Article

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).

4 Followers
 · 
194 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Prostate cancer (PCa) is the most commonly diagnosed cancer among men in the United States. In this paper, we survey computer aided-diagnosis (CADx) systems that use multiparametric magnetic resonance imaging (MP-MRI) for detection and diagnosis of prostate cancer. We review and list mainstream techniques that are commonly utilized in image segmentation, registration, feature extraction, and classification. The performances of 15 state-of-the-art prostate CADx systems are compared through the area under their receiver operating characteristic curves (AUC). Challenges and potential directions to further the research of prostate CADx are discussed in this paper. Further improvements should be investigated to make prostate CADx systems useful in clinical practice.
    BioMed Research International 12/2014; 2014:789561. DOI:10.1155/2014/789561 · 2.71 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: There is a renewed interest in MR-guided laser interstitial thermal therapy (LITT) as a minimally invasive alternative to craniotomy for local treatment of various brain tumors and epilepsy. LITT allows for focused delivery of laser energy monitored in real time by MRI, for precise ablation of the lesion. Although highly promising, the long-term effects of laser ablation as a viable treatment option for neurological disorders have yet to be rigorously studied and quantified. In this work, we present a quantitative framework for monitoring per-voxel thermal-induced changes post-LITT over time on multi parametric MRI. We demonstrate that voxel-by-voxel quantification of MRI markers over time can enable a careful and accurate (a) characterization of early LITT-related changes (if and when they are exaggerated and when they subside), and (b) identification and monitoring of MRI markers that potentially allow for better quantification of response to LITT therapy. The framework was evaluated on two distinct cohorts of patients (GBM, epilepsy), who were monitored post-LITT at regular time-intervals via multi-parametric MRI. On a cohort of six GBM studies we found that (a) it may be important for the initial treatment-related changes to subside to more reliably capture MRI markers relating to tumor recurrence, and (b) T1w MRI and T2-GRE may better differentiate changes that may correspond to tumor recurrence from patients with no recurrence, as compared to T2w-MRI, and FLAIR. Similarly, our preliminary analysis of four epilepsy studies suggests that (a) early LITT changes (attributed to swelling, edema) appear to subside within 4-weeks post-LITT, and (b) ADC may be more reflective of early treatment changes (up to 1 month), while T1w may be more reflective of early delayed treatment changes (1 month, 3 months), while T2-w and T2-FLAIR appeared to be more sensitive to late treatment related changes (6-months post-LITT) compared to the other MRI protocols under evaluation.
    PLoS ONE 12/2014; 9(12):e114293. DOI:10.1371/journal.pone.0114293 · 3.53 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this work, we present a new methodology to facilitate prediction of recurrent prostate cancer (CaP) following radical prostatectomy (RP) via the integration of quantitative image features and protein expression in the excised prostate. Creating a fused predictor from high-dimensional data streams is challenging because the classifier must 1) account for the “curse of dimensionality” problem, which hinders classifier performance when the number of features exceeds the number of patient studies and 2) balance potential mismatches in the number of features across different channels to avoid classifier bias towards channels with more features. Our new data integration methodology, supervised Multi-view Canonical Correlation Analysis (sMVCCA), aims to integrate infinite views of highdimensional data to provide more amenable data representations for disease classification. Additionally, we demonstrate sMVCCA using Spearman's rank correlation which, unlike Pearson's correlation, can account for nonlinear correlations and outliers. Forty CaP patients with pathological Gleason scores 6-8 were considered for this study. 21 of these men revealed biochemical recurrence (BCR) following RP, while 19 did not. For each patient, 189 quantitative histomorphometric attributes and 650 protein expression levels were extracted from the primary tumor nodule. The fused histomorphometric/proteomic representation via sMVCCA combined with a random forest classifier predicted BCR with a mean AUC of 0.74 and a maximum AUC of 0.9286. We found sMVCCA to perform statistically significantly (p <; 0.05) better than comparative state-of-the-art data fusion strategies for predicting BCR. Furthermore, Kaplan-Meier analysis demonstrated improved BCR-free survival prediction for the sMVCCA-fused classifier as compared to histology or proteomic features alone.
    IEEE Transactions on Medical Imaging 09/2014; DOI:10.1109/TMI.2014.2355175 · 3.80 Impact Factor

Full-text (2 Sources)

Download
79 Downloads
Available from
May 28, 2014