A data-driven approach to prostate cancer detection from dynamic contrast enhanced MRI

Abstract

Magnetic resonance imaging (MRI), particularly dynamic contrast enhanced (DCE) imaging, has shown great potential in prostate cancer diagnosis and staging. In the current practice of DCE-MRI, diagnosis is based on quantitative parameters extracted from the series of T1-weighted images acquired after the injection of a contrast agent. To calculate these parameters, a pharmacokinetic model is fitted to the T1-weighted intensities. Most models make simplistic assumptions about the perfusion process. Moreover, these models require accurate estimation of the arterial input function, which is challenging. In this work we propose a data-driven approach to characterization of the prostate tissue that uses the time series of DCE T1-weighted images without pharmacokinetic modeling. This approach uses a number of model-free empirical parameters and also the principal component analysis (PCA) of the normalized T1-weighted intensities, as features for cancer detection from DCE MRI. The optimal set of principal components is extracted with sparse regularized regression through Least Absolute Shrinkage and Selection Operator (LASSO). A support vector machine classifier was used with leave-onepatient-out cross validation to determine the ability of this set of features in cancer detection. Our data is obtained from patients prior to radical prostatectomy and the results are validated based on histological evaluation of the extracted specimens. Our results, obtained on 449 tissue regions from 64 images, show that the proposed data-driven features outperform the traditional pharmacokinetic parameters with an area under ROC of 0.86 for LASSO-isolated PCA parameters, compared to 0.78 for pharmacokinetic parameters. This shows that our novel approach to the analysis of DCE data has the potential to improve the multiparametric MRI protocol for prostate cancer detection.

Head and Neck Cancer Tumor Segmentation Using Support Vector Machine in Dynamic Contrast-Enhanced MRI

“…Before extracting the features from the TIC in the DCE-MRI images, we performed the normalization as [8]$\begin{array}{c}T1i_{\mathrm{r}\mathrm{e}\mathrm{a}\mathrm{l}}\left(t\right)=\frac{i_n\left(t\right)-i\left(\mathrm{p}\mathrm{r}\mathrm{e}\right)}{i\left(\mathrm{p}\mathrm{r}\mathrm{e}\right)},\end{array}$where i real ( t ) denotes the final normalized TIC, i n ( t ) denotes the original TIC, and i (pre) denotes the average intensity in the first eight scans (before the injection of contrast agent) of i n ( t ).…”

Scandent Tree: A Random Forest Learning Method for Incomplete Multimodal Datasets

“…We used the apparent diffusion coefficient (ADC) from diffusion MRI, and three pharmacokinetic parameters from DCE MRI: volume transfer constant, k trans , fractional volume of extravascular extracellular space, v e , and fractional plasma volume v p [10,11].…”

Identification of Potential MR-Derived Biomarkers for Tumor Tissue Response to 177Lu-Octreotate Therapy in an Animal Model of Small Intestine Neuroendocrine Tumor

“…Few studies have used feature selection techniques for the purpose of unraveling the most efficacious subset of high-dimensional MR feature sets. However, in a recent study on prostate cancer diagnostic performance, Haq et al applied the lasso method to find the optimal set of principal components from T1 intensities and semiquantitative DCE-MRI features, and found that the set produced by the lasso method outperformed traditional pharmacokinetic parameters in receiver operating characteristic tests of diagnostic performance [51] . Based on our literature review, there seems to be no previous studies that combine the lasso method with data imputation in the repetitive manner for statistical evaluation, as done by us.…”