaP diagnosis and grading based on their contributions in the reduced embedding obtained by performing PCA on the full MP-MRI feature space. In this work we demonstrate that a scheme called variable importance projection (VIP) can be employed in conjunction with PCA to identify the most discriminatory attributes. We apply our new PCA-VIP scheme to discover MP-MRI markers for discrimination between (a) CaP and benign tissue using 12 studies comprised of T2-w, DWI, and DCE MRI protocols and (b) high and low grade CaP using 36 MRS studies. The PCA-VIP score identified ADC values obtained from Diffusion and Gabor gradient texture features extracted from T2- w MRI as being most significant for CaP diagnosis. Our method also identified 3 metabolites that play a role in CaP detection--polyamine, citrate, and choline--and 4 metabolites that differentially express in low and high grade CaP: citrate, choline, polyamine, and creatine. The PCA-VIP scheme offers an alternative to traditional feature selection schemes that are encumbered by the curse of dimensionality.
    Prostate Cancer Imaging. Image Analysis and Image-Guided Interventions - International Workshop, Held in Conjunction with MICCAI 2011, Toronto, Canada, September 22, 2011. Proceedings; 01/2011
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Multimodal data, especially imaging and non-imaging data, is being routinely acquired in the context of disease diagnostics; however, computational challenges have limited the ability to quantitatively integrate imaging and non-imaging data channels with different dimensionalities and scales. To the best of our knowledge relatively few attempts have been made to quantitatively fuse such data to construct classifiers and none have attempted to quantitatively combine histology (imaging) and proteomic (non-imaging) measurements for making diagnostic and prognostic predictions. The objective of this work is to create a common subspace to simultaneously accommodate both the imaging and non-imaging data (and hence data corresponding to different scales and dimensionalities), called a metaspace. This metaspace can be used to build a meta-classifier that produces better classification results than a classifier that is based on a single modality alone. Canonical Correlation Analysis (CCA) and Regularized CCA (RCCA) are statistical techniques that extract correlations between two modes of data to construct a homogeneous, uniform representation of heterogeneous data channels. In this paper, we present a novel modification to CCA and RCCA, Supervised Regularized Canonical Correlation Analysis (SRCCA), that (1) enables the quantitative integration of data from multiple modalities using a feature selection scheme, (2) is regularized, and (3) is computationally cheap. We leverage this SRCCA framework towards the fusion of proteomic and histologic image signatures for identifying prostate cancer patients at the risk of 5 year biochemical recurrence following radical prostatectomy. A cohort of 19 grade, stage matched prostate cancer patients, all of whom had radical prostatectomy, including 10 of whom had biochemical recurrence within 5 years of surgery and 9 of whom did not, were considered in this study. The aim was to construct a lower fused dimensional metaspace comprising both the histological and proteomic measurements obtained from the site of the dominant nodule on the surgical specimen. In conjunction with SRCCA, a random forest classifier was able to identify prostate cancer patients, who developed biochemical recurrence within 5 years, with a maximum classification accuracy of 93%. The classifier performance in the SRCCA space was found to be statistically significantly higher compared to the fused data representations obtained, not only from CCA and RCCA, but also two other statistical techniques called Principal Component Analysis and Partial Least Squares Regression. These results suggest that SRCCA is a computationally efficient and a highly accurate scheme for representing multimodal (histologic and proteomic) data in a metaspace and that it could be used to construct fused biomarkers for predicting disease recurrence and prognosis.
    BMC Bioinformatics 12/2011; 12(1):483. DOI:10.1186/1471-2105-12-483 · 2.67 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: There is a growing need to localize prostate cancers on magnetic resonance imaging (MRI) to facilitate the use of image guided biopsy, focal therapy, and active surveillance follow up. Our goal was to develop a decision support system (DSS) for detecting and localizing peripheral zone prostate cancers by using machine learning approach to calculate a cancer probability map from multiparametric MR images (MP-MRI). This IRB approved Health Insurance Portability and Accountability Act compliant retrospective study consisted of 31 patients (mean age and serum prostate specific antigen of 60.4 and 6.62 ng∕ml, respectively) who had MP-MRI at 3 T followed by radical prostatectomy. Seven patients were excluded due to technical issues with their MP-MRI (e.g., motion artifact, failure to perform all sequences). Cancer and normal regions were identified in the peripheral zone by correlating them to whole mount histology slides of the excised prostatectomy specimens. To facilitate the correlation, tissue blocks matching the MR slices were obtained using a MR-based patient-specific mold. Segmented regions on the MP-MRI were correlated to histopathology and used as training sets for the learning system that generated the cancer probability maps. Leave-one-patient-out cross-validation on the cancer and normal regions was performed to determine the learning system's efficacy, an evolutionary strategies approach (also known as a genetic algorithm) was used to find the optimal values for a set of parameters, and finally a cancer probability map was generated. For the 24 patients that were used in the study, 225 cancer and 264 noncancerous regions were identified from the region maps. The efficacy of DSS was first determined without optimizing support vector machines (SVM) parameters, where a region having a cancer probability greater than or equal to 50% was considered as a correct classification. The nonoptimized system had an f-measure of 85% and the Kappa coefficient of 71% (Rater's agreement, where raters are DSS and ground truth histology). The efficacy of the DSS after optimizing SVM parameters using a genetic algorithm had an f-measure of 89% and a Kappa coefficient of 80%. Thus, after optimization of the DSS there was a 4% increase in the f-measure and a 9% increase in the Kappa coefficient. This DSS provides a cancer probability map for peripheral zone prostate tumors based on endorectal MP-MRI. These cancer probability maps can potentially aid radiologists in accurately localizing peripheral zone prostate cancers for planning targeted biopsies, focal therapy, and follow up for active surveillance.
    Medical Physics 07/2012; 39(7):4093-103. DOI:10.1118/1.4722753 · 3.01 Impact Factor
Show more